Murugan Pallikonda Rajasekaran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Murugan Pallikonda Rajasekaran has a total of 74 co-authors. Here are the top co-authors by number of shared publications:
- Arunprasath Thiyagarajan
Kalasalingam Academy of Research and Education
8 shared publications S. Sheik Abdullah
Kalasalingam Academy of Research and Education
7 shared publicationsKottaimalai Ramaraj
Kalasalingam Academy of Research and Education
6 shared publications- Kottaimalai Ramaraj
Kalasalingam Academy of Research and Education
6 shared publications Arunprasath Thiyagarajan
Kalasalingam Academy of Research and Education
5 shared publicationsGautam Amiya
Kalasalingam Academy of Research and Education
5 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 47-60
ResNet50V2-Driven Facial Geometry Analysis for Early Identification of Autistic Traits
- 2 July 2026
- Published by Springer Nature
- p. 47-60
ResNet50V2-Driven Facial Geometry Analysis for Early Identification of Autistic Traits
- 8 February 2026
- Published by MECS Publisher in International Journal of Intelligent Systems and Applications
- Vol. 18 (1) , 45-61
A Novel Hybrid Model for Brain Tumor Analysis Using Dual Attention AtroDense U-Net and Auction Optimized LSTM Network
Timely identification of brain tumors helps improve treatment outcomes and reduces mortality. Accurate and non-invasive diagnostic tools for segmenting and classifying tumor regions in brain MRI scans are crucial for minimizing the need for surgical biopsies. This study builds a deep learning model for tumor segmentation and classification, aiming high accuracy and efficiency. A gaussian bilateral filter is used for noise reduction and to improve MRI image quality. Tumor segmentation is performed using an advanced U-Net model, the Dual Attention AtroDense U-Net (DA-AtroDense U-Net), which integrates dense connections, atrous convolution and attention mechanisms to preserve spatial detail and improve boundary localization. Texture-based radiomic features are subsequently extracted from the segmented tumor region using Kirsch Edge Detector (KED) and Gray-Level Co-occurrence Matrix (GLCM) and refined through feature selection to reduce redundancy using the Cat-and-Mouse Optimization (CMO) algorithm. Tumor classification employs an Auction-Optimized hybrid LSTM Network (AOHLN). Evaluated on BraTS 2019 and 2020 datasets, the developed model achieved a Dice Similarity Coefficient of 0.9907 and a Jaccard Index of 0.9816 for segmentation accuracy and an overall accuracy of 98.99% for classification, highlighting its potential as a dependable and non-invasive diagnostic solution.
- 8 February 2026
- Published by MECS Publisher in International Journal of Intelligent Systems and Applications
- Vol. 18 (1) , 45-61
A Novel Hybrid Model for Brain Tumor Analysis Using Dual Attention AtroDense U-Net and Auction Optimized LSTM Network
Timely identification of brain tumors helps improve treatment outcomes and reduces mortality. Accurate and non-invasive diagnostic tools for segmenting and classifying tumor regions in brain MRI scans are crucial for minimizing the need for surgical biopsies. This study builds a deep learning model for tumor segmentation and classification, aiming high accuracy and efficiency. A gaussian bilateral filter is used for noise reduction and to improve MRI image quality. Tumor segmentation is performed using an advanced U-Net model, the Dual Attention AtroDense U-Net (DA-AtroDense U-Net), which integrates dense connections, atrous convolution and attention mechanisms to preserve spatial detail and improve boundary localization. Texture-based radiomic features are subsequently extracted from the segmented tumor region using Kirsch Edge Detector (KED) and Gray-Level Co-occurrence Matrix (GLCM) and refined through feature selection to reduce redundancy using the Cat-and-Mouse Optimization (CMO) algorithm. Tumor classification employs an Auction-Optimized hybrid LSTM Network (AOHLN). Evaluated on BraTS 2019 and 2020 datasets, the developed model achieved a Dice Similarity Coefficient of 0.9907 and a Jaccard Index of 0.9816 for segmentation accuracy and an overall accuracy of 98.99% for classification, highlighting its potential as a dependable and non-invasive diagnostic solution.
- 21 January 2026
- Published by Springer Nature
- p. 241-264
Blockchain Associated Machine Learning Approach for Earlier Prognosis and Preclusion of Osteoporosis in Elderly
- 21 January 2026
- Published by Springer Nature
- p. 241-264
Blockchain Associated Machine Learning Approach for Earlier Prognosis and Preclusion of Osteoporosis in Elderly
- Open Access
- 29 September 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
Classification of anterior cruciate ligament tears in knee magnetic resonance images using pre-trained model and custom model
An anterior cruciate ligament (ACL) tear is a prevalent knee injury among athletes, and aged people with osteoporosis are at increased risk for it. For early detection and treatment, precise and rapid identification of ACL tears is significant. A fully automated system that can identify ACL tear is necessary to aid healthcare providers in determining the nature of injuries detected on Magnetic Resonance Imaging (MRI) scans. Two Convolutional Neural Networks (CNN), the pretrained model and the CustomNet model are trained and tested using 581 MRI scans of the knee. Feature extraction is done with the pre-trained ResNet-18 model, and the ISOMAP algorithm is used in the CustomNet model. Linear and nonlinear dimensionality reduction techniques are employed to extract the needed features from the image. For the ResNet-18 model, the accuracy rate ranges between 86% and 92% for various data partitions. After performing PCA, the improved classification rate ranges between 92% and 96.2%. The CustomNet model’s accuracy rate ranges from 40 to 70%, 70–90%, 60–70%, and 50–70% for different hyperparameter ensembles. Five-fold cross validation is implemented in CustomNet and it achieved an overall accuracy of 85.6%. These two models demonstrate superior efficiency and accuracy in classifying normal and ACL torn Knee MR images.
- 29 September 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
Open AccessClassification of anterior cruciate ligament tears in knee magnetic resonance images using pre-trained model and custom model
An anterior cruciate ligament (ACL) tear is a prevalent knee injury among athletes, and aged people with osteoporosis are at increased risk for it. For early detection and treatment, precise and rapid identification of ACL tears is significant. A fully automated system that can identify ACL tear is necessary to aid healthcare providers in determining the nature of injuries detected on Magnetic Resonance Imaging (MRI) scans. Two Convolutional Neural Networks (CNN), the pretrained model and the CustomNet model are trained and tested using 581 MRI scans of the knee. Feature extraction is done with the pre-trained ResNet-18 model, and the ISOMAP algorithm is used in the CustomNet model. Linear and nonlinear dimensionality reduction techniques are employed to extract the needed features from the image. For the ResNet-18 model, the accuracy rate ranges between 86% and 92% for various data partitions. After performing PCA, the improved classification rate ranges between 92% and 96.2%. The CustomNet model’s accuracy rate ranges from 40 to 70%, 70–90%, 60–70%, and 50–70% for different hyperparameter ensembles. Five-fold cross validation is implemented in CustomNet and it achieved an overall accuracy of 85.6%. These two models demonstrate superior efficiency and accuracy in classifying normal and ACL torn Knee MR images.
- Open Access
- 3 September 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1
Correction: Deep learning based classification of tibio-femoral knee osteoarthritis from lateral view knee joint X-ray images
- 3 September 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1
Open AccessCorrection: Deep learning based classification of tibio-femoral knee osteoarthritis from lateral view knee joint X-ray images
- Open Access
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
Deep learning based classification of tibio-femoral knee osteoarthritis from lateral view knee joint X-ray images
Design an effective deep learning-driven method to locate and classify the tibio-femoral knee joint space width (JSW) with respect to both anterior-posterior (AP) and lateral views. Compare the results and see how successfully a deep learning approach can locate and classify tibio-femoral knee joint osteoarthritis from both anterior-posterior (AP) and lateral-view knee joint x-ray images. To evaluate the performance of a deep learning approach to classify and compare radiographic tibio-femoral knee joint osteoarthritis from both AP and lateral view knee joint digital X-ray images. We use 4334 data points (knee X-ray images) for this study. This paper introduces a methodology to locate, classify, and compare the outcomes of tibio-femoral knee joint osteoarthritis from both AP and lateral knee joint x-ray images. We have fine-tuned DenseNet 201 with transfer learning to extract the features to detect and classify tibio-femoral knee joint osteoarthritis from both AP view and lateral view knee joint X-ray images. The proposed model is compared with some classifiers. The proposed model locate the tibio femoral knee JSW localization accuracy at 98.12% (lateral view) and 99.32% (AP view). The classification accuracy with respect to the lateral view is 92.42% and the AP view is 98.57%, which indicates the performance of automatic detection and classification of tibio-femoral knee joint osteoarthritis with respect to both views (AP and lateral views).We represent the first automated deep learning approach to classify tibio-femoral osteoarthritis on both the AP view and the lateral view, respectively. The proposed deep learning approach trained on the femur and tibial bone regions from both AP view and lateral view digital X-ray images. The proposed model performs better at locating and classifying tibio femoral knee joint osteoarthritis than the existing approaches. The proposed approach will be helpful for the clinicians/medical experts to analyze the progression of tibio-femoral knee OA in different views. The proposed approach performs better in AP view than Lateral view. So, when compared to other continuing existing architectures/models, the proposed model offers exceptional outcomes with fine-tuning.
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
Open AccessDeep learning based classification of tibio-femoral knee osteoarthritis from lateral view knee joint X-ray images
Design an effective deep learning-driven method to locate and classify the tibio-femoral knee joint space width (JSW) with respect to both anterior-posterior (AP) and lateral views. Compare the results and see how successfully a deep learning approach can locate and classify tibio-femoral knee joint osteoarthritis from both anterior-posterior (AP) and lateral-view knee joint x-ray images. To evaluate the performance of a deep learning approach to classify and compare radiographic tibio-femoral knee joint osteoarthritis from both AP and lateral view knee joint digital X-ray images. We use 4334 data points (knee X-ray images) for this study. This paper introduces a methodology to locate, classify, and compare the outcomes of tibio-femoral knee joint osteoarthritis from both AP and lateral knee joint x-ray images. We have fine-tuned DenseNet 201 with transfer learning to extract the features to detect and classify tibio-femoral knee joint osteoarthritis from both AP view and lateral view knee joint X-ray images. The proposed model is compared with some classifiers. The proposed model locate the tibio femoral knee JSW localization accuracy at 98.12% (lateral view) and 99.32% (AP view). The classification accuracy with respect to the lateral view is 92.42% and the AP view is 98.57%, which indicates the performance of automatic detection and classification of tibio-femoral knee joint osteoarthritis with respect to both views (AP and lateral views).We represent the first automated deep learning approach to classify tibio-femoral osteoarthritis on both the AP view and the lateral view, respectively. The proposed deep learning approach trained on the femur and tibial bone regions from both AP view and lateral view digital X-ray images. The proposed model performs better at locating and classifying tibio femoral knee joint osteoarthritis than the existing approaches. The proposed approach will be helpful for the clinicians/medical experts to analyze the progression of tibio-femoral knee OA in different views. The proposed approach performs better in AP view than Lateral view. So, when compared to other continuing existing architectures/models, the proposed model offers exceptional outcomes with fine-tuning.
- 12 February 2025
- Published by Springer Nature
- p. 823-828
Estimation of Bone Degeneration and Porosity Using T-Score from DXA Images for Osteoporotic Patient Classification and Therapy Ideation
- 12 February 2025
- Published by Springer Nature
- p. 823-828
Estimation of Bone Degeneration and Porosity Using T-Score from DXA Images for Osteoporotic Patient Classification and Therapy Ideation
- Open Access
- 1 January 2025
- Published by Wiley in Applied and Environmental Soil Science
- Vol. 2025 (1)
Estimate the Coastal Flood Prone Zone From the Past Events in Tamilnadu and Kerala
Tamil Nadu and Kerala achieve the coastal flood disaster that leads to the maximum social and economic loss for India. The coastal flood prone methods used Sentinel 1A, Tropical Rainfall Measuring Mission (TRMM), and Gravity Recovery and Climate Experiment with Terrestrial Water Storage Anomaly (GRACE‐TWSA) product in the Tamil Nadu and Ernakulam flood events. These data estimate the change detection of pre‐flood and post‐flood events, flood inundation mapping, and Reager’s Flood Potential Index (RFPI). Sentinel 1A was overlaid for four consecutive days to determine the portion of flood inundation mapping. Using GRACE‐TWSA and TRMM data, the Flood Potential Index (FPI) used the RFPI method at a monthly scale. Then, RFPI, GRACE‐TWSA, and TRMM data were compared for four cities of the flooded year in Chennai, Tamil Nadu, and Ernakulam, Kerala. Finally, flood inundation determined the 90‐sq·km of the 2015 Chennai flood and 25‐sq·km of the 2018 Ernakulam flood with the limited remote sensing data. Maximum RFPI between the postflood and preflood period (12 months) achieves the maximum, approximately 80% from the monsoon rainfall with approximately 20% of the total water storage to attain 100% at RFPI at both flooded years. The RFPI results monitor the prone locations from these extreme past floods on the south coast of India. The research insight shares the surplus water resources by the downpour from northeast monsoon in Tamil Nadu and southwest monsoon in Kerala. Downpour naturally disputes the water resources to sustain the socioeconomic reforms between interstates. The study also supports the policy of sustainable development goals in 11, 13, 14, and 15 in the future.
- 1 January 2025
- Published by Wiley in Applied and Environmental Soil Science
- Vol. 2025 (1)
Open AccessEstimate the Coastal Flood Prone Zone From the Past Events in Tamilnadu and Kerala
Tamil Nadu and Kerala achieve the coastal flood disaster that leads to the maximum social and economic loss for India. The coastal flood prone methods used Sentinel 1A, Tropical Rainfall Measuring Mission (TRMM), and Gravity Recovery and Climate Experiment with Terrestrial Water Storage Anomaly (GRACE‐TWSA) product in the Tamil Nadu and Ernakulam flood events. These data estimate the change detection of pre‐flood and post‐flood events, flood inundation mapping, and Reager’s Flood Potential Index (RFPI). Sentinel 1A was overlaid for four consecutive days to determine the portion of flood inundation mapping. Using GRACE‐TWSA and TRMM data, the Flood Potential Index (FPI) used the RFPI method at a monthly scale. Then, RFPI, GRACE‐TWSA, and TRMM data were compared for four cities of the flooded year in Chennai, Tamil Nadu, and Ernakulam, Kerala. Finally, flood inundation determined the 90‐sq·km of the 2015 Chennai flood and 25‐sq·km of the 2018 Ernakulam flood with the limited remote sensing data. Maximum RFPI between the postflood and preflood period (12 months) achieves the maximum, approximately 80% from the monsoon rainfall with approximately 20% of the total water storage to attain 100% at RFPI at both flooded years. The RFPI results monitor the prone locations from these extreme past floods on the south coast of India. The research insight shares the surplus water resources by the downpour from northeast monsoon in Tamil Nadu and southwest monsoon in Kerala. Downpour naturally disputes the water resources to sustain the socioeconomic reforms between interstates. The study also supports the policy of sustainable development goals in 11, 13, 14, and 15 in the future.
- Open Access
- 25 December 2024
- Published by MDPI AG in Mathematical and Computational Applications
- Vol. 30 (1) , 1
Advanced Hybrid Brain Tumor Segmentation in MRI: Elephant Herding Optimization Combined with Entropy-Guided Fuzzy Clustering
Accurate and early detection of brain tumors is essential for improving clinical outcomes and guiding effective treatment planning. Traditional segmentation techniques in MRI often struggle with challenges such as noise, intensity variations, and complex tumor morphologies, which can hinder their effectiveness in critical healthcare scenarios. This study proposes an innovative hybrid methodology that integrates advanced metaheuristic optimization and entropy-based fuzzy clustering to enhance segmentation precision in brain tumor detection. This method combines the nature-inspired Elephant Herding Optimization (EHO) algorithm with Entropy-Driven Fuzzy C-Means (EnFCM) clustering, offering significant improvements over conventional methods. EHO is utilized to optimize the clustering process, enhancing the algorithm’s ability to delineate tumor boundaries, while entropy-based fuzzy clustering accounts for intensity inhomogeneity and diverse tumor characteristics, promoting more consistent and reliable segmentation results. This approach was evaluated using the BraTS challenge dataset, a benchmark in the field of brain tumor segmentation. The results demonstrate marked improvements across several performance metrics, including Dice similarity, mean squared error (MSE), peak signal-to-noise ratio (PSNR), and the Tanimoto coefficient (TC), underscoring this method’s robustness and segmentation accuracy. By managing image noise and reducing computational demands, the EHO-EnFCM approach not only captures intricate tumor structures but also facilitates efficient image processing, making it suitable for real-time clinical applications. Overall, the findings reveal the potential of this hybrid approach to advance MRI-based tumor detection, offering a promising tool that enhances both accuracy and computational efficiency for medical imaging and diagnosis.
- 25 December 2024
- Published by MDPI AG in Mathematical and Computational Applications
- Vol. 30 (1) , 1
Open AccessAdvanced Hybrid Brain Tumor Segmentation in MRI: Elephant Herding Optimization Combined with Entropy-Guided Fuzzy Clustering
Accurate and early detection of brain tumors is essential for improving clinical outcomes and guiding effective treatment planning. Traditional segmentation techniques in MRI often struggle with challenges such as noise, intensity variations, and complex tumor morphologies, which can hinder their effectiveness in critical healthcare scenarios. This study proposes an innovative hybrid methodology that integrates advanced metaheuristic optimization and entropy-based fuzzy clustering to enhance segmentation precision in brain tumor detection. This method combines the nature-inspired Elephant Herding Optimization (EHO) algorithm with Entropy-Driven Fuzzy C-Means (EnFCM) clustering, offering significant improvements over conventional methods. EHO is utilized to optimize the clustering process, enhancing the algorithm’s ability to delineate tumor boundaries, while entropy-based fuzzy clustering accounts for intensity inhomogeneity and diverse tumor characteristics, promoting more consistent and reliable segmentation results. This approach was evaluated using the BraTS challenge dataset, a benchmark in the field of brain tumor segmentation. The results demonstrate marked improvements across several performance metrics, including Dice similarity, mean squared error (MSE), peak signal-to-noise ratio (PSNR), and the Tanimoto coefficient (TC), underscoring this method’s robustness and segmentation accuracy. By managing image noise and reducing computational demands, the EHO-EnFCM approach not only captures intricate tumor structures but also facilitates efficient image processing, making it suitable for real-time clinical applications. Overall, the findings reveal the potential of this hybrid approach to advance MRI-based tumor detection, offering a promising tool that enhances both accuracy and computational efficiency for medical imaging and diagnosis.