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 Articles will not be published until the final proofs are validated by their authors.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.

International Journal of Biomedical Engineering and Technology (19 papers in press)

Regular Issues

  • Comparative Biomechanical Analysis of Lumbar spine in Trainees with Varied Barbell Positions: A Finite Element Study   Order a copy of this article
    by Diwei Chen, Datao Xu, Huiyu Zhou, Xuanzhen Cen, Yang Song, Dong Sun 
    Abstract: Considering various training goals, barbell squat variations like high bar back squat (HBBS) and front barbell squat (FBS) are popular. However, it's crucial to understand their differing effects on lumbar spine biomechanics. The objective is to comprehensively investigate the biomechanical mechanisms of lumbar during squatting movements. Data from 16 participants underwent analysis using musculoskeletal and finite element models. In the FBS, the lumbar vertebral joints exhibit a significantly greater extension angle compared to HBBS. Additionally, significant disparities in extension moment of the lumbar vertebral joints are observed between HBBS and FBS during the 0-26% and 34-77% phases of the movement. Moreover, Von Mises stress values on both the vertebrae and intervertebral discs are lower than those experienced in HBBS. The research results indicate that, with a focus on lumbar spine protection, FBS can effectively reduce the load on the lumbar spine under comparable conditions.
    Keywords: finite element model; lumber spine; squat exercise; lower back pain; kinetics; training injuries.
    DOI: 10.1504/IJBET.2024.10065991
     
  • Cardiac Disorder Classification: An Efficient Novel Deep Kronecker Neural Network with Sand Cat Swarm Optimisation Algorithm for Feature Selection   Order a copy of this article
    by Meghavathu S.S. Nayak, Hussain Syed 
    Abstract: Diagnosing a disease takes time and requires highly technical methods. These days, predicting and diagnosing cardiovascular disease (CVD) is crucial to lowering the death rate and catching them in early stages. Prior research employed machine learning (ML) techniques for disease prediction; however, adequate attention should have been paid to feature identification through appropriate methods for selecting features. This research introduced a novel deep learning (DL)-based deep Kronecker neural network (DKNN) for CVD classification. Essential features are extracted using the DenseNet-201 approach, and feature selection techniques help highlight the most important traits while reducing diagnosis costs. Therefore, the Sand Cat Swarm Optimization (SCSO) method is used to identify the most relevant features for diagnosing heart disease. Furthermore, the imbalanced data problem is resolved, and overfitting is decreased through cycle generative adversarial network (CGAN) based data augmentation. Differentiating from other approaches, the proposed approach obtains above 99% accuracy, precision, recall, and F1-score.
    Keywords: cardiovascular disease; CVD; deep Kronecker neural network; DKNN; DenseNet-201; sand cat swarm optimisation; SCSO; cycle generative adversarial network; CGAN.
    DOI: 10.1504/IJBET.2024.10066762
     
  • Automated Breast Cancer Segmentation and Classification in Mammogram Images Using Deep Learning Approach   Order a copy of this article
    by Dhanalaxmi B., Venkatesh N., Yeligeti Raju, G. Jagan Naik, Channapragada Rama Seshagiri Rao, V.Prema Tulasi 
    Abstract: One of the most prevalent cancers among women is breast cancer. The mortality rate of this cancer may be lowered with an early diagnosis. In the literature, a wide range of AI-based techniques have been proposed. Nevertheless, they face several difficulties, including inadequate training models, irrelevant feature extraction, and similarities between cancerous and non-cancerous regions. Therefore, we propose a novel improved deep learning based model for the segmentation and classification of breast cancer in this research. An enhanced UNet++ (EUNet++) model is used to segment the affected part of the lesion region. The improved ResNext (IResNext) model classifies mammogram images into benign and malignant classes. The findings showed that the suggested framework outperformed other models trained on the same dataset, achieving an exceptional 99.56% classification accuracy for the CBIS-DDSM dataset and 99.64% for the INbreast dataset.
    Keywords: Breast cancer; Deep learning; Enhanced UNet++; Improved ResNext; and data augmentation. The ResNet50V2 model extracts high-level statistical and texture data.
    DOI: 10.1504/IJBET.2024.10067021
     
  • Design, Optimisation and Pharmacodynamic Evaluation of Thymoquinone Nanosponges for the Treatment of Rheumatoid Arthritis   Order a copy of this article
    by Zuha Rahiqa, Preeti Karwa, Ayesha Syed, Ansari A.L.I. Ansari 
    Abstract: The seeds of the Nigella sativa (NS) plant contain a significant amount of bioactive substance called thymoquinone (TQ). It is non-toxic and has numerous potential uses in the treatment of human illnesses, such as cancer, diabetes. Since it is hydrophobic in nature it has limited medication solubility and lessens the negative effects of hepatic, gastrointestinal, rheumatoid, and asthma conditions. The goal of the current study is to optimise the solvent emulsion method for preparing TQ loaded nanosponge (TQ-NS) gel by employing the fundamentals of design of experiments. Particle size and entrapment efficiency (EE%) critical parameters were assessed using a hybrid design technique consisting of Mini Run Resolution IV design and Box-Behnken design. The improved TQ-NS was added to 1% w/w Carbopol gel along with an equivalent amount of TQ. The particle size, PDI, zeta potential, and EE% of improved TQ-NS formulations were 254.1
    Keywords: Thymoquinone; Rheumatoid Arthritis; Quality by Design; Box Behnken design; Nanosponges.
    DOI: 10.1504/IJBET.2024.10067231
     
  • Evaluation of Weight-Bearing, Walking Stability, and Gait Symmetry in Patients undergoing Restoration following Hip joint Fractures   Order a copy of this article
    by Anam Raza, Imran Mahmood, Tayyaba Sultana 
    Abstract: This study numerically quantifies patients' restoration following a range of hip joint fractures. Ground reaction force (GRF) data collected from 221 subjects was grouped into four conditions: hip coxa fracture (HC), pelvis fracture (HP), femur fracture (HF), and normal hip joint (NH). The GRF data were windowed into three subphases: initial double-limb support, single-limb support, and terminal double-limb support. During each subphase, the thresholds of mass normalised GRF were calculated for both fractured and intact limbs. The results showed a significant decline (p < 0.001) in walking stability and weight-bearing ability for all hip fractures. Furthermore, the fractured patients showed a massive increase in interlimb weight-bearing dependency (up to 20%) in the vertical direction in comparison to normal subjects, and a significant decrease in interlimb symmetries (up to 28%) in the anterior-posterior (AP) and medial-lateral (ML) directions. The methods and findings provide a comprehensive package to evaluate fracture restoration clinically using 3D-GRF.
    Keywords: fracture; weight-bearing; stability; gait; rehabilitation.
    DOI: 10.1504/IJBET.2024.10067401
     
  • Analysis of Fractal Dimension of Segmented Blood Vessels in Fundus Images Using U-Net Architecture   Order a copy of this article
    by Saranya M, Sunitha K.A, Sridhar P.Arjunan 
    Abstract: Precise segmentation of retinal blood vessels (RBVs) is pivotal in ophthalmology research, aiding in detecting diverse retinal abnormalities. This study proposes a contrast-limited adaptive histogram equalisation (CLAHE) technique to improve retinal image quality and visibility of microvascular structures. We aimed to determine the complexity of blood vessels using fractal dimensions (FD) and compare different metrics for their effectiveness. We employed the UNet architecture to separate blood vessels, and our results on the DRIVE retinal fundus image standard dataset showed an impressive accuracy rate of 97.24%, surpassing traditional filtering methods. Box counting, information, capacity, correlation, and probability dimensions are used in the FD analysis to help us understand the complex and irregular structures of retinal blood vessels. These metrics are valuable for detecting and monitoring retinal diseases in clinical settings. Our comparison with other techniques reveals promising results, particularly in the capacity and information dimensions, with statistical significance (P < 0.05). The potential of fractal dimensions as a screening tool for diabetic retinopathy underscores their importance in epidemiological studies.
    Keywords: blood vessels; fundus image; DRIVE dataset; filter techniques; U-Net architecture; fractal dimension; diabetic retinopathy; statistical analysis; deep learning.
    DOI: 10.1504/IJBET.2024.10067439
     
  • A Systems Pharmacology based ADME Profiling and Molecular Docking Analysis Unveils the Potential Role of Baicalein as the Natural Drug Candidate for Gallbladder Cancer   Order a copy of this article
    by Aakansha Singh, Anjana Dwivedi 
    Abstract: Phytochemicals show promising anti-cancer properties with minimal side-effects, offering an alternative to conventional chemotherapy. This work employs systems pharmacology and molecular docking techniques to examine Baicalein, Cirsimaritin, Hispidulin, Kaempferol, and Sinensetin as therapeutic candidates for gallbladder cancer (GBC). Using Swiss Target Prediction and public databases, 100 potential flavonoid targets and 880 GBCrelated DEGs were identified. Common genes were identified using Venny 2.1.0. GO and KEGG pathway analysis (p-value <0.05) revealed their involvement in carbon metabolism and FoxO pathways. A PPI network (confidence score >0.40) constructed with STRING, identified six hub genes with connectivity degree 4. Expression dysregulation was confirmed by GEPIA2 (p-value <0.01, Log2FC >1). Molecular docking analysis using Autodock Vina reported stronger binding affinities of Baicalein for EGFR, MMP9, and TERT, and similar affinities for CCNB1 and MET, when compared to Gefitinib. This study brings forth baicalein as a possible natural alternative for GBC treatment.
    Keywords: Gallbladder cancer; flavonoids; network pharmacology; hub genes; molecular docking; bioinformatics.
    DOI: 10.1504/IJBET.2024.10067441
     
  • Modifying the Power Spectrum of the LPC Model within Kalman Filtering for Speech Enhancement   Order a copy of this article
    by Tarek Mellahi, Adil Bouhous, Rachid Hamdi 
    Abstract: We focused on enhancing speech improvement algorithms by addressing the challenge of extracting high-quality LPC parameters from noisy speech. The Kalman filter is a widely used algorithm in speech enhancement, and we aim to improve it by modifying the power spectrum parameters through a new approach called the modified power spectrum method within the LPC model for the Kalman Filter algorithm (MPS-LPC-KF). We evaluated our method using the NOIZEUS corpus and found it outperformed other existing methods. We are excited to see that our research has the potential to advance speech enhancement algorithms and ultimately improve communication in noisy environments.
    Keywords: Kalman filtering; speech enhancement; modified power spectrum method.
    DOI: 10.1504/IJBET.2024.10067443
     
  • Prediction of Type 2 Diabetes based on Feature Augmentation and Morlet Wavelet Assisted Deep Learning Network with FFT Overlap and Add Convolution   Order a copy of this article
    by Hitesh B. Patel, Keyur Brahmbhatt 
    Abstract: The enormous development in the technology makes a diagnosis easier in the medical field using various existing approaches. Even though, the approach possesses some disadvantages like lowering disease treatment costs; research showed that network features, which are important in decision making but have a low accuracy value, were critical. A new deep-learning technique for diabetes detection is proposed in this research that resolves the challenges in the existing. The approach combines adversarial variational auto-encoder (AVAE) for data/feature augmentation with a Morlet wavelet-assisted deep learning network featuring fast Fourier transform (FFT) overlap and add convolution (MW-FFT-OAconv) to enhance classification accuracy. A novel optimiser, the weighted mean of vectors (WMOV), is introduced to acquire the weight parameters of the MW-FFT-OAconv network. Experimental results evaluated using statistical measures such as accuracy, F1-Score, precision, true negative rate (TNR), true positive rate (TPR), classifier error percentage (CEP), and Mathew coefficient correlation (MCC), demonstrate the effectiveness of the proposed approach. Compared to previous machine learning prediction models (random foest, naive Bayes, and decision tree), the proposed technique achieves an accuracy level of 98.44% in predicting type 2 diabetes.
    Keywords: Adversarial Variational Auto-Encoder (AVAE); Morlet Wavelet assisted deep learning network with FFT Overlap and Add convolution (MW-FFT-OAconv); weIghted meaN oF vectOrs (WMOV); classifier error perce.
    DOI: 10.1504/IJBET.2024.10067777
     
  • Effects of Atherosclerotic Plaque Characteristics on Haemodynamics during Interventional Robot Diagnosis and Treatment   Order a copy of this article
    by Haoyu Xia, Zongming Zhu, Suqiang Ji, Liang Liang 
    Abstract: Atherosclerosis alters blood flow dynamics, yet the interaction between blood flow and vascular deformation with interventional devices remains underexplored. This study investigates the impact of plaque morphology and interventional robot positioning on blood flow characteristics. A bidirectional fluid-structure interaction (FSI) model was applied to calculate flow characteristics under varying plaque heights and shoulder widths. Particle image velocimetry (PIV) and a magnetically controlled microrobot system measured pulsatile flow fields in an experimental setup. Results show that plaque geometry and robot position significantly affect blood flow streamlines, pressure distribution, vascular deformation, and wall shear stress. When the robot moved from a distance of 25 mm to 5 mm from the plaque, the above-mentioned haemodynamic parameters increased by 11.41%, 5.51%, 9.28%, and 147%, respectively. The close alignment between simulations and experimental data confirms the accuracy of the method. This research enhances understanding of haemodynamic changes during interventional procedures and informs future clinical applications.
    Keywords: atherosclerosis; haemodynamics; fluid-structure interaction; FSI; interventional robot; particle image velocimetry; PIV.
    DOI: 10.1504/IJBET.2024.10067787
     
  • Motorised Bionic Arm Using SSVEP with Enhanced Hand Gesture Accuracy and Reliability   Order a copy of this article
    by Jahanzeb Sheikh, Tan Tian Swee, Maheza Irna Mohamad Salim, Michael Loong Peng Tan, Hum Yan Hum, Tengku Ahmad T. Alang 
    Abstract: The development of motorised bionic arms has been a significant focus in prosthetics. This study explored the design and implementation of a motorised bionic arm, emphasising enhanced hand gesture accuracy and reliability. Initially, the functional circuit and algorithm were designed, followed by the development of a motorised framework to control a 3D-printed real-time bionic arm, utilising Steady State Visually Evoked Potential (SSVEP) stimuli. The system's effectiveness was evaluated through accuracy and reliability tests on repeatability of gestures such as hand open, hand close, thumb up, and pointing, induced by four flickering frequencies (10-20 Hz). Findings revealed a mean accuracy of 97.5%, with individual accuracy rates ranging from 88.75% to 100%. Over 30 tests, the average angles were 168.8
    Keywords: Bionic Arm; Degree of Freedom (DoF); Hand Gestures; Motorized; Prosthetic; 3D printed prosthetic.
    DOI: 10.1504/IJBET.2024.10068321
     
  • A Comprehensive Review on Magnetic Tissue Scaffold for Hyperthermia Treatment   Order a copy of this article
    by Debashish Gogoi, Tanyu Donarld Kongnyui, Manjesh Kumar 
    Abstract: This review explores the use of magnetic bone tissue scaffolds in hyperthermia treatment. It is a therapy that heats cancer cells to damage or destroy them while minimising harm to healthy tissues. Hyperthermia leverages the greater heat sensitivity of cancer cells, potentially enhancing treatment outcomes. Bone scaffolds, typically composed of biocompatible materials like ceramics or polymers, have emerged as promising tools for hyperthermia by incorporating magnetic nanoparticles that generate heat under an alternating magnetic field. This study aims to evaluate the current advancements in magnetic bone scaffolds for hyperthermia therapy, focusing on the materials, fabrication methods, and magnetic properties that influence their performance. The review also addresses key challenges in optimising scaffold design and offers recommendations for future research to improve therapeutic efficacy. Conclusions indicate that magnetic scaffolds have significant potential for targeted cancer treatment and bone regeneration, yet further studies are needed to enhance their clinical application. This review can guide future efforts toward optimising scaffold-based hyperthermia therapies.
    Keywords: Hyperthermia treatment; additive manufacturing; cancer; tumour; magnetic properties.
    DOI: 10.1504/IJBET.2024.10068450
     
  • Finger Gesture Recognition by Mediapipe Algorithm and Advanced YOLOV7 Network for Deaf People   Order a copy of this article
    by Thanh-Hai Nguyen, Ba-Viet Ngo, Thanh-Long Nguyen, Chi-Cuong Vu 
    Abstract: Sign language is a challenge to be able to recognise and understand correctly its meaning. Therefore, with the deaf community, understanding sign language for daily activities is essential. For the support of the deaf community in interfacing together, researchers have represented different methods to support them in using sign languages. This article proposes using simple landmark hands with different finger shapes to detect ten letters in the American sign language (ASL) writing system. Therefore, an inference MediaPipe algorithm for extracting hand features with the advanced you only look once version 7 (YOLOv7) network was applied for sign language recognition. The article used 2000 hand images of 5 persons of different ages and genders with the YOLOv7 network to produce the high recognition performance. In particular, the average mAP accuracy reached 0.995, accuracy reached 99.4%, and recall parameter reached 99.2% using the confusion matrix. This algorithm can be developed with more letters.
    Keywords: gesture recognition; YOLOv7 network; inference – MediaPipe algorithm; hand features; sign language.
    DOI: 10.1504/IJBET.2024.10068659
     
  • An Integrated Data-Driven Analysis-Based Deep Learning Framework for Early Autism Detection in Children to Improve Diagnostic Performance   Order a copy of this article
    by Jahanara Shaik, R. Shekhar, Chetan Shelke 
    Abstract: Autism spectrum disorder (ASD) children must be recognised early to obtain prompt care, promote development, and reduce long-term issues. This research provides a VGG16 and ResNet50-based data-driven deep learning system for early ASD screening using facial picture data. The study meticulously normalises, augments, and selects features using chi-square methods to ensure high-quality inputs and low dataset variability. Hyperparameter adjustment optimises model performance and five-fold cross-validation provides robust evaluation. VGG16 can recognise complex face characteristics with 87% accuracy for autistic classifications due to its precision and recall measures. Bio-inspired optimisation improves classification, helping ResNet50 outperform training epochs. Despite these advances, multimodal inputs are still needed for complete analysis due to the limits of facial data and the diversity of datasets. Deep learning models with feature selection can improve diagnostic precision, reduce false positives, and enable clinical real-time ASD screening. The proposed framework speeds diagnosis and is adaptable to varied healthcare circumstances. Future studies will focus on behavioural and genetic data, expandable artificial intelligence (XAI) for interpretability, and larger datasets for robustness. A scalable and effective ASD diagnosis using AI shows the transformative potential of AI in healthcare.
    Keywords: Autism Spectrum Disorder; Deep Learning; VGG16; ResNet50; Early Diagnosis; Explainable AI (XAI); Early Autism Detection.
    DOI: 10.1504/IJBET.2024.10068985
     
  • Robust Time Domain Scalogram Filter Bank Feature Learning Model For Speech Depression Detection With Metaheuristic Spatio Temporal Residual BIGRU Model   Order a copy of this article
    by Uma Jaishankar, Jagannath H. Nirmal, Girish Gidaye 
    Abstract: This paper presents a better time-domain scalogram filter bank feature learning model. This model incorporates non-linear transformation, increased scalogram downsampling, and time-domain filtering to improve the feature extraction process. Although a number of existing methods try to identify depression through speech, they frequently fall short of accurately capturing the temporal and spatial relationships present in speech signals. By integrating spatial and temporal attention mechanisms and residual learning, the advanced Deep Learning (DL)-based model, the convolutional spatial and temporal attention-based residual Gazelle Bidirectional gated recurrent unit (BIGRU) (CSTAResGBIGRU) model is proposed. In this study, two benchmark datasets, the Distress Analysis Interview Corpus/Wizard-of-Oz set (DAIC-WOZ) and the Emotional Audio-Textual Corpus (EATD-Corpus), are used to demonstrate the efficiency of the proposed approach.. As per the experimental outcomes, the proposed model can outperform the state-of-the-art techniques, and it can attain 99.31% and 99.5% accuracy in DAIC-WOZ and EATD-Corpus correspondingly.
    Keywords: Speech depression; classification; benchmark dataset; scalogram filter; performance metrics and pre-processing.
    DOI: 10.1504/IJBET.2024.10068988
     
  • Major Mandible Reconstruction: Design, Analysis, and Additive Manufacturing of Customised Implant and Surgical Osteotomy Guide   Order a copy of this article
    by Hari Narayan Singh, Yashwant Kumar Modi, A. Kuthe, Sanat Agrawal 
    Abstract: A patient-specific major mandible reconstruction has been presented in this article. During the process, a customized surgical osteotomy resection guide was designed to avoid overcutting and undercutting of the infected part of diseased mandible. The reconstructed bone models and customized mandible implant were 3D printed to test form and fit of the implant. Finite element analysis was used to simulate the distribution of von Mises stress and deformation in Ti6Al4V implant by subjecting it to an occlusal bite force of 300 N, replicating the forces experienced during biting. The analysis was performed for four different biting scenarios. The highest values for maximum von Mises stress and maximum deformation was observed when the biting force was applied at the incisor. Despite variations in stress and deformation, the Ti6Al4V implant was determined to be safe in all four biting scenarios.
    Keywords: Mandible reconstruction; FEM analysis; 3D printing; customized mandible implant; and additive manufacturing.
    DOI: 10.1504/IJBET.2024.10068993
     
  • Dense Parallel Convolutional Neural Network for Lung and Colon Cancer Detection using Histopathological Images   Order a copy of this article
    by Mangore Anirudh K, Geeta S. Navale, Jawahar Sambhaji Gawade, Shailesh Pramod Bendale, Mubin Tamboli, Amol Dhumane 
    Abstract: Lung and colon cancer are deadly diseases, which cause mortality and morbidity. Here, the Dense Parallel Convolutional Neural Network (DPCNN) is proposed for detecting Lung and Colon Cancer by Histopathological Images (HI). Initially, the HI of the lung and colon are taken from the Lung and Colon Cancer Histopathological Images dataset and subjected to pre-processing. A Medav filter is used to pre-process the image. The Parallel Reverse Attention Network (PraNet) is then used to segregate the cancer region. Next, feature extraction is carried out, and features like Gray Level Run Length Matrix (GRLM) with Local Neighborhood Difference Pattern (LNDP) are extracted. After this, Lung and colon cancer detection is performed by the DPCNN approach. The DPCNN is a combination of DenseNet and Parallel Convolutional Neural Network (PCNN). The DPCNN obtained the True Negative Rate (TNR), accuracy, and True Positive Rate (TPR) of 92.044%, 92.773%, and 93.099%.
    Keywords: Dense Parallel Convolutional Neural Network; PraNet; Gray Level Run Length Matrix; Parallel Convolutional Neural Network Matrix; DenseNet.
    DOI: 10.1504/IJBET.2024.10069028
     
  • Fusion of Multiple Time-Frequency Representation Techniques and Classifiers for ECG and PPG Signal Analysis   Order a copy of this article
    by Piyush Mahajan, Amit Kaul 
    Abstract: This study explores the fusion of multiple Time-Frequency Representation (TFR) techniques for analyzing Electrocardiogram (ECG) and Photoplethysmogram (PPG) signals. We examined 11 TFR methods for noise removal, characteristic point detection, and feature extraction. Multiple classifiers were trained to classify ECG signals into six arrhythmia classes and PPG signals for hypertension detection. The ensemble classifiers, particularly those combining Continuous Wavelet Transform (CWT), S-Transform, Wigner-Ville Distribution (WVD), and Synchrosqueezed Wavelet Transform (SSWT), achieved a testing accuracy of 96.6% for ECG signals. A combination of CWT and SSWT with the K-Nearest Neighbour (KNN) classifier achieved 81.48% accuracy on the PPG dataset. The ensemble approach using majority voting significantly enhanced classification performance, reaching 99.75% accuracy for ECG arrhythmia and 82.52% for PPG classification. This fusion of TFR techniques and ensemble classifiers demonstrates improved accuracy in signal classification tasks.
    Keywords: ECG;PPG;TFR;ML.
    DOI: 10.1504/IJBET.2024.10069147
     
  • Hybrid Approach for Skin Lesion Analysis:- Integrating Modified U-Net Segmentation with Vision Transformers for Multi-Class Skin Cancer Detection   Order a copy of this article
    by Ramya J, Anil Kumar K.M 
    Abstract: Skin cancer is a major global health concern, where early and accurate detection is crucial for patient survival. Traditional CNN-based methods in skin lesion classification face challenges, particularly with the complexity of spatial and semantic features. To address these issues, we propose a unique hybrid deep learning approach integrating vision transformer (ViT) and a modified U-Net model. ViT processes images as tokens instead of pixels, enabling superior feature extraction and classification. Pre-processing techniques, including non-local means filtering for denoising and unsharp masking for contrast enhancement, are applied to enhance model robustness. Our hybrid approach integrates U-Net for precise segmentation, achieving metrics such as IOU of 92.46%, AUC of 97.64%, and dice coefficient of 95.96%. ViT for classification achieves exceptional accuracy, precision, recall, and F1 score, all at 99%. Using the HAM10000 dataset, our method surpasses existing techniques, demonstrating remarkable effectiveness in skin cancer detection and classification.
    Keywords: Skin Cancer Images; Multi-class classification; Vision Transformers; Region-of-Interest Segmentation; Computerized; Medical image processing.
    DOI: 10.1504/IJBET.2025.10069272