Rakesh Chandra Joshi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Rakesh Chandra Joshi has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
- Malay Kishore Dutta
Amity Centre for Artificial Intelligence, Amity University, Noida, Uttar Pradesh, India
20 shared publications Malay Kishore Dutta
Centre for Advanced Studies, Dr. A.P.J. Abdul Kalam Technical University,Lucknow,U.P.,India
11 shared publicationsRadim Burget
Department of Telecommunications, FEEC Brno University of Technology Brno Czechia
7 shared publications- Radim Burget
Brno University of Technology
7 shared publications - Saumya Yadav
I.E.C. Engineering College,Dept. of Computer Sc. & Engg,GREATER NOIDA,UP,India
6 shared publications - Carlos Manuel Travieso
Signals and Communications Department (DSC), Institute for Technological Development and Innovation in Communications (IDeTIC), University of Las Palmas de Gran Canaria (ULPGC), 35017 Las Palmas de Gran Canaria, Spain
4 shared publications
Latest Publications
- 28 September 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 130
GRAN-EEG: A ghost-residual attention network for subject-independent EEG-based objective pain recognition
- 28 September 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 130
GRAN-EEG: A ghost-residual attention network for subject-independent EEG-based objective pain recognition
- 10 July 2026
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 124 (Pt 2) , 109225
Biomarkers for minimally invasive multigrade liver cancer diagnosis using integrative heterogeneous models and evolutionary algorithms
- 10 July 2026
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 124 (Pt 2) , 109225
Biomarkers for minimally invasive multigrade liver cancer diagnosis using integrative heterogeneous models and evolutionary algorithms
- 4 January 2026
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 36 (1)
SpineDeep ‐Net: Dual‐Self‐Attention‐Based Deep Neural Network for Automating Slice Selection and Precise Transverse Plane Localization in Lumbar Spine MRI for Intervertebral Disc Analysis
The rising prevalence of lumbar spine disorders demands scalable solutions for mass screening and automated diagnosis. Accurate analysis of specific MRI slices, such as mid‐sagittal or transverse mid‐height intervertebral disc (IVD) slices, is essential but currently relies on time‐consuming, error‐prone manual selection. Automating this process is crucial to enhance the efficiency and accuracy of computer‐aided diagnostic systems. To address this need, this study introduces a novel deep learning‐based framework—SpineDeep‐Net that integrates self‐attention mechanisms within a multi‐layer convolutional neural network for automatic selection of optimal transverse planes of lumbar spine MRI disc slices. By focusing on mid‐height slices of L3/L4, L4/L5, and L5/S1 IVDs—the most diagnostically relevant slices, SpineDeep‐Net eliminates the reliance on manual selection processes, thereby accelerating and improving the diagnostic pipeline. Unlike standard attention, the proposed dual‐self‐attention employs two sequential attention stages that jointly enhance long‐range spatial cue extraction and emphasize subtle disc‐level differences. This mechanism enables the model to focus more effectively on diagnostically relevant regions within lumbar MRI slices by dynamically recalibrating feature maps and strengthening feature dependencies. Experimental evaluations demonstrate the superior performance of SpineDeep‐Net, achieving 96.83% accuracy and 98.41% specificity, outperforming state‐of‐the‐art methods. By automating the selection and classification of clinically critical disc slices, SpineDeep‐Net addresses a key challenge in lumbar spine diagnostics, providing a reliable, scalable, and efficient tool that aids radiologists in making informed clinical decisions. The proposed framework highlights the transformative potential of self‐attention‐guided deep learning in advancing healthcare diagnostics. The source code is publicly available at https://github.com/rakeshchandrajoshi/spinedeepnet .
- 4 January 2026
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 36 (1)
SpineDeep ‐Net: Dual‐Self‐Attention‐Based Deep Neural Network for Automating Slice Selection and Precise Transverse Plane Localization in Lumbar Spine MRI for Intervertebral Disc Analysis
The rising prevalence of lumbar spine disorders demands scalable solutions for mass screening and automated diagnosis. Accurate analysis of specific MRI slices, such as mid‐sagittal or transverse mid‐height intervertebral disc (IVD) slices, is essential but currently relies on time‐consuming, error‐prone manual selection. Automating this process is crucial to enhance the efficiency and accuracy of computer‐aided diagnostic systems. To address this need, this study introduces a novel deep learning‐based framework—SpineDeep‐Net that integrates self‐attention mechanisms within a multi‐layer convolutional neural network for automatic selection of optimal transverse planes of lumbar spine MRI disc slices. By focusing on mid‐height slices of L3/L4, L4/L5, and L5/S1 IVDs—the most diagnostically relevant slices, SpineDeep‐Net eliminates the reliance on manual selection processes, thereby accelerating and improving the diagnostic pipeline. Unlike standard attention, the proposed dual‐self‐attention employs two sequential attention stages that jointly enhance long‐range spatial cue extraction and emphasize subtle disc‐level differences. This mechanism enables the model to focus more effectively on diagnostically relevant regions within lumbar MRI slices by dynamically recalibrating feature maps and strengthening feature dependencies. Experimental evaluations demonstrate the superior performance of SpineDeep‐Net, achieving 96.83% accuracy and 98.41% specificity, outperforming state‐of‐the‐art methods. By automating the selection and classification of clinically critical disc slices, SpineDeep‐Net addresses a key challenge in lumbar spine diagnostics, providing a reliable, scalable, and efficient tool that aids radiologists in making informed clinical decisions. The proposed framework highlights the transformative potential of self‐attention‐guided deep learning in advancing healthcare diagnostics. The source code is publicly available at https://github.com/rakeshchandrajoshi/spinedeepnet .
- 6 August 2025
- Published by Springer Nature in Indian Journal of Surgical Oncology
- Vol. 17 (5) , 1057-1064
Multiparametric MRI Radiomics for the Prediction of Histologic Grade in Bladder Cancer
Histological grade holds great clinical significance in the management and prognosis of bladder cancer; therefore, timely and accurate prediction through non-invasive techniques such as MRI may improve health outcomes. Our objective was to create an MRI-based radiomics model that can predict the histological grade of cancer pre-operatively. In a prospective study, we gathered data from 45 bladder cancer patients who had an mpMRI scan from December 2018 to December 2022 prior to their operative procedure. Radiomics features were extracted from T2-weighted (T2W), diffusion-weighted imaging (DWI), and dynamic DCE-MRI-enhanced (DCE) MR images obtained from a 1.5 T MRI scanner. A standard 5-point VI-RADS scoring system was also assessed for each scan. The variable clustering algorithm was applied to these features, and all cluster features were univariably assessed using receiver operating characteristic (ROC) curves. Multiple predictive models were created and cross-validated based on multivariable analysis to minimize overfitting and predict the grade of the tumor. Among 45 eligible patients, 28 (62.2%) patients had high-grade tumors and the rest 17 (37.8%) were low grade. In the adjusted analysis, only DCE-MRI based (Gray Level Co-occurrence Matrix (Gray Level Co-occurrence Matrix (GLCM))-inverse variance (OR = 1.42, p = 0.028), Major Axis Length (OR = 1.04, p = 0.03)), and age (OR = 1.08, p = 0.039) were associated with the high-grade bladder cancer. Our radiomics models comprising DCE-MRI-based parameters, a T2W parameter, and age yielded the highest performance for predicting grades of bladder cancer (AUC = 0.91; 95% CI 0.82–1.00). These models demonstrated reasonably high predictive performance in bootstrap validation analysis as well. An mpMRI radiomics approach based on MRI has the potential to serve as a non-invasive imaging tool for preoperative grading of bladder cancer.
- 6 August 2025
- Published by Springer Nature in Indian Journal of Surgical Oncology
- Vol. 17 (5) , 1057-1064
Multiparametric MRI Radiomics for the Prediction of Histologic Grade in Bladder Cancer
Histological grade holds great clinical significance in the management and prognosis of bladder cancer; therefore, timely and accurate prediction through non-invasive techniques such as MRI may improve health outcomes. Our objective was to create an MRI-based radiomics model that can predict the histological grade of cancer pre-operatively. In a prospective study, we gathered data from 45 bladder cancer patients who had an mpMRI scan from December 2018 to December 2022 prior to their operative procedure. Radiomics features were extracted from T2-weighted (T2W), diffusion-weighted imaging (DWI), and dynamic DCE-MRI-enhanced (DCE) MR images obtained from a 1.5 T MRI scanner. A standard 5-point VI-RADS scoring system was also assessed for each scan. The variable clustering algorithm was applied to these features, and all cluster features were univariably assessed using receiver operating characteristic (ROC) curves. Multiple predictive models were created and cross-validated based on multivariable analysis to minimize overfitting and predict the grade of the tumor. Among 45 eligible patients, 28 (62.2%) patients had high-grade tumors and the rest 17 (37.8%) were low grade. In the adjusted analysis, only DCE-MRI based (Gray Level Co-occurrence Matrix (Gray Level Co-occurrence Matrix (GLCM))-inverse variance (OR = 1.42, p = 0.028), Major Axis Length (OR = 1.04, p = 0.03)), and age (OR = 1.08, p = 0.039) were associated with the high-grade bladder cancer. Our radiomics models comprising DCE-MRI-based parameters, a T2W parameter, and age yielded the highest performance for predicting grades of bladder cancer (AUC = 0.91; 95% CI 0.82–1.00). These models demonstrated reasonably high predictive performance in bootstrap validation analysis as well. An mpMRI radiomics approach based on MRI has the potential to serve as a non-invasive imaging tool for preoperative grading of bladder cancer.
- 10 December 2024
- Published by Elsevier in ISA Transactions
- Vol. 157, 340-356
Optimized inverse kinematics modeling and joint angle prediction for six-degree-of-freedom anthropomorphic robots with Explainable AI
- 10 December 2024
- Published by Elsevier in ISA Transactions
- Vol. 157, 340-356
Optimized inverse kinematics modeling and joint angle prediction for six-degree-of-freedom anthropomorphic robots with Explainable AI
- Open Access
- 2 December 2024
- Published by MDPI AG in Prosthesis
- Vol. 6 (6) , 1459-1478
AI-Enhanced Analysis to Investigate the Feasibility of EMG Signals for Prosthetic Hand Force Control Incorporating Anthropometric Measures
Background/Objectives: The potential application of electromyography (EMG) as a method for precise force control in prosthetic devices is investigated, expanding on its traditional use in gesture detection. Variability in EMG signals among individuals is influenced by physiological factors such as muscle mass, body fat percentage, and subcutaneous fat, as well as demographic variables like age, gender, height, and weight. This study aims to evaluate how these factors impact EMG signal quality and force output. Methods: EMG data was normalized using the maximum voluntary contraction (MVC) method, recorded at 100%, 50%, and 25% of MVC with simultaneous grip force measurement. Physiological parameters, including fat percentage, subcutaneous fat, and muscle mass, were analyzed. An extreme gradient boosting algorithm was applied to model the relationship between EMG amplitude and grip force. Results: The findings demonstrated significant linear correlations, with r2 coefficients reaching up to 0.93 and 0.83 in most cases. Muscle mass and fat levels were identified as key determinants of EMG variability, with significance coefficients ranging from 0.36592 to 0.0856 for muscle mass and 0.281918 to 0.06001 for fat levels. Conclusions: These results underscore the potential of EMG to enhance force control in prosthetic limbs, particularly in tasks such as grasping, holding, and releasing objects. Incorporating body composition factors into EMG-based prediction algorithms offers a refined approach to improving the precision and functionality of prosthetic control systems for complex motor tasks.
- 2 December 2024
- Published by MDPI AG in Prosthesis
- Vol. 6 (6) , 1459-1478
Open AccessAI-Enhanced Analysis to Investigate the Feasibility of EMG Signals for Prosthetic Hand Force Control Incorporating Anthropometric Measures
Background/Objectives: The potential application of electromyography (EMG) as a method for precise force control in prosthetic devices is investigated, expanding on its traditional use in gesture detection. Variability in EMG signals among individuals is influenced by physiological factors such as muscle mass, body fat percentage, and subcutaneous fat, as well as demographic variables like age, gender, height, and weight. This study aims to evaluate how these factors impact EMG signal quality and force output. Methods: EMG data was normalized using the maximum voluntary contraction (MVC) method, recorded at 100%, 50%, and 25% of MVC with simultaneous grip force measurement. Physiological parameters, including fat percentage, subcutaneous fat, and muscle mass, were analyzed. An extreme gradient boosting algorithm was applied to model the relationship between EMG amplitude and grip force. Results: The findings demonstrated significant linear correlations, with r2 coefficients reaching up to 0.93 and 0.83 in most cases. Muscle mass and fat levels were identified as key determinants of EMG variability, with significance coefficients ranging from 0.36592 to 0.0856 for muscle mass and 0.281918 to 0.06001 for fat levels. Conclusions: These results underscore the potential of EMG to enhance force control in prosthetic limbs, particularly in tasks such as grasping, holding, and releasing objects. Incorporating body composition factors into EMG-based prediction algorithms offers a refined approach to improving the precision and functionality of prosthetic control systems for complex motor tasks.
- 22 July 2024
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 255, 108349
Biomarker profiling and integrating heterogeneous models for enhanced multi-grade breast cancer prognostication
- 22 July 2024
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 255, 108349
Biomarker profiling and integrating heterogeneous models for enhanced multi-grade breast cancer prognostication