Forthcoming and Online First Articles

International Journal of Biomedical Engineering and Technology

International Journal of Biomedical Engineering and Technology (IJBET)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Biomedical Engineering and Technology (52 papers in press)

Regular Issues

  • Monitoring optical responses and physiological status of human skin in vivo with diffuse reflectance difference spectroscopy   Order a copy of this article
    by Jung Huang, Jyun-Ying Chen 
    Abstract: Fourier-transform visible-near infrared spectroscopy was applied to analyse diffuse reflectance from human skin perturbed with three skin-agitating methods. Principal component analysis (PCA) was applied to deduce three characteristic spectral responses of human skin. Based on Monte Carlo multilayer simulation, the responses can be attributed to changes in light scattering and haemoglobin and melanin content. The eigenspectra form a basis for resolving the optical responses of human skin from diffuse reflectance difference spectra measured at different time points after the skin tissue is mechanically stressed. We demonstrate that by applying this analysis scheme on in vivo measured diffuse reflectance difference spectra, valuable information about the responses of skin tissue can be deduced and thereby the physiological status of skin can be monitored.
    Keywords: diffuse reflectance spectroscopy; skin tissue; optical response; monte-carlo simulation; principal component analysis.

  • A wearable system to analyze tremors in the presence of external stressors   Order a copy of this article
    by Vanitha K M, Viswanath Talasila, Narasimha Prasad L V 
    Abstract: This paper focuses on the development of a low-cost wearable sensing system to detect physiological and pathological tremors. The spirogram analysis for tremor detection is performed in a novel setting. In addition, the designed wearable system is capable of analyzing tremor in other functional task contexts, apart from just handwriting analysis. Further, subjects are exposed to external stressors before they perform the spirogram task. Our results present a preliminary indication that motor control degradation, beyond a certain level of external stressors, may be limited.
    Keywords: Tremor; Physiological Tremor; Pathological Tremor; Rehabilitation; Spirogram.
    DOI: 10.1504/IJBET.2020.10042785
  • Assessment of Meditation Effects Using Heart Rate Variability Analysis   Order a copy of this article
    by Aboli Londhe, MIthilesh Atulkar 
    Abstract: Meditation claimed to regularize the autonomic nervous system (ANS) and causes reduced metabolic movement, inciting physical and mental relaxation. It is being looked upon as the future integrative mean of improving quality of life. The most accessible organ for assessment of ANS activities is heart and its oscillations. The heart rate variability (HRV) analysis has been emerged as a successful non-invasive method elucidate changes of sympathetic and vagal activity. The alternations of a heart are complex and constantly changing, which allows the cardiovascular system to rapidly adjust to sudden physical and psychological changes. In this paper, the exhaustive overview of HRV analysis attempts for evaluating meditation effects is presented. Moreover, The HRV metrics, their clinical significance, applications and reported usefulness in meditation assessment are presented.The variations in HRV have been analyzed using both linear and nonlinear parameters for both meditators and non-medidators.The effect of two meditation techniques namely, Chi and Kundalini Yoga meditation on HRV has been investigated extensively and significance of these techniques have been evaluated using statistical analysis.
    Keywords: Meditation; Heart Rate Variability; Linear; Non-Linear; Chi; Kundalini Yoga.

  • Automated pathological lung volume segmentation with anterior and posterior separation in X-ray CT images   Order a copy of this article
    by Anita Khanna, Narendra D. Londhe, S. Gupta 
    Abstract: 3D volume lung segmentation is a precursor for morphometric and volumetric analysis. The proposed work is a fully automated lung segmentation method with due attention given to left and right lung separation in the anterior and posterior sections involving new concept of bounding box. The method proceeds in three steps: firstly, lung segmentation performed with morphological operations. Secondly airways extracted using 3D region growing. Finally, left and right lung lobes separated by analysing bounding box characteristics of each image. The performance matrices and net volume of lung have been evaluated with manual analysis and the results are quite satisfactory with average F1 score 0.983, precision 0.989, recall 0.976, specificity 0.998 and Jaccard index 0.965 and comparative lung volumes. The proposed method showed the consistency with reliability index of 97.72%. The time taken for complete segmentation for each subject is between 60-70 sec on Intel Core i7-8750H, CPU @ 2.20 GHz.
    Keywords: computed tomography; 3D lung segmentation; region growing; airways detection; bounding box; reliability index.

  • Automated detection and grading of prostate cancer in Multiparametric MRI   Order a copy of this article
    by Prashant Kharote, Manoj Sankhe, Deepak Patkar 
    Abstract: The objective of this paper is to develop a transparent and meticulous feature learning framework for prostate cancer detection and grading of prostate cancer using Multiparametric Magnetic Resonance Images (mpMRI). Automated segmentation of prostate from MRI is crucial task in image guided intervention. Prostate cancer is confined by applying approved rules for prostate cancer diagnosis from mpMRI data. The clustering is performed on Apparent Diffusion Coefficient (ADC) and Diffusion Weighted Images (DWI) to obtain a probabilistic map which confirms cancerous region. The performance of presented method is enormously figured out on the dataset that contains T2-Weigted, DWI and ADC map images of 236 subjects. Total 218 regions included for analysis with 53 non-cancerous regions and 165 cancerous lesions. We obtained tumor detection accuracy of 93.2% and AUC of 0.94 by using random forest classifier. The results yield by proposed algorithm is validated by two experienced radiologists. rn
    Keywords: Prostate; segmentation; deformable model; multiparametric magnetic resonance imaging (MPMRI); atlas based segmentation; active contour model; deep learning; PIRADS; prostate cancer; classifier.

  • Rapid Detection of COVID-19 from Chest X-Ray Images using Deep Convolutional Neural Networks   Order a copy of this article
    by Sweta Panigrahi, U.S.N. Raju, Debanjan Pathak, Kadambari K.V., Harika Ala 
    Abstract: The entire world is suffering from the corona pandemic (COVID - 19) since December 2019. Deep Convolutional Neural Networks (Deep CNN) can be used to develop a rapid detection system of COVID-19. Among all the existing literature, ResNet50 is showing better performance, but with three main limitations i.e., 1. Overfitting, 2. Computation cost, and 3. Loss of feature information. To overcome these problems authors have proposed four different modifications on ResNet50, naming it as LightWeightResNet50. An image dataset containing Chest X-ray images of coronavirus patients and normal persons is used for evaluation. 5-fold cross-validation is applied with transfer learning. Ten different performance measures (True Positive, False Negative, False Positive, True Negative, Accuracy, Recall, Specificity, Precision, F1-Score and Area Under Curve) are used for evaluation along with fold-wise performance measures comparison. The four proposed methods have an accuracy improvement of 4%, 13%, 14% and 7% respectively when compared with ResNet50.
    Keywords: COVID-19 Diagnosis; Chest X-Ray images; Deep CNN; Transfer Learning; Cross-validation.

  • Evaluation of protein/polysaccharide blend biopolymeric material for fabrication of drug eluting wound dressing   Order a copy of this article
    by Shailendra Shera, R.M. Banik 
    Abstract: Silk fibroin protein and polysaccharide xanthan was mixed in three ratios i.e 80:20 (SFX82), 60:40 (SFX64) and 50:50 (SFX55) to fabricate blended dressing and functionalized with antibiotic amoxicillin. The dressings exhibited sustained release of incorporated antibiotics for prolonged period which helped in maintaining therapeutic concentrations of drug for quick wound recovery. The dressings showed biphasic release profile i.e. burst followed by sustained release. SFX64 showed highest cumulative drug release among all three dressing. Further, SFX64 exhibited smoother surface leading to less bacterial adhesion. Changes in wound size and histological assessments of wound tissues over time confirmed that amoxicillin loaded dressings showed faster healing, higher wound closure rate, regular and thicker formation of epidermis. SFX64 dressing was the best performer with pronounced sustained delivery of antibiotic at therapeutic concentration, smoother surface, and maximum wound recovery of 99.12
    Keywords: Silk fibroin; Xanthan; Blends; Biphasic; Wound healing; Wound dressing; Sustained drug release; Bacterial adhesion; Invivo wound healing; Histology.

  • A Review on Wheelchair and Add-in Devices Design for Disabled   Order a copy of this article
    by SATEESH REDDY AVUTU, Sudip Paul, Venkateswara Reddy B 
    Abstract: Owing to rapidly aging populations and rising road accidents, the daily use of wheelchairs, which has become necessary to aid mobility for the disabled, is growing globally. The patients with spinal cord injuries, cerebral palsy, and those inflicted with seizures need a wheelchair. The authors expect that the information gathered within this research will enhance the understanding of modern-day wheelchair requirements. This article presents the global research campaign, starting with a debut to the wheelchair and the communities they serve. Technological inventions focus on probably the most researched regions, creating one of the most interesting for future research and development. This article reviews the role of wheelchairs for different disabilities by examining its respective merits and demerits. It highlights the gap between the associated technological features and capabilities, including the navigation and motion control methods, pros and cons of indoor-outdoor navigation on different surfaces such as standard, sandy, muddy and hilly terrain when using a wheelchair. Concerns related to the improvement of the disabled, their living conditions have concluded.
    Keywords: Assistive Device; Ergonomic Design aspects; Indoor-Outdoor Navigation; Rehabilitation; Wheelchair Technologies.

  • Mammograms enhancement based on multifractal measures for microcalcifications detection   Order a copy of this article
    by Nadia Kermouni Serradj, Messadi Mahammed, Lazzouni Sihem 
    Abstract: The breast cancer is the most common cancer in women and represents its leading cause of death in the world [1]. The microcalcifications (MCs) are the essential signs of precancerous cells. Their small size makes them difficult to detect and locate, hence the need of developing Computer Aided Detection (CAD) systems for early detection of breast cancer. In this paper, an approach of MCs detection is proposed. Our system includes three phases. In the first, we start by a preprocessing step to remove various noises, followed by a step of intensity enhancement based on the haze removal algorithm. The third step is based on multifractal measures to construct the ?-image which enhance MCs contrast. The proposed method was tested on three databases with a set of 371 images and evaluated in terms of PSNR and sensitivity. The obtained results are very significant and better compared to other approaches proposed in the literature.
    Keywords: multifractal measure; contrast enhancement; microcalcifications; mammogram images.

  • A Review on Prediction of Diabetes using Machine Learning and Data mining Classification Techniques   Order a copy of this article
    by Abhilash Pati, Manoranjan Parhi, Binod Kumar Pattanayak 
    Abstract: Machine Learning (ML) and Data Mining (DM) techniques have grown in popularity among the researchers and scientists in various fields. Healthcare industry could not be an exception to it. ML and DM have become the powerful tools in prediction of various diseases. Diabetes or Diabetes Mellitus, a gaggle of metabolic disorder, can be caused due to age, obesity, lack of exercise, hereditary diabetes, living style, bad diet, hypertension, etc. and for that the entire body system can be affected harmfully and be able to capture dangerous diseases like heart disease, kidney disease, stroke, eye problem, nerve damage, etc. For this, we tried to go for a systematic review on diabetes by applying ML and DM classification algorithms for prediction and diagnosis. From the study, it may be concluded that Random Forest (RF) and Support vector machine (SVM) are to be the most successful and widely used methods for predicting diabetes. Concerning the sort of knowledge, medical datasets as well as Pima Indian Diabetes Datasets (PIDDs), provided by the UCI-ML Repository, were mainly used. This survey has been done on the applications of ML and DM classification approaches that may be useful for further investigation in predictions and resulting valuable knowledge on Diabetes.
    Keywords: Diabetes Mellitus; Prediction; Machine Learning (ML); Data Miningrn(DM); Classification Techniques.
    DOI: 10.1504/IJBET.2023.10051282
  • Suicidal Behaviour Screening using Machine Learning Techniques   Order a copy of this article
    by Anju Bhandari Gandhi, Devendra Prasad, Umesh Kumar Lilhore 
    Abstract: In a fast-growing world, patients of anxiety and depression are more vulnerable to attempt an obnoxious step like suicide. Therefore periodic screening of these patients can be done for their wellbeing as well as to stop the negative flow of energy. We aimed to explore the potential of Machine Learning to identify and predict Suicidal Behavior in patients with anxiety and stress by comparing the performance of Machine Learning Algorithms (Logistic Regression, Random Forest, Decision Tree, Multi-layer Perceptron Classifier). The analysis is performed using a python programming language for the screening of patients aiming to predict the risk of suicides. Random forest classifier outperforms with an accuracy of 95%. This current research work leverages the application of machine learning in the domain of the healthcare sector in the automated screening of patients. This Artificial Intelligence based solution reduces time consumption. This present kind of analysis can affect a remarkable monitoring system for healthcare departments.
    Keywords: Machine Learning; Suicidal features; Jupyter; depression; counselling.

  • A Convex Optimization Approach to Parallel Magnetic Resonance Imaging Reconstruction   Order a copy of this article
    by Ifat Al Baqee 
    Abstract: In parallel magnetic resonance imaging (pMRI), the image reconstruction with unknown coil sensitivity functions is known as a non-convex problem in the existing literatures. The analysis of this paper shows that there exists a convex solution region in the space of the magnitude image and sensitivity encoded image functions, which contains the true magnitude image solution. The derivation of the convex solution region resolves the non-convex difficulty and leads to a convex optimization formulation of the pMRI reconstruction problem. The formulated problem consists of two steps. Each of the steps solves a regularized convex optimization problem and provides a globally optimal solution, in the sense that the solution optimizes the performance index and is independent of the initial conditions. The applications of the proposed two-step optimization to in-vivo and phantom data sets result in superior pMRI reconstruction performance compared with state-of-the-art algorithms.
    Keywords: Medical imaging; Parallel magnetic resonance imaging; MRI reconstruction; Convex optimization; Regularized optimization.

  • Thermo Regulated Infant Warming Wrapper with infrared light emitting diodes for prevention of hypothermia in preterm low birth weight babies   Order a copy of this article
    by Sarath S Nair, Nagesh D S 
    Abstract: Preterm born babies having low birth weight are subjected to heavy loss of heat due to inadequate fat deposit under their skin. This creates a reduction in core body temperature to below physiologically tolerable levels and eventually ends up in cold stress or hypothermia. In this paper, an improved method for providing a thermo neutral environment is provided making the best use of the thermal insulating properties of the polyethylene and poly urethane foam with embedded infrared light emitting diodes. Bench top testing shows the device has an average warming time of 15 minutes and retains the temperature to more than 24 hours. The warmer is tested to provide reliable operation for more than three-month period within which the baby is expected to gain normal weight. The efficacy, safety and performance of the device is tested as per international standards and results are produced. The wrapper can improve the healthcare of the new-born at large, especially for developing countries.
    Keywords: Infant warmer; hypothermia; Incubator; phototherapy; radiant warmer.

  • Evaluation of chondrocyte culture in novel airlift bioreactor using Computational Fluid Dynamics (CFD) tools   Order a copy of this article
    by Aditya Anand, Sarada Prasanna Mallick, Ishan Saurav Chandel, Bhisham Narayan Singh, Pradeep Srivastava 
    Abstract: This study delineates the design of a novel airlift bioreactor (ALBR) with wavy draft tube, using computational fluid dynamics (CFD) for chondrocyte culture. The advantage of using wavy walled ALBR is that it enhances mass transfer when the optimum superficial gas velocity of 0.5 m sec-1 is applied. To simulate the gas-liquid flow and investigate the effects of wavy shape in the cylindrical draft tube in the internal loop of ALBR, Eulerian model in CFD was used. The correlation was established between the geometry of the ALBR and the hydrodynamics of the broth. The result of the experiment supports the fact that enhanced mixing with controlled shear in the bioreactor leads to better growth of the cell and also, significantly improves the oxygen transfer and mass transfer of nutrients by diffusion.
    Keywords: airlift bioreactor; chondrocyte; eulerian model; mass transfer; diffusion.

  • A Seamless Healthcare Platform for total Connectivity throughout the Patients Medical Journey   Order a copy of this article
    by Padmini Selvaganesan, Ajay Mahajan, Alex Russell, Anton Milo 
    Abstract: A smart patient healthcare interface platform is proposed that seamlessly follows the patient from the first consult, through surgery, and to recovery at home. Current state-of-the-art is very fragmented, and certain portions of the patients journey are not recorded for review by the clinicians, that if recorded could improve patient outcomes. The Seamless Healthcare Platform (SHP) is designed for integration to existing hospital electronic medical platforms. This is part of a grand vision to build connectivity between patients and clinicians such that there are no walls or boundaries while delivering quality healthcare at low-cost. A physical device was developed as a proof-of-concept, along with the software, and was validated at a hospital. It was shown that the data collected was reliable and useful in creating a two-way communication between the patient and the healthcare provider, thereby improving the overall quality of healthcare provided.
    Keywords: low-cost remote monitoring; patient-clinician connectivity; seamless healthcare.

  • A Comparative Analysis of Fall Risk Factors in Elderly and their Automatic Assessment   Order a copy of this article
    by Carolin Wuerich, Christian Wiede, Anton Grabmaier 
    Abstract: In the geriatric population, falls are a prevalent issue and can entail severe physical and psychological consequences. Fall risk assessment can provide early information in order to adopt prevention measures. However, there are many different reasons why a person might fall ranging from muscolosceletal deficits to cognitive, mental or sensory impairments, and cardiovascular diseases. While the majority of the approaches on fall risk assessment are based on gait analyses, other methods have shown that including considerations of other possible causes can significantly improve the prediction. Thus, for the development of an effective fall risk assessment and to choose the appropriate interventions, the underlying causes need to be identified. This review provides an overview of fall risk factors in the elderly population outlining the correlations between the causes, symptoms and fall risk. Moreover, the state of the art of assessment methods for the identified risk factors as well as for fall risk in general is presented.
    Keywords: aging; automation; cognitive decline; elderly; fall prevention; fall risk; fall risk factors; physiological decline; risk assessment.

  • Isolation and characterization of copper resistant bacteria from khetri copper mines and analysis of the expression of copper-induced proteins   Order a copy of this article
    by Shraddha Mishra, Sanjay Kumar Verma 
    Abstract: The present study focuses on the isolation and characterization of copper-resistant bacteria from khetri copper mines and analysis of proteins expression under copper stress in selected isolate (KH-5) using SDS-PAGE analysis. A total of 14 different bacterial colonies (KH-1 to KH-14) were isolated on media containing 2 mM of copper and were further characterized for their biochemical properties. The cross-metal tolerance study exhibited their tolerance to other heavy metals (As, Zn, Ni, Co, and Cd) along with copper. The growth curve analysis of all the isolates showed a delay in the lag phase for KH-11, KH-12, KH-2, KH-3, KH-8, and KH-9 in comparison to other strains that indicate the more robust metal resistance mechanisms in other isolates. Based on the results of all these studies, KH-5 was selected for the study of protein expression in the presence of copper stress which showed the same protein band pattern as control (non-stressed condition) without induction of any new protein band in the stressed condition. This suggests the presence of a constitutive copper resistance mechanism in the KH-5. Thus, further studies can be done to explore the copper resistance mechanism in this isolate.
    Keywords: copper; tolerance; protein expression.

  • New Approach for Quality Analysis of the Hearing Impaired using Combined Temporal and Spectral Processing   Order a copy of this article
    by Hemangi Shinde, Vibha Vyas, Vikram C. M. 
    Abstract: This paper proposes a novel approach of combining temporal and spectral speech enhancement methods for Hearing Impaired (HI) listeners. The temporally processed speech is combined with five different types of Maximum a-Posterior (MAP) estimators, namely, Magnitude Squared Spectrum Estimator (MSSE), MSSE using posteriori SNR uncertainty, using priori SNR uncertainty, soft masking using posterior SNR uncertainty on magnitude squared spectrum and using priori SNR uncertainty on magnitude squared spectrum. The temporal, spectral and the combined temporal spectral algorithms are evaluated in terms of quality for HI listeners using noisy speech signals at -5, 0, 5 and 10 dB SNR in a cafeteria, a station, in traffic and train noise environments. The experimental results depict that the new combined temporal spectral algorithm showed significantly better results over the individual temporal, spectral methods as well as a previous combined temporal and spectral method investigated and tested by the author earlier for HI people.
    Keywords: Speech Enhancement; hearing impaired; temporal processing; spectral processing; mean opinion score.

  • An Insight into Phantom Sensation and the Application of Ultrasound Imaging to the Study of Gesture Motions for Transhumeral Prosthesis   Order a copy of this article
    by Ejay Nsugbe, Carol Phillips 
    Abstract: Transhumeral amputees account for the largest cohort of upper-limb amputees missing a substantial amount of their upper-limb, as per combined statistics with the UK and Italy. In this work, we utilise the human motor control theory, and Penfield homunculus as a basis for providing a review and school of thought behind phantom limb sensations, pain and associated therapy. Clinical work was also conducted on five non-amputated individuals using ultrasound imaging along the humerus while participants were instructed to produce a number of hand movements. This set of results has thus suggested that mainly compound gesture motions, which involve a degree of bulk muscular recruitment, can be detected along the humerus. It is foreseen that this set of gestures can be used to explore mobility and sensation of phantom limbs by clinical rehabilitation prosthetists.
    Keywords: Upper-Limb Prosthesis; Transhumeral Amputee; Ultrasound Imaging; Phantom Sensation; Homunculus; Cybernetics; Human Motor Control; Myoelectric Prosthesis; Medical Physics; Phantom Limb.

  • Histopathological Image Classification using Dilated Residual Grooming Kernel Model   Order a copy of this article
    by Ramgopal Kashyap 
    Abstract: Breast cancer is one of the main reasons for death among women. Deep learning and machine learning models are contributing to the early and accurate diagnosis of Breast cancer. This research aims to contribute the medical science and technology with the novel deep learning-based model to detect the small cancer cell and the precise diagnosis of the cancer cells. The proposed model takes breast cancer Histopathological Image Classification (BreakHis) and Breast Cancer Histopathological Annotation and Diagnosis (BreCaHAD) image dataset and performs strain normalization to solve the color divergence issues. After that, data augmentation with nineteen different parameters like scaling, rotation, flip, resize, gamma value is performed to solve the overfitting issues. The proposed Dilated Residual Grooming Kernel (DRGK) model is a 19-layer model that includes proposed multiscale dilated convolution (MSDC) unit. The MSDC unit uses the dilated convolutions to extract the features very effectively, to detect small objects and thin boundary without increasing the complexity. This unit combines three small units for extractions of low-level features like edge, contour, colors, detection of small objects and to enhance the receptive field without losing the image information; it makes the computation efficient. The proposed DRGK model accelerates the process along with MSDC unit and convolution, pooling, downsampling, and dilated convolution operations. The proposed model gives better performance in terms of accuracy, average precision score, precision, sensitivity, and f1 score. Experimental results show that the proposed method outperforms many state-of-the-art ones with the accuracy of 98.50%. The total memory required by the proposed model is 32.7 M where each number takes 4 bytes, so each image takes 32.7*4MB=130.8 M.B. of memory.
    Keywords: Breast Cancer; Channel attention model; Contrast limited adaptive histogram equalization; Data augmentation; Deep learning; Dilated convolution unit; Dilated residual growing kernel model; Dilated spatial convolution; Strain normalization.

  • Evaluation of Stress Distribution During Insertion of Tapered Dental Implant in Various Osteotomy Techniques: Three-dimensional Finite Element Study   Order a copy of this article
    by Bhavan Chand Yemineni, Jaideep Mahendra, Jigeesh Nasina, Little Mahendra, Lakshmi Shivasubramanian, Shareen Babu Perika 
    Abstract: Conventional osteotomy techniques in some cases can induce higher stress on bone during implant insertion, as a result of higher torque. The aim of the present study was to evaluate and compare the stress exerted on the underlying osseous tissues during the insertion of a tapered implant using different osteotomy techniques through a dynamic finite element analysis which has been widely applied to study biomedical problems through computer aided software. In three different types of osteotomy techniques namely conventional (B1), bone tap (B2), countersink (B3), five models and implants designed per technique were prepared, implant insertion was simulated and stress exerted by implant during each, was evaluated. Comparison of stress scores on the cortical and cancellous bone at different time points and time intervals from initiation of insertion to final placement of the implant was done. There was a highly statistically significant difference between B1 & B2 (p=0.0001) and B2 & B3 (p=0.0001) groups, whereas there was no statistically significant difference in the stress scores between B1 & B3 (p=0.3080) groups at all time points of implant placement. Overall, highly significant difference was observed between the stresses exerted in each technique. Within the limitations of our study, bone tap significantly exerted lesser stresses on the entire bone than conventional and countersink type of osteotomy procedures. Considering the stress distribution at the crestal region, countersink showed lower values in comparison with others.
    Keywords: FEA; finite element analysis; ANSYS; von mises; osteotomy; bone tap; countersink; cortical bone; cancellous bone; stress distribution; implant insertion; torque; mandible; dental implant; crestal bone.

  • Early Diagnosis of Alzheimer Disease using EEG Signals: The Role of Pre-processing   Order a copy of this article
    by Vinayak Bairagi, Sachin Elgandelwar 
    Abstract: Electroencephalograms (EEGs) have significant ability to measure the brain activity and have huge potential for the analysis of the brain diseases like Alzheimer disease (AD). EEG is a measurement of electrical signal generated from the neurons presents in the brain. These nonstationary EEGs signals show the sign of many current diseases or even give the warning about impending diseases. Three main effects of Alzheimer disease on EEG signal have been identified like signal slowing, reduction in EEG complexity and a change in the normal state of EEG synchrony. Brain computer interface (BCI) system gives a way for the detection of the preliminary stage of the Alzheimer disease based on nonlinear EEG signals. Pre-processing of the EEG decides the efficiency of this methodology. Artifacts must be removed before analyzing the EEG signals. Henceforth in recent year, pre-processing of EEG signals has got a great deal of enthusiasm for researchers. In this paper, state of art EEG pre-processing techniques is explored. This paper indicates clear and simple understanding of selected preprocessing techniques with respect to Alzheimer disease diagnosis.
    Keywords: Alzheimer Disease (AD); Electroencephalogram Signals (EEG); Independent Component Analysis (ICA); Filtering; Wavelet Transform.

  • A Survey on Data Mining and Machine Learning Techniques for Diagnosing Hepatitis Disease   Order a copy of this article
    by Tabeen Tasneem, Mir Md. Jahangir Kabir, Shuxiang Xu, Tazeen Tasneem 
    Abstract: With the advancement of technology in recent years,rndifferent new techniques are being used for classification andrnprediction of different complex diseases, as well as to analyzernbiomedical data in the medical field. Hepatitis is a liver diseasernthat has an adverse influence on people of any age group andrngenerally no symptoms appear. Hence, the diagnosis of hepatitisrnin the early stage becomes crucial. Use of technology can easernthe process and so researchers have proposed some classificationrntechniques for early detection of hepatitis. This paper aimsrnat summarizing the up-to-the-minute techniques used for therndiagnosis and prediction of hepatitis and in order to fulfill therngoal, numerous articles from 1996 to 2020 have been investigated.rnThis research work can be helpful to develop new techniques inrnfuture by knowing the pitfalls of the previous ones.
    Keywords: Hepatitis diagnosis; Data mining; Machine learning; Classification; Disease prediction.

  • Numerical Analysis of Artificial Hip Joints: Effect of Geometry   Order a copy of this article
    by Abhishek Kumar Singh, Abhishek Mishra 
    Abstract: The present work deals with the comparison analysis of solid and hollow hip joint implant. A three-dimensional finite element model of hip joint implant is developed using ANSYS 18.0 for determination of contact stresses, sliding distance and deformation caused due to loading on the joint in the standing condition. The finite element contact stresses generated on the contact surfaces of hip implant model along with the sliding distance has been used in for FEM analysis. Result of analysis shows that total deformation in the joint for smaller femoral head diameter is less for the hollow femoral head than solid femoral head, but as the size of the femoral head and other components are increased, total deformation in the hollow femoral head comes out as more than that of solid femoral head.
    Keywords: Artificial hip-joints; solid femoral head; hollow femoral head; FEM analysis.

  • An Ultrasonic sensor driven obstacle detection and localization system in 3D space for Visually Impaired Persons   Order a copy of this article
    by Bhupendra Singh 
    Abstract: There are several challenges faced by Visual Impaired persons while travelling through the outdoor environment. The white canernmost commonly used by them for obstacle detection in their route hasrnits limitation with the inability to detect obstacles above waist height.rnDue to this limitation head injury is very commonly faced by the VisuallyrnImpaired persons. In this work, we have developed eyeglasses whichrnconsist of two Ultrasonic sensors and two buzzers for obstacle detectionrnand localization. The location of the obstacle in 3D space is conveyedrnto the user with varying frequency patterns through the buzzers. The 3Drnlocation of the obstacle is conveyed in terms of laterality, elevation andrndepth information. Upon testing the system for the effectiveness in detecting the obstacle in 3D space, it is found as 70.5% laterality detectionrnrate, 70.5% elevation detection rate and 80.8% depth detection rate. Onrncomparing our results with similar results reported in the literature as arnstate of the art, our results outperform them all.
    Keywords: Assistive Technology,; Electronic Travel Aids; ;Healthcare,;rnSensors; ;Visual Impairment.
    DOI: 10.1504/IJBET.2021.10049267
  • Simulation of insufflation gas via an alternative Multi-functional Forceps with applications in Laparoscopic Surgeries   Order a copy of this article
    by Md. Abdul Raheem Junaidi, Harsha Sista, Daseswara Rao Yenduluri, Ram Chandra Murthy K 
    Abstract: Purpose: To simulate the gas flow in a multi-functional laparoscopic instrument using ANSYS FLUENT software. \r\nMaterial and Methods:The laparoscopic procedure used by surgeons is a minimally invasive surgery to operate upon the abdominal cavity. The Suction-Irrigation (S-I) process is used to clean and disinfect the abdominal cavity to enable safe and efficient surgical intervention. In most surgeries, the dissector forceps are repeatedly exchanged with the S-I device to operate and clean the surgery site. The improved forceps is a combination of a suction-irrigator and a dissector forceps. \r\nResults:A more comprehensive CFD flow analysis of the improved forceps, the flow of CO2, is simulated in the present work for different driving pressures. The resulting flow rate of CO2 is compared among the prospective designs and the S-I device currently used. The results are investigated with the help of contours plots. \r\nConclusion:The new surgical forceps eliminates re-insertion of dissector with suction-irrigator and is reusable, multi-functional, non-toxic, corrosion-resistant, toughened, and cost-effective. In addition, this forceps aids in reducing the time of surgery, fatigue to the surgeon, and trauma to the patient. This can also potentially benefit in single port and robotic laparoscopic surgeries.\r\n
    Keywords: Computational Fluid Dynamics; Forceps; Newtonian; S-I device; Insufflator; multi-functional instrument.
    DOI: 10.1504/IJBET.2021.10048204
  • Development of non-contact optical device for monitoring neonatal jaundice based on the skin color of the upper trunk using skin reflectometry   Order a copy of this article
    by Vignesh Kumar Kanamail, Periyasamy R, Senthil Kumar K, Suresh Chelliya D, Senguttuvan D 
    Abstract: Jaundice occurs in new born babies within few days of birth due to elevated bilirubin levels in the blood and also the most common causes of hospital admission of young infants. In general, skin colour changes in new born are visually assessed and total serum bilirubin (TSB) level are measured through blood sampling method for identifying the severity of jaundice. Transcutaneous Bilirubin (TcB) is often preferred as an alternative method to avoid frequent blood sampling. However, this method has a challenge in dealing with neonates in countries of the Indian subcontinent where babies have distinctive skin colour. Hence the aim of this paper was to develop a non-invasive, non-contact handheld optical device (460nm LED light source and a photodiode) to measure bilirubin concentration in neonates of Indian subcontinent based on the skin reflectance. The device was tested with mock bilirubin samples (n=8), human blood serum samples (n=8) and on neonates in Neonatal Intensive Care Unit (n=39). The results were validated with TSB value and positive correlation factor of R =0.95 to 0.99 was observed between TcB and TSB by applying first order linear regression analysis. Therefore, the proposed indigenously developed device was successfully detected the jaundice by estimating the bilirubin concentration in neonates based on skin reflectance.
    Keywords: Neonatal Jaundice; Non-Invasive Bilirubin Monitoring; Optical method; Skin Reflectance; Transcutaneous Bilirubin.

  • Implementation of machine learning algorithms for automated human gait activity recognition using sEMG signals   Order a copy of this article
    by Ankit Vijayvargiya, Balan Dhanka, Vishu Gupta, Rajesh Kumar 
    Abstract: Recognition of various human gait activities based on the sEMG signal has an important role to control the exoskeleton or prosthesis. These robotic assistive devices are used for enhancing the physical performance of an injured or disabled person. In this paper, a comparative assessment of various computational classifiers is presented for the recognition of different gait activities from the sEMG signal. Analysis of sEMG signal is complicated because of a multiple muscle contribute to a single activity and the effect of other muscles produces noise. So, first, we have applied the discrete wavelet transform to the sEMG signal based on the Daubechies wavelet and then extracted eleven-time domain features. Thereafter, features are standardized and fed to eight different computational classifiers. The performance indices of classifiers are calculated for ten runs. The results suggest that the MLP Classifier gives the highest accuracy (97.72%) in identifying different gait activities from sEMG signals.
    Keywords: Human Gait Activity Recognition; Discrete Wavelet Transform (DWT); Computational Classifier; Surface Electromyography (sEMG) Signal.

  • Differences in Kinematic Variables in Single Leg Stance test between young and elderly people   Order a copy of this article
    by David Perez Cruzado, Manuel Gonzalez Sanchez, Antonio Cuesta Vargas 
    Abstract: Background. Parameterising the Single Leg Stance test could be useful in clinical practice and basic research. The aim of the present study was to understand the intergroup and intragroup differences in kinematic variables among young adults and older adults in the performing of Single Leg Stance test. Methods. Two groups of participants were measured, 6 individuals over 65 years old and 6 individuals between 20-25 years old. Inertial sensors were located in the trunk and in the lumbar zone. Results. Significant differences between groups were found in the lumbar and trunk sensor in different movements (flexo/extension, inclination and rotation). Significant differences between the dominant and non-dominant leg were not found. Conclusion. There were significant differences between both groups. It is also important to highlight the excellent values of reliability of the inertial sensors.
    Keywords: elderly; aging; kinematics; balance; inertial sensor.

  • PPG based Windkessel Model Parameter Identification via Unscented Kalman Filtering   Order a copy of this article
    by Akhil Walia, Amit Kaul 
    Abstract: Modeling of arterial system is helpful in understanding the cardiovascularrnsystem and related ailments. Among various methods, Windkessel model is one approach which plays signi cant role in understanding the working principle of natural arterial system. The windkessel models describe the hydraulic properties of arterial system. In this paper, PPG based windkessel model has been suggested which utilizes PPG signal as measurement. State dynamics of proposed model has also been developed. The main contribution of this work lies on the identi cation of model parameters using Extended Kalman lter (EKF) and Unscented Kalman lter (UKF). Estimated parameters are compared with nominal values to validate model structures. The comparative analysisrnhas been carried out with the pre-existing method. Execution time taken to simulate the proposed model for modeling a single PPG pulse is approximately one second.
    Keywords: Windkessel model; Compliance; Inertance; Unscented Kalman Filter (UKF).

  • A novel hybrid system for detecting epileptic seizure in neonate and adult patients   Order a copy of this article
    by Ahmed Adda, Hadjira Benoudnine, Mohamed Daoud, Philippe Ravier 
    Abstract: Epilepsy is a brain disease characterized by recurrent seizures. Electroencephalography (EEG) is a prominent tool used in clinical routine for monitoring and diagnosing seizures. Visual inspection of EEG traces is a time-consuming and laborious process. The literature survey shows that though some advanced methods suggested for automatic seizure detection perform quite well in case of adult patients, they fail in discovering neonatal seizure activity, due to the fact that neonatal seizures are less prominent than adult seizures. Therefore, this research proposes a generalized automatic system for detecting seizures in epileptic patients regardless their ages. The proposed system takes advantage of hybridation between generalized Hurst exponent (GHE) and approximate entropy (ApEn) features extracted from the amplitude envelope of EEG signals. These features are taken as input parameters of the support vector machine (SVM) classifier, which distinguishes EEG signals based on the existence or not of seizures. In order to assess the generality of the proposed technique, binary test (normal vs. seizure) was achieved on two independent datasets, including Bonn University EEG database for adults and that of neonatal EEG collected at the Royal Womens Hospital, Brisbane, Australia. In the first dataset, our system detects seizures with an accuracy of 99 %, whereas in the second dataset, the proposed system reached an accuracy of 100%. The experimental results show that the proposed method demonstrates superiority to existing systems by solving the seizure detection tasks with a single automatic system, which shows very high accuracy for both neonate and adult patients. Such a system could help neurologists in the visual analysis, diagnosis of long-term EEG recordings and considerably reduces the time required for this process.
    Keywords: Electroencephalogram; epilepsy; seizure; Signal envelope; Hurst parameter; Entropy.

  • Fetal Brain Extraction using Mathematically Modelled Local Fetal Minima   Order a copy of this article
    by Durgadevi Paramasivam 
    Abstract: Division of the cerebrum from fetal MRI is a generally new field, with little work distributed on completely programmed preparation. Programmed mind division strategies produced for MRI of fetal brain images can\'t be straightforwardly applied to consider the creating fetal cerebrum in utero, since the fetal mind is altogether extraordinary regarding math just as tissue morphology. In this paper, the proposed segmentation techniques, to separate brain parcel from the MRI of the human embryo and in forthcomings days decided to determine the abnormality of the fetal brain at various gestational weeks. Lately, an assortment of division techniques has been proposed for the programmed depiction of the fetal and neonatal cerebrum MRI. These strategies mean to characterize areas of the premium of various granularities: mind, tissue types, or more limited constructions. Various philosophies have been applied for this division task and can be grouped into the solo, parametric, characterization, atlas combination, and deformable models. Cerebrum atlases are usually used as preparing information in the division interaction. Difficulties identifying with the picture securing, the quick mental health just as the restricted accessibility of imaging information anyway thwart this division task. This paper discusses fetal brain segmentation using mathematically modelled fetal brain minima by using a curve fitting segmentation technique. Broad tests show that the proposed approach beats the ebb and flow techniques explicitly Watershed extraction, Otsus extraction, Edge detection based extraction, and Histogram based extraction. The results dictated by applying the proposed calculation and results gained are significant
    Keywords: Fetal MRI; Brain Localisation; fetal minima; automatic; curve fitting; smoothing filter; thresholding; segmentation; Structural Similarity Index (SSIM). .

  • Depression Diagnosis Using a Hybrid Residual Neural Network   Order a copy of this article
    by Mahsa Ofoghi Rezaei, Somayeh Makouei, Sebelan Danishvar 
    Abstract: Depression is one of the most widespread psychiatric disorders. EEG signals can be utilized as a tool to diagnose depression objectively. This paper employs a hybrid method to classify healthy and depressed signals, which uses a pre-trained ResNet101 to extract features automatically. Thereby, the problem of designing and training deep networks for automatic feature extraction is solved. The hypothesis in the present study is that feature-extraction layers in ResNet101 also perform desirably in detecting depressed signals. In hybrid structures, SVM, KNN, and DT classifiers are used for final classification purposes. ResNet101-SVM, ResNet101-KNN, and ResNet101-DT structures have reached accuracy of 93.8%, 90.1%, and 82.1%, respectively. Moreover, for the ResNet101-SVM structure, which has shown the best performance among all structures, the accuracy, sensitivity, and specificity are 94.7%, 94.0%, and 95.2% after applying the 10-fold cross-validation method. The results indicate the proper performance of all structures, especially the ResNet101-SVM structure, in diagnosing depression.
    Keywords: Depression; Diagnosis; Classification; EEG; Deep learning; Residual network; Hybrid model; SVM; KNN; DT.

  • Design of Artificial Pancreas (AP) based on HGAPSO-FOPID Control Algorithm   Order a copy of this article
    by Akshaya Kumar Patra, Anuja Nanda 
    Abstract: This manuscript presents the design of Hybrid Genetic Algorithm-Particle Swarm Optimization-Fractional Order Proportional Integral Derivative (HGAPSO-FOPID) controller to inject the optimal dose of insulin through the AP for Blood Glucose (BG) regulation in Type-I Diabetes Mellitus (TIDM) patients. In this strategy, the controller parameters are tuned based on the Hybrid Genetic Algorithm Particle Swarm Optimization (HGAPSO) technique for better control execution. The productivity of the HGAPSO-FOPID controller as to accuracy, robustness and stability is tested by use of MATLAB and SIMULINK. The procured outputs reveal the better implementation of HGAPSO-FOPID controller to regulate the BG level within the range of normo-glycaemia (70 120mg/dl). The justification of improved control execution of the HGAPSO-FOPID controller is revealed by the relative result examination with other prominent control techniques.
    Keywords: BG level; AP; MID; HGAPSO-FOPID controller; diabetes.

  • Artificial Intelligence Methods for Image Classification Applied to Biological Sounds for the Early Diagnosis of Cardiorespiratory Pathologies and COVID-19 Infection   Order a copy of this article
    by Agostino Giorgio 
    Abstract: With the spread of the COVID-19 pandemic, the scientific community took prompt action to seek adequate solutions for the prevention and treatment of the disease. However, what seems less developed at present are methods for early diagnosis of the disease which would be useful especially when it is becoming more complicated towards interstitial pneumonia which is the main cause of ICU admissions and deaths. The aim of this work is to describe methods typically used for signal and image digital processing, especially artificial intelligence (AI) algorithms, which could allow a very early diagnosis of the onset of COVID-19 infection as well as many other respiratory and cardiac pathologies. For this purpose, at least for a first screening, the use of medium-capacity smartphones may also be sufficient, without the need to resort to expensive medical equipment and diagnostic tests that require long waiting times and are always onerous.
    Keywords: COVID-19; Artificial Intelligence; Digital Signal Processing; Matlab; Digital Medical Devices; Biological sounds; Auscultation.

  • Regression transfer learning for the prediction of three-dimensional ground reaction forces and joint moments during gait   Order a copy of this article
    by Goksu Avdan, Sinan Onal, Banafsheh Rekabdar 
    Abstract: Clinical gait analysis is a useful tool for assessing a patients walking conditions. Force platforms are gait analysis tools used to collect the ground reaction forces (GRFs); however, they are expensive and time-consuming. Therefore, this study focuses on the prediction of GRFs and joint moments without using force platforms. To address this problem, we proposed to combine deep learning methods with regression transfer learning (RTL). The inputs of the proposed method are joint angles and marker trajectories from a public dataset. Principal component analysis (PCA) has been used to reduce the data dimensionality to improve the computational time and prediction accuracy. A synthetic dataset has been generated to pre-train the deep learning method for transfer learning purpose. The experimental results indicate that the proposed transfer learning method increases the target domains learning process and can successfully predict the average GRFs and joint moments with 97.44% and 96.56% accuracy, respectively.
    Keywords: Regression transfer learning; Deep learning; 1D convolution neural network (1D CNN; Gait analysis; Ground reaction forces.

  • Diagnosing Cardiovascular Diseases from Photoplethysmograph: A Review   Order a copy of this article
    by Devaki V, Jayanthi Thiruvengadam 
    Abstract: The peripheral blood volume are the variations measured at the skin surface, using a source of light and a photo detector, which is performed by a non-invasive technology called Photoplethysmograph. At recent times, much interest has been shown by countless researchers worldwide to obtain valuable information from pulse waveform besides oxygen saturation measurement, pulse rate and heart rate evaluation. Photoplethysmograph based techniques are most preferable method for the wearable devices. Each derivative of pulse waveform carry beneficial information related to health. The evolution in the wearable cardiac monitoring devices has paved a way for the individualized medical care. The application of multi-spectral photoplethysmography in various areas of cardiovascular diseases such as myocardial infarction, arterial parameters estimation, arrhythmias, Heart Rate Variability detection (HRV) discussed by researchers are presented in this article. This review gives an extensive overview on currently improved technologies that are applied in cardiovascular disease diagnosis using multi-spectral photoplethysmograph
    Keywords: Cardio-vascular diseases; Non-invasive diagnosis; Photoplethysmography; Wearable devices; optical method; multi wavelength.

    by Seema , Jasbir Singh Saini, Sanjeev Kumar 
    Abstract: This paper introduces the implementation of a master slave configuration set up for robotic surgery. Image processing has been used for establishing the same. A hardware set up has been designed which interfaces with a GUI. The two work in conjunction to achieve the controlled movement of a robotic arm. The software section is divided into two sections basically, Image Dataset Selection and Validation and the development of a suitable GUI. The image dataset selected was a set of 140 MRI brain tumour related images. The designed GUI allows the surgeon to capture the patient live view and set an image for processing and using further. Also, the hardware setup is controlled from the master/ doctors end. This selected frame goes through the process of image segmentation method that had been selected and improved.
    Keywords: Haptics; master slave configuration; image processing.

  • Reduction in wear loss of Ultra-high molecular weight polyethylene composite under Human body temperature   Order a copy of this article
    by RAVIVARDHAN N A, Jagadish T 
    Abstract: Ultra-high molecular weight polyethylene (UHMWPE), a standard material used in artificial joints, generates wear debris when used in total hip replacement. In this study UHMWPE polymer reinforced with Multi-walled Carbon Nanotubes (MWCNT) has been developed to enhance the wear resistance property of the material. The compressed composite specimens were subjected to wear test at different load under room temperature and at 40C, i.e. close to human body temperature. This is the first report on the effect of human body temperature on wear properties of composite materials. Wear properties were studied for UHMWPE and UHMWPE-MWCNT composites. The study has confirmed a reduction in wear loss of UHMWPE by reinforcement with MWCNT and a high-level reduction in wear loss of the composite materials on exposure to human body temperature. The findings of this study have made a great contribution to joint transplantation therapy by providing valuable input regarding wear-resistant implant material.
    Keywords: Biomaterials; Composites; UHMWPE; MWCNT; wear loss.

  • Three Dimensional Reconstruction Of Brain Tumors From 2D MRI Scans: Optimized Curve Fitting Process   Order a copy of this article
    by Sushitha Susan Joseph, Aju Dennisan 
    Abstract: This paper intends to introduce a 3D reconstruction model along with the solution of curve fitting problem via optimization process. This helps the model to sustain the accurate construction by estimating the boundary, corner points etc. To make the better adjustment the parameters in the curve fitting process are optimized by a new Clan Updated Grey Wolf Algorithm (CUGWA), which is the hybrid version of conventional GWO and EHO algorithms. The boundary fitting is precisely done by considering the minimization of RMSE among original and fitted boundaries. Finally, performance of the adopted method is validated over other existing schemes with respect to curve fit analysis and convergence analysis.
    Keywords: 3D Reconstruction; Brain Tumor image; Parameterization; Bezier curve; Optimization.

  • An Investigation of Retinal Descriptors on Indian database for Automatic Pathological Diagnosis and Classification of Retinopathy of Prematurity   Order a copy of this article
    by Sushma Kadge, Sanjay Nalabalwar, Anil Nandgaonkar, Parag Shah, V. Narendran 
    Abstract: Early diagnosis is crucial to prevent blindness in preterm neonates. Scarcity of specialists indicates an urgent need for automated identification, classification and diagnosis of Retinopathy of Prematurity (ROP). Previous automation works didn't consider the classification of ROP stages which is an essential decision maker in treatment. We developed an automatic assessment system for ROP classification (AASRC) on Indian databases. We studied stochastic gradient descent (SGD) along with five other classifiers. 64 experiments were conducted to explore the intra database based on Gray-Level Co-Occurrence Matrix (GLCM) descriptors using various frequency based parameters for classification of ROP. Information gain (IG) scoring function is used to identify best descriptor while Students t-tests is used for validation. The classification accuracy rate of ROP disorder achieved are 99.03%, 93.87%, 94.55%, 92.51% and 97.95% respectively for Normal/Abnormal, Stage 1, Stage 2, Stage 3, and Stage 4. The experimental findings demonstrate the proposed feature descriptors and classifier outperforms state-of-the-art models.
    Keywords: Retinopathy of Prematurity; ROP Retina Image analysis; Classification; Stochastic gradient descent and GLCM.

    by Vijayakumari B, Vidhya S, Saraya J 
    Abstract: The long-lasting part in human body is teeth and even after the death of the person it remains un-affected. Hence in Forensic department, teeth play a crucial role to recognize a dead or missing person. In Forensic analysis, gender difference is a considerable course of action. Yet, gender identification with dental images using deep learning methods are still in research. An algorithm is proposed in this paper to find human gender using panoramic Dental X-ray Images (DXI). This work is organized as three sections such as Image Pre-processing, Gradient Based Recursive Threshold (GBRT) segmentation and classification. Initially, using prime magic square filter the unwanted noises are removed. Secondly, to perform segmentation GBRT is used. Finally with Resnet50 network, the gender is classified. The dataset of 285 dental images were taken and they are augmented to 4000 dental images and then they are separated as 3000 images for training and 1000
    Keywords: Gender classification; Dental radiographs; Morphological operations; GBRT segmentation; Deep CNN ResNet50 classified results.
    DOI: 10.1504/IJBET.2023.10050046
  • Diagnosis Results of Athletes with Ankle Joint Pain Based on the Neutrosophic Ensemble Image   Order a copy of this article
    by Guoqing Shi 
    Abstract: This article is mainly to study the diagnosis results of athletes with ankle joint pain based on the neutrosophic set of images. In the experiment of this research, the eutrophic ensemble image technology was used to diagnose and analyse the patients. At the same time, the PACS system in the construction method of medical image diagnosis knowledge base is used to realise medical image information management, integrate medical images, and improve the utilisation rate to diagnose patients with ankle joint pain. Through reconstructed image quality and EBCOT coding technology, the accuracy of medical images is improved. Compared with routine examination, the effect of medical imaging examination is much better. The diagnosis rate of patients is much higher than that of routine examinations, which also improves the satisfaction and trust of patients.
    Keywords: sports injuries; ankle joint pain; neutrosophic image; neutrosophic imaging; imaging diagnosis.
    DOI: 10.1504/IJBET.2023.10050485
  • Unveiling the potential of complex network in coronavirus proliferation study   Order a copy of this article
    by S. Sankararaman 
    Abstract: The development of novel methods for understanding virus replication is the need of the time of the COVID-19 pandemic. The present work proposes a novel surrogate graph-based method for understanding SARS-CoV-2 replication. Constructing a time history pattern (THP) matrix from the video of the virus interaction with normal cells, the inertia moment (IM) and complex network features are determined. The variation of IM and the graph features are correlated with the proliferation of SARS-CoV-2. Thus the work suggests the possibility of complex network and IM analyses to understand the kinetics of the virus infection.
    Keywords: graph theory; coronavirus; proliferation; inertia moment; complex network.
    DOI: 10.1504/IJBET.2022.10051583
  • CT and MRI Image Fusion Via Dual-Branch GAN   Order a copy of this article
    by Wenzhe Zhai, Wenhao Song, Jinyong Chen, Guisheng Zhang, Qilei Li, Mingliang Gao 
    Abstract: CT and MRI image fusion is a popular research field that plays a vital role in clinical diagnosis. To retain more salient features and complementary information from source images, we propose a dual-branch generative adversarial network (DBGAN) to fuse the CT and MRI images. The proposed DBGAN is designed in a dual branching structure schema, which consists of a couple of generators and discriminators. The generators and discriminators establish a generative adversarial relationship so that the fused images generated by the generators are indistinguishable from the discriminators. Furthermore, we employ the multiscale extraction module (MEM) and self-attention module (SAM) in the generators to enhance the salient features and detailed information of the fused images. The subjective and objective evaluation demonstrate the superiority of the proposed method over the state-of-the-art methods.
    Keywords: image fusion; generative adversarial network; CT/MRI image; healthcare.
    DOI: 10.1504/IJBET.2023.10051630
  • Retina blood vessels segmentation by combining deep learning networks   Order a copy of this article
    by Bachiri Mohamed Elssaleh, Adel Rahmoune, Faycal Rahmoune 
    Abstract: In this paper, we propose two deep learning architectures for the segmentation and detection of the vascular networks of blood vessels in fundus images. First, we combined VGG16 with U-net, then, we used Resnet 34 in combination with U-net. Both architectures employ an encoding and a decoding path. In this paper, we used the DRIVE and STARE databases. After applying VGG 16+U-net on the DRIVE database, we obtained the accuracy value of 0.96955, 0.79929 sensitivity, 0.98624 specificity, 0.9805 recall, and 0.9833 F1-Score. We applied VGG 16+U-net on STARE database and we got 0.95259 accuracy, 0.89996 sensitivity, 0.95530 specificity, 0.9933 recall, and 0.9742 F1-Score. Concerning Resnet 34 + U-net, we got the value of 0.9692 accuracy, 0.7859 sensitivity, 0.9870 specificity, 0.9794 recall, and 0.9832 F1-Score after applying on DRIVE database. Moreover, we got 0.9363 accuracy, 0.9335 sensitivity, 0.9246 specificity, 0.9961 recall, and 0.9649 F1-Score after we applied Resnet 34+U-net on STARE.
    Keywords: retinal segmentation; convolution neuron network; U-Net; deep learning; VGG 16; Resnet 34.
    DOI: 10.1504/IJBET.2022.10051639
  • Development of a mathematical correlation for polydisperse non-spherical drug particle deposition in the human upper respiratory system   Order a copy of this article
    by Sanaz Aghaei, Hassan Khaleghi 
    Abstract: Estimating the drug particle deposition in the upper respiratory system is essential to provide more effective treatment for respiratory diseases. This study numerically investigates the effect of both particle size distribution and particle shape on the total deposition efficiency in the human upper respiratory system. To investigate the effect of particle size distribution, spherical monodisperse and polydisperse particles are compared. Non-spherical polydisperse particles are also studied to investigate the effect of sphericity. It is concluded that by decreasing particle size and increasing particle sphericity, the total deposition efficiency decreases. This means that more particles escape from the upper airways to the bronchi and bronchioles. Therefore, for lung disease treatment, finer particles with higher sphericity are more suitable. Furthermore, a mathematical correlation is developed to represent the total deposition efficiency as a function of Stokes number and sphericity. This correlation estimates the deposition of both spherical and non-spherical polydisperse particles.
    Keywords: polydisperse particles; non-spherical particles; total deposition efficiency; mathematical correlation; idealised upper respiratory model.
    DOI: 10.1504/IJBET.2022.10051642
  • CT image super-resolution reconstruction via Pixel-Attention Feedback Network   Order a copy of this article
    by Jianrun Shang, Guisheng Zhang, Wenhao Song, Mingliang Gao, Qilei Li, Jinfeng Pan 
    Abstract: Computed tomography (CT) imaging has been widely used in clinical medicine, and high-resolution CT images play a crucial role in the determination of lesions. To fully excavate the contributive information of initial features and improve the feature representation ability of the model, we propose a pixel-attention feedback network (PAFNet) for CT image super-resolution reconstruction. Specifically, the PAFNet adopts multi-feedback network as backbone to make full use of initial features. Subsequently, a gated feedback (GF) block is introduced to refine the underlying features using the feedback features. To enrich the output characteristics and pay attention to essential details, a pixel attention mechanism is adopted to the self-calibration convolution. The subjective and objective evaluation demonstrate the superiority of the proposed method over the state-of-the-art approaches.
    Keywords: super-resolution; CT image; pixel attention; feedback network.
    DOI: 10.1504/IJBET.2023.10051832
  • Research and Design of Online Drug Mall System Based on SOA   Order a copy of this article
    by Yong Peng, Shi Wang 
    Abstract: The development of online drug mall system is getting faster and faster. However, when the online drug mall system expands various subsystems with different functions to meet various drug sales rules, the information interaction between each subsystem and the management of different systems have become a problem to be solved urgently. In view of this phenomenon, the traditional online drug mall system needs a unified integrated platform with simple structure and convenient management. We propose and develop an online drug mall system based on the SOA architecture, the SOA architecture can effectively improve concurrency, scalability, flexibility and low maintenance cost of the online drug mall system. The system fully implements the required functions, and has certain stability and reliability, and can provide users with a good user experience.
    Keywords: service oriented architecture; online pharmacy; data interaction; web service; distributed services.
    DOI: 10.1504/IJBET.2023.10052123
  • Asymmetry in People with Transtibial and Transfemoral Amputation for the Activities of Daily Living   Order a copy of this article
    by Mohammad Shah Faizan, Swati Pal 
    Abstract: Asymmetry between the prosthetic and the intact leg may cause discomfort and seriously deteriorate people’s quality of life. It is important to know the current status of asymmetry involved in the recent leg prosthetics so that efforts will be made to minimise it. In this paper, 31 articles that focus on the asymmetry in people with unilateral transtibial and transfemoral amputation were screened using PRISMA. The articles were further reviewed and computed for the symmetry index. The results revealed the presence of a high level of asymmetry during various activities performed. The level of asymmetry decreases with the activities associated with increasing speed. The microprocessor-controlled prosthetics have lesser asymmetry as compared to the non-microprocessor-controlled. The recent prosthetics were not fully effective in minimising the asymmetry, thus, more advanced research is needed in the design of prosthetics, by taking into consideration the varied nature of daily activities.
    Keywords: leg prosthetics; microprocessor-controlled prosthetics; non-microprocessor-controlled prosthetics; unilateral amputation; asymmetry; symmetry index; activities of daily living; biomedical devices.
    DOI: 10.1504/IJBET.2022.10052342
  • Automated Hard Exudate Segmentation using Neural Encoders and Attention Mechanisms for Diabetic Retinopathy Diagnosis   Order a copy of this article
    by Pratiksha Gawas, Sowmya Kamath S. 
    Abstract: Diabetic retinopathy (DR) is a complication caused by increased blood glucose levels, which causes retinal damage in diabetic patients’ eyes. If not discovered and treated early, it can lead to vision loss. Hard exudates (HE) is one its characteristic signs. Identification of HE is a paramount step in early diagnosis of DR. In this work, the suitability of U-Net-based deep CNN with different encoder configurations and attention gates (AG) is experimented, for HE segmentation. The proposed models were benchmarked on the standard IDRiD dataset. To overcome the challenges related to the limited dataset, data augmentation techniques were also applied to generate image patches and used for model training. Extensive experiments on the dataset revealed that U-Net with AG achieved an accuracy of 98.8%. The U-Net with ResNet50 as the encoder backbone achieved an accuracy of 98.64%. The findings show that the presented models are effective and suitable for early-stage clinical diagnosis.
    Keywords: hard exudate; hard exudate segmentation; neural encoders; attention mechanism; diabetic retinopathy; diabetic retinopathy prediction; medical informatics; deep learning.
    DOI: 10.1504/IJBET.2022.10052447

Special Issue on: Artificial Intelligence for Biomedical and Healthcare systems in IoT

  • Sports training on recovery of nerve function and nerve cell apoptosis in athletes with hemorrhagic brain injury   Order a copy of this article
    by Guoqing Shi 
    Abstract: This article carried out further research on whether sports training will recover after athletes’ brain injury and whether exercise will affect the apoptosis of nerve cells. The method is to reflect the real situation of the athletes by studying experimental mice during the experiment, we selected a total of 60 male and female mice, which were basically similar in weight, and divided them into several groups, and selected two of them as a reference. One group serves as an experiment and one group serves as a control. Each group is divided into seven hours after operation: 5 h, 10 h, 20 h, 40 h, 80 h, 7 d and 14 d. The total number of rats at each time point is 5 through experiments, we can find that the process of sports training is a beneficial process compared with the rats at the same time, and the rats’ recovery of bleeding is more obvious compared with the same.
    Keywords: exercise training; brain injury; nerve function recovery; nerve cell apoptosis; cerebral haemorrhage; medical system.
    DOI: 10.1504/IJBET.2022.10049710