Selvathi Dharmar
Selvathi Dharmar has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
S. Thamarai Selvi
4 shared publications- Chinnathevar Sujatha
Sethu Institute of Technology
3 shared publications - Duraiswamy Jude Hemanth
Karunya Institute of Technology and Sciences
3 shared publications Henry Selvaraj
3 shared publicationsJ. Anitha
Karunya University, India
3 shared publications- Manjula Sankararaju
Department of ECE, Rajalakshmi Institute of Technology, Chennai, India
3 shared publications
Latest Publications
- 23 March 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (7) , 197
ProAttNet: a novel network of prostate segmentation with multi-attention residual U-Net using magnetic resonance images
- 23 March 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38 (7) , 197
ProAttNet: a novel network of prostate segmentation with multi-attention residual U-Net using magnetic resonance images
- 20 April 2025
- Published by Springer Nature
- p. 143-153
Transfer Learning Approach with ResNet Architecture for Colon Cancer Classification Using Histopathological Images
- 20 April 2025
- Published by Springer Nature
- p. 143-153
Transfer Learning Approach with ResNet Architecture for Colon Cancer Classification Using Histopathological Images
- 9 March 2025
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (2)
GRASP ‐Net: Grouped Residual Convolution U‐Net With Attention Mechanism and Atrous Spatial Pyramid Pooling for Prostate Zone Segmentation Using MR Images
Prostate cancer is a prevalent disease in men, especially among the elderly, and magnetic resonance imaging is the leading acquisition method for the diagnosis and evaluation of the prostate. Accurate segmentation of the prostate, particularly the transition zone and peripheral zone, is crucial for early detection and effective treatment planning. This work introduces GRASP‐Net as an innovative deep learning‐based model to improve prostate MRI zonal segmentation accuracy. GRASP‐Net integrates grouped residual convolutional modules, attention mechanisms, convolutional block attention module, and atrous spatial pyramid pooling blocks to enhance feature extraction and boundary segmentation. The model has been evaluated on the Medical Segmentation Decathlon Task 05 Prostate dataset, comparing its performance against other well‐known models. Overall, the GRASP‐Net model achieved higher segmentation results with a dice similarity coefficient of 0.928 for the transition zone and 0.864 for the peripheral zone, surpassing previous state‐of‐the‐art results. Additionally, the model exhibits significant performance on 95 percentile Hausdorff Distance, Average Surface Distance, and Sensitivity values and proving its accuracy in anatomical prostate structure localization. These advancements emphasize the promising prospect of the GRASP‐Net model to advance prostate cancer diagnosis and treatment, presenting an effective tool for clinical usage.
- 9 March 2025
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (2)
GRASP ‐Net: Grouped Residual Convolution U‐Net With Attention Mechanism and Atrous Spatial Pyramid Pooling for Prostate Zone Segmentation Using MR Images
Prostate cancer is a prevalent disease in men, especially among the elderly, and magnetic resonance imaging is the leading acquisition method for the diagnosis and evaluation of the prostate. Accurate segmentation of the prostate, particularly the transition zone and peripheral zone, is crucial for early detection and effective treatment planning. This work introduces GRASP‐Net as an innovative deep learning‐based model to improve prostate MRI zonal segmentation accuracy. GRASP‐Net integrates grouped residual convolutional modules, attention mechanisms, convolutional block attention module, and atrous spatial pyramid pooling blocks to enhance feature extraction and boundary segmentation. The model has been evaluated on the Medical Segmentation Decathlon Task 05 Prostate dataset, comparing its performance against other well‐known models. Overall, the GRASP‐Net model achieved higher segmentation results with a dice similarity coefficient of 0.928 for the transition zone and 0.864 for the peripheral zone, surpassing previous state‐of‐the‐art results. Additionally, the model exhibits significant performance on 95 percentile Hausdorff Distance, Average Surface Distance, and Sensitivity values and proving its accuracy in anatomical prostate structure localization. These advancements emphasize the promising prospect of the GRASP‐Net model to advance prostate cancer diagnosis and treatment, presenting an effective tool for clinical usage.
- Open Access
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 39192-39213
Computerized Diagnosis Methods for Pediatric Cardiology: A Review
Pediatric cardiac disorders include an extensive range of heart conditions in infants, children and carried over to adolescents in certain cases. These disorders may be congenital or acquired and can vary in impacting the life of the pediatric subject which requires complex surgical procedures and certain cases that do not require medical intervention. Congenital heart disease (CHD) is present during birth and acquired cardiac diseases are developed after birth predominantly due to autoimmune responses or infections. Various acquisition techniques help in visualizing the heart, identify disorders and help the physicians to plan for operative procedures. Pediatric Cardiac Screening is one of the crucial techniques to record cardiac activity which has difficulties in acquisition as children tend to move during the procedure. The data obtained from these modalities may suffer from various artifacts which makes the diagnosis difficult for the clinicians. To make the diagnosis easier and artifact free, artificial intelligence plays a vital role. Artificial Intelligence (AI)-based techniques from traditional machine learning (ML) to deep learning (DL) techniques for classification and segmentation of pediatric cardiac signals and images are systematically reviewed. DL based studies have become a choice of research in pediatric healthcare. Support Vector Machines with linear kernels are the most commonly used ML based classifiers in the reviewed papers. DL methods use Convolutional Neural Networks (CNN) as the primary classifier and U-Net architectures are preferred for segmentation studies in the reviewed papers. There are a very few surveys available to present the diagnostics related to pediatric cardiac disorders and this paper tries to bring out the challenges along with the traditional machine learning and emerging deep learning techniques implemented in classification and segmentation of the pediatric cardiac disorders.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 39192-39213
Open AccessComputerized Diagnosis Methods for Pediatric Cardiology: A Review
Pediatric cardiac disorders include an extensive range of heart conditions in infants, children and carried over to adolescents in certain cases. These disorders may be congenital or acquired and can vary in impacting the life of the pediatric subject which requires complex surgical procedures and certain cases that do not require medical intervention. Congenital heart disease (CHD) is present during birth and acquired cardiac diseases are developed after birth predominantly due to autoimmune responses or infections. Various acquisition techniques help in visualizing the heart, identify disorders and help the physicians to plan for operative procedures. Pediatric Cardiac Screening is one of the crucial techniques to record cardiac activity which has difficulties in acquisition as children tend to move during the procedure. The data obtained from these modalities may suffer from various artifacts which makes the diagnosis difficult for the clinicians. To make the diagnosis easier and artifact free, artificial intelligence plays a vital role. Artificial Intelligence (AI)-based techniques from traditional machine learning (ML) to deep learning (DL) techniques for classification and segmentation of pediatric cardiac signals and images are systematically reviewed. DL based studies have become a choice of research in pediatric healthcare. Support Vector Machines with linear kernels are the most commonly used ML based classifiers in the reviewed papers. DL methods use Convolutional Neural Networks (CNN) as the primary classifier and U-Net architectures are preferred for segmentation studies in the reviewed papers. There are a very few surveys available to present the diagnostics related to pediatric cardiac disorders and this paper tries to bring out the challenges along with the traditional machine learning and emerging deep learning techniques implemented in classification and segmentation of the pediatric cardiac disorders.
- Top Cited Papers
- 22 July 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (28) , 20605-20617
A CNN-LSTM hybrid network for automatic seizure detection in EEG signals
- 22 July 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (28) , 20605-20617
Top Cited PapersA CNN-LSTM hybrid network for automatic seizure detection in EEG signals
- 23 March 2021
- Published by Springer Nature in Multidimensional Systems and Signal Processing
- Vol. 33 (1) , 1-15
Fetal biometric based abnormality detection during prenatal development using deep learning techniques
- 23 March 2021
- Published by Springer Nature in Multidimensional Systems and Signal Processing
- Vol. 33 (1) , 1-15
Fetal biometric based abnormality detection during prenatal development using deep learning techniques
- Open Access
- 1 January 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1717 (1) , 012019
Design and Analysis of Modified UWB Mono-Cone Antenna for WBAN Applications
A low-profile UWB antenna is presented in this paper for wireless body area network (WBAN) applications. The proposed antenna consists of a modified mono-cone structure by adding a semi-sphere on top of the mono-cone. A top-plate is added as overhead to the proposed antenna. This plate leads to a height reduction when compared to conventional mono-cone antennas. In this paper, the effect of ground plane dimensions, effect of top-plate dimensions, effect of the supporting legs and effect of the total height of the antenna is studied to get a better insight into the working of the radiating structure. The antenna operates in the frequency range of 4.1 GHz to 10.1GHz with return loss less than -10dB. The bandwidth of the proposed antenna is 6 GHz. The frequency domain results are obtained by simulating the design using Ansoft HFSS. The voltage standing wave ratio is less than 2 within the frequency range of the proposed antenna design. The influence of the human proximity on the antenna was simulated by placing the proposed antenna over a human body model.
- 1 January 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1717 (1) , 012019
Open AccessDesign and Analysis of Modified UWB Mono-Cone Antenna for WBAN Applications
A low-profile UWB antenna is presented in this paper for wireless body area network (WBAN) applications. The proposed antenna consists of a modified mono-cone structure by adding a semi-sphere on top of the mono-cone. A top-plate is added as overhead to the proposed antenna. This plate leads to a height reduction when compared to conventional mono-cone antennas. In this paper, the effect of ground plane dimensions, effect of top-plate dimensions, effect of the supporting legs and effect of the total height of the antenna is studied to get a better insight into the working of the radiating structure. The antenna operates in the frequency range of 4.1 GHz to 10.1GHz with return loss less than -10dB. The bandwidth of the proposed antenna is 6 GHz. The frequency domain results are obtained by simulating the design using Ansoft HFSS. The voltage standing wave ratio is less than 2 within the frequency range of the proposed antenna design. The influence of the human proximity on the antenna was simulated by placing the proposed antenna over a human body model.
- Open Access
- 6 June 2018
- Published by Oriental Scientific Publishing Company in Biomedical and Pharmacology Journal
- Vol. 11 (2) , 795-805
Fundus Image Classification Using Wavelet Based Features in Detection of Glaucoma
Glaucoma frequently called as the "noiseless hoodlum of sight". The main source of visual impairment worldwide beside Diabetic Retinopathy is Glaucoma. It is discernible by augmented pressure inside the eyeball result in optic disc harm and moderate however beyond any doubt loss of vision. As the renaissance of the worsened optic nerve filaments isn't suitable medicinally, glaucoma regularly goes covered up in its patients anticipating later stages. All around it is assessed that roughly 60.5 million individuals beyond 40 years old experience glaucoma in 2010. This number potentially will lift to 80 million by 2020. Late innovation in medical imaging provides effective quantitative imaging alternatives for the identification and supervision of glaucoma. Glaucoma order can be competently done utilizing surface highlights. The wavelet channels utilized as a part of this paper are daubechies, symlet3 which will expand the precision and execution of classification of glaucomatous pictures. These channels are inspected by utilizing a standard 2-D Discrete Wavelet Transform (DWT) which is utilized to separate features and examine changes. The separated features are sustained into the feed forward neural system classifier that classifies the normal images and abnormal glaucomatous images.
- 6 June 2018
- Published by Oriental Scientific Publishing Company in Biomedical and Pharmacology Journal
- Vol. 11 (2) , 795-805
Open AccessFundus Image Classification Using Wavelet Based Features in Detection of Glaucoma
Glaucoma frequently called as the "noiseless hoodlum of sight". The main source of visual impairment worldwide beside Diabetic Retinopathy is Glaucoma. It is discernible by augmented pressure inside the eyeball result in optic disc harm and moderate however beyond any doubt loss of vision. As the renaissance of the worsened optic nerve filaments isn't suitable medicinally, glaucoma regularly goes covered up in its patients anticipating later stages. All around it is assessed that roughly 60.5 million individuals beyond 40 years old experience glaucoma in 2010. This number potentially will lift to 80 million by 2020. Late innovation in medical imaging provides effective quantitative imaging alternatives for the identification and supervision of glaucoma. Glaucoma order can be competently done utilizing surface highlights. The wavelet channels utilized as a part of this paper are daubechies, symlet3 which will expand the precision and execution of classification of glaucomatous pictures. These channels are inspected by utilizing a standard 2-D Discrete Wavelet Transform (DWT) which is utilized to separate features and examine changes. The separated features are sustained into the feed forward neural system classifier that classifies the normal images and abnormal glaucomatous images.
- 1 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 661-666
Brain Region Segmentation using Convolutional Neural Network
Brain region segmentation or skull stripping is an essential step in neuroimaging application such as surgical, surface reconstruction, image registration etc. The accuracy of all existing methods depends on the registration and image geometry. When this fails, the probability of success is very less. In order to avoid this, Convolutional Neural Network (CNN) is used. For brain extraction which is free from geometry and registration. CNN learned the connectedness and shape of the brain. OASIS database is used which is publicly available benchmark dataset. In this method, training phase uses 30 images and 10 images are used for testing phase. The performance of CNN results is closer to the ground truth results given by experts.
- 1 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 661-666
Brain Region Segmentation using Convolutional Neural Network
Brain region segmentation or skull stripping is an essential step in neuroimaging application such as surgical, surface reconstruction, image registration etc. The accuracy of all existing methods depends on the registration and image geometry. When this fails, the probability of success is very less. In order to avoid this, Convolutional Neural Network (CNN) is used. For brain extraction which is free from geometry and registration. CNN learned the connectedness and shape of the brain. OASIS database is used which is publicly available benchmark dataset. In this method, training phase uses 30 images and 10 images are used for testing phase. The performance of CNN results is closer to the ground truth results given by experts.