Most recent issue published online in the International Journal of Biomedical Engineering and Technology.
International Journal of Biomedical Engineering and Technology
http://www.inderscience.com/browse/index.php?journalID=226&year=2024&vol=44&issue=3
Inderscience Publishers Ltd
en-uk
support@inderscience.com
International Journal of Biomedical Engineering and Technology
1752-6418
1752-6426
© 2024 Inderscience Enterprises Ltd.
© 2024 Inderscience Publishers Ltd
editor@inderscience.com
International Journal of Biomedical Engineering and Technology
https://www.inderscience.com/images/files/coverImgs/ijbet_scoverijbet.jpg
http://www.inderscience.com/browse/index.php?journalID=226&year=2024&vol=44&issue=3
-
Atherosclerotic plaque segmentation using modified UNet with hybrid pooling layers
http://www.inderscience.com/link.php?id=137344
Atherosclerotic plaque segmentation is a vital task in cardiovascular image processing. Fuzzy nature of the carotid images makes it difficult to extract vital features from the plaque tissue region. UNet deep learning models use max-pooling layers for extraction of feature maps and are quite effective in medical image segmentation. In this study, we hypothesised that the UNet model with a hybrid pooling layer consisting of average pooling layer and max-pooling layers could exert more control on feature selection, and therefore be more effective solution for carotid plaque segmentation. We used a public database of 66 B-mode ultrasound images of the carotid artery for our experiments. We experimented with four cases of modified UNet model using a hybrid pooling layer with four different values of 'α' and compared it with the standard UNet model. Modified UNet model with hybrid pooling layers shows nearly 5% improvements in DSC and JI values.
Atherosclerotic plaque segmentation using modified UNet with hybrid pooling layers
Soni Singh; Pankaj Kumar Jain; Neeraj Sharma; Mausumi Pohit
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 205 - 225
Atherosclerotic plaque segmentation is a vital task in cardiovascular image processing. Fuzzy nature of the carotid images makes it difficult to extract vital features from the plaque tissue region. UNet deep learning models use max-pooling layers for extraction of feature maps and are quite effective in medical image segmentation. In this study, we hypothesised that the UNet model with a hybrid pooling layer consisting of average pooling layer and max-pooling layers could exert more control on feature selection, and therefore be more effective solution for carotid plaque segmentation. We used a public database of 66 B-mode ultrasound images of the carotid artery for our experiments. We experimented with four cases of modified UNet model using a hybrid pooling layer with four different values of 'α' and compared it with the standard UNet model. Modified UNet model with hybrid pooling layers shows nearly 5% improvements in DSC and JI values.]]>
10.1504/IJBET.2024.137344
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 205 - 225
Soni Singh
Pankaj Kumar Jain
Neeraj Sharma
Mausumi Pohit
School of Vocational Studies and Applied Sciences, Gautam Buddha University, Greater Noida, UP, India ' School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, UP, India ' School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, UP, India ' School of Vocational Studies and Applied Sciences, Gautam Buddha University, Greater Noida, UP, India
UNet
hybrid pooling layer
atherosclerosis
carotid plaque segmentation
deep learning
2024-03-13T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
44
3
205
225
2024-03-13T23:20:50-05:00
-
An efficient brain tumour segmentation approach using cascade convolutional neural networks
http://www.inderscience.com/link.php?id=137343
Brain tumours pose a significant threat to human life, as they are a major cause of death. Early detection of brain tumours is vital to improve treatment and reduce mortality rates. Automatic segmentation using deep learning methods is crucial for clinical evaluation and treatment planning but remains challenging due to the diverse tumour locations and structures. In this work, we employed the concatenation of two different convolutional neural networks: the two-pathway architecture and the inception architecture. We also utilised a patch-based technique that combines global and local features to predict the output region. Our proposed system achieved dice scores of 0.86, 0.81, and 0.75 for the whole tumour, tumour core, and enhancing tumour on the BraTS 2018 dataset, respectively. For BraTS 2019, the dice scores were 0.85, 0.79, and 0.67, respectively. Compared to existing state-of-the-art CNN models, our proposed system significantly improves both qualitative and quantitative brain tumour segmentation results.
An efficient brain tumour segmentation approach using cascade convolutional neural networks
Ahmed Hechri; Abdelrahman Hamed; Ahmed Boudaka
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 226 - 241
Brain tumours pose a significant threat to human life, as they are a major cause of death. Early detection of brain tumours is vital to improve treatment and reduce mortality rates. Automatic segmentation using deep learning methods is crucial for clinical evaluation and treatment planning but remains challenging due to the diverse tumour locations and structures. In this work, we employed the concatenation of two different convolutional neural networks: the two-pathway architecture and the inception architecture. We also utilised a patch-based technique that combines global and local features to predict the output region. Our proposed system achieved dice scores of 0.86, 0.81, and 0.75 for the whole tumour, tumour core, and enhancing tumour on the BraTS 2018 dataset, respectively. For BraTS 2019, the dice scores were 0.85, 0.79, and 0.67, respectively. Compared to existing state-of-the-art CNN models, our proposed system significantly improves both qualitative and quantitative brain tumour segmentation results.]]>
10.1504/IJBET.2024.137343
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 226 - 241
Ahmed Hechri
Abdelrahman Hamed
Ahmed Boudaka
Department of Electrical and Electronics Engineering, British Applied College, Umm Al Quwain, United Arab Emirates; Laboratory of Electronics and Micro-Electronics, Faculty of Sciences, University of Tunis El Manar, University of Monastir, Tunisia ' Department of Electrical and Electronics Engineering, British Applied College, Umm Al Quwain, United Arab Emirates ' Department of Electrical and Electronics Engineering, British Applied College, Umm Al Quwain, United Arab Emirates
MR images
tumour segmentation
convolutional neural network
CNN
two pathways
inception
2024-03-13T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
44
3
226
241
2024-03-13T23:20:50-05:00
-
EEG-based variable node functional network comparison for multiclass brain disease detection using stacked ensemble model
http://www.inderscience.com/link.php?id=137345
The brain connectivity network (BCN) is considered to be an effective approach for analysing brain functionality. The EEG-based BCN considers electrodes as a node and functional similarity between EEGs from corresponding nodes as edge. The EEG dataset available for the evaluation might contain variable number of nodes. The variable number of nodes provides biased results while performing graph classification. Hence, the study proposed a strategy to mitigate the aforementioned challenge. The proposed method characterises variable node BCN with the help of network level metrics as a feature vector. The extracted metrics characterises the network as a whole and do not rely on the number of nodes. Two public datasets, with 16 electrodes and 19 electrodes EEG data, are used to test the suggested method. The classification is performed with the stacked-ensemble classification technique. Finally, the quantitative analysis of the proposed approach represents a significant performance with the 92.34% classification accuracy.
EEG-based variable node functional network comparison for multiclass brain disease detection using stacked ensemble model
Mangesh Ramaji Kose; Mitul Kumar Ahirwal; Mithilesh Atulkar
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 242 - 270
The brain connectivity network (BCN) is considered to be an effective approach for analysing brain functionality. The EEG-based BCN considers electrodes as a node and functional similarity between EEGs from corresponding nodes as edge. The EEG dataset available for the evaluation might contain variable number of nodes. The variable number of nodes provides biased results while performing graph classification. Hence, the study proposed a strategy to mitigate the aforementioned challenge. The proposed method characterises variable node BCN with the help of network level metrics as a feature vector. The extracted metrics characterises the network as a whole and do not rely on the number of nodes. Two public datasets, with 16 electrodes and 19 electrodes EEG data, are used to test the suggested method. The classification is performed with the stacked-ensemble classification technique. Finally, the quantitative analysis of the proposed approach represents a significant performance with the 92.34% classification accuracy.]]>
10.1504/IJBET.2024.137345
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 242 - 270
Mangesh Ramaji Kose
Mitul Kumar Ahirwal
Mithilesh Atulkar
Department of Computer Applications, National Institute of Technology, Raipur †492010, India ' Department of Computer Applications, Maulana Azad National Institute of Technology Bhopal, Bhopal †462003, India ' Department of Computer Applications, National Institute of Technology, Raipur †492010, India
brain connectivity network
BCN
electroencephalogram
EEG
graph theory-based metrics
SMOTE
stacked-ensemble classification
2024-03-13T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
44
3
242
270
2024-03-13T23:20:50-05:00
-
ADB-Net: an attention-based dilated bridge model for fully automatic intra-tumour segmentation of gliomas
http://www.inderscience.com/link.php?id=137346
Glioma segmentation is a complicated task due to the non-uniform and unstructured morphology of gliomas. Moreover, the requirement for trainable parameters grows exponentially with architectural advancements. In this work, a lightweight and modified attention-based dilated bridge net (ADB-Net) architecture is developed for accurate segmentation of glioma sub-regions. The proposed work has four main benefactions. Firstly, the bridging network in D-Link is enhanced by incorporating a deformed residual connection after each dilation convolutional block to promote the mapping of multi-level information between encoding/decoding units. Secondly, a proper selection of the dilation factor is included for dilated convolutional blocks. Thirdly, four modified attention skip modules (ASM) are also introduced to provide recognition of varied-sized tumours. Lastly, the proposed architecture outperforms its baselines while minimising the number of trainable parameters by more than 50%. It achieves dice scores for the complete tumour, tumour core, and enhancing tumour as 0.971, 0.979, and 0.962, respectively.
ADB-Net: an attention-based dilated bridge model for fully automatic intra-tumour segmentation of gliomas
Radhika Malhotra; Barjinder Singh Saini; Savita Gupta
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 271 - 287
Glioma segmentation is a complicated task due to the non-uniform and unstructured morphology of gliomas. Moreover, the requirement for trainable parameters grows exponentially with architectural advancements. In this work, a lightweight and modified attention-based dilated bridge net (ADB-Net) architecture is developed for accurate segmentation of glioma sub-regions. The proposed work has four main benefactions. Firstly, the bridging network in D-Link is enhanced by incorporating a deformed residual connection after each dilation convolutional block to promote the mapping of multi-level information between encoding/decoding units. Secondly, a proper selection of the dilation factor is included for dilated convolutional blocks. Thirdly, four modified attention skip modules (ASM) are also introduced to provide recognition of varied-sized tumours. Lastly, the proposed architecture outperforms its baselines while minimising the number of trainable parameters by more than 50%. It achieves dice scores for the complete tumour, tumour core, and enhancing tumour as 0.971, 0.979, and 0.962, respectively.]]>
10.1504/IJBET.2024.137346
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 271 - 287
Radhika Malhotra
Barjinder Singh Saini
Savita Gupta
Department of Electronics and Communication, Dr. B.R. Ambedkar National Institute of Technology, Jalandhar, Punjab, 144011, India ' Department of Electronics and Communication, Dr. B.R. Ambedkar National Institute of Technology, Jalandhar, Punjab, 144011, India ' Department of Computer Science and Engineering, UIET, Sector 25 Panjab University, Chandigarh, 160023, India
D-Link
attention
glioma
segmentation
loss function
BraTS
convolutional neural networks
CNN
attention skip modules
ASM
2024-03-13T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
44
3
271
287
2024-03-13T23:20:50-05:00
-
Video analytics-based multi-symptoms system for determining progression of Parkinson disease
http://www.inderscience.com/link.php?id=137347
Parkinson disease is the second most common neurodegenerative disease, and its symptoms tend to increase progressively and affect numerous parts of the body. Parkinson disease patients suffer from symptoms such as rigidity in the body, Bradykinesia, tremors in hands, facial tremor, and freezing of gait. Traditionally assessment of Parkinson disease is based on clinician observation on the severity of symptoms of patients during the visit. Symptoms of Parkinson are highly episodic and cannot be completely observed at the doctor's clinic. With the effect of COVID-19, physical visit of the elderly population to the clinic is considered unsafe. Video-based assessment at the patients home led to the solution of avoiding the patient to be exposed to the outside world. We propose a non-invasive video analytics-based assessment of progression of Parkinson disease based on finger tapping and tremor using UPDRS scale. We also propose a video-based technique utilising deep learning and convolutional neural networks which analyse the gait characteristics of patients to identify Parkinson. We intend to distinguish a healthy subject and progression of disease at different stages. These techniques can assist clinical experts for examination of patients to identify the progression of the disease.
Video analytics-based multi-symptoms system for determining progression of Parkinson disease
Jignesh Sisodia; Dhananjay Kalbande
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 288 - 302
Parkinson disease is the second most common neurodegenerative disease, and its symptoms tend to increase progressively and affect numerous parts of the body. Parkinson disease patients suffer from symptoms such as rigidity in the body, Bradykinesia, tremors in hands, facial tremor, and freezing of gait. Traditionally assessment of Parkinson disease is based on clinician observation on the severity of symptoms of patients during the visit. Symptoms of Parkinson are highly episodic and cannot be completely observed at the doctor's clinic. With the effect of COVID-19, physical visit of the elderly population to the clinic is considered unsafe. Video-based assessment at the patients home led to the solution of avoiding the patient to be exposed to the outside world. We propose a non-invasive video analytics-based assessment of progression of Parkinson disease based on finger tapping and tremor using UPDRS scale. We also propose a video-based technique utilising deep learning and convolutional neural networks which analyse the gait characteristics of patients to identify Parkinson. We intend to distinguish a healthy subject and progression of disease at different stages. These techniques can assist clinical experts for examination of patients to identify the progression of the disease.]]>
10.1504/IJBET.2024.137347
International Journal of Biomedical Engineering and Technology, Vol. 44, No. 3 (2024) pp. 288 - 302
Jignesh Sisodia
Dhananjay Kalbande
Sardar Patel Institute of Technology, Mumbai, India ' Sardar Patel Institute of Technology, Mumbai, India
Parkinson disease
video analytics
deep learning
convolutional neural network
CNN
2024-03-13T23:20:50-05:00
Copyright © 2024 Inderscience Enterprises Ltd.
44
3
288
302
2024-03-13T23:20:50-05:00