Sikamony S. Kumar
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
Sikamony S. Kumar has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Devi Devapal
College of Engineering, Pathanapuram, Kollam, Kerala, India
4 shared publications Ezhil E. Nithila
4 shared publications- Benisha Maria Xavier
Department of ECE, Jeppiaar Institute of Technology, Chennai, India
3 shared publications J. Rajeesh
Dept. of ECE, Noorul Islam College of Engineering, Kumaracoil 629 180, India
3 shared publications- K. A. Sreeja
SCMS School of Engineering and Technology
3 shared publications Kuruvilla John
Noorul Islam Centre for Higher Education
3 shared publications
Latest Publications
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 293-322
Vision-Language Models for Medical Imaging
Vision–Language Models (VLMs) have emerged as a powerful paradigm for medical imaging by jointly learning from visual data and clinical language. Unlike traditional vision-only approaches, VLMs integrate medical images with radiology reports, clinical notes, and textual prompts, enabling richer semantic understanding, improved generalization, and enhanced interpretability. This chapter presents a comprehensive overview of VLMs for medical imaging, covering their motivation, fundamental architectures, training data requirements, optimization strategies, and evaluation methodologies. A detailed taxonomy of medical VLMs is discussed, including contrastive, generative, and foundation-based models. The chapter further explores key applications such as diagnosis, segmentation, report generation, visual question answering, and clinical decision support. Critical challenges and future research directions toward robust, human-centered, and clinically validated multimodal AI systems are outlined.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 293-322
Vision-Language Models for Medical Imaging
Vision–Language Models (VLMs) have emerged as a powerful paradigm for medical imaging by jointly learning from visual data and clinical language. Unlike traditional vision-only approaches, VLMs integrate medical images with radiology reports, clinical notes, and textual prompts, enabling richer semantic understanding, improved generalization, and enhanced interpretability. This chapter presents a comprehensive overview of VLMs for medical imaging, covering their motivation, fundamental architectures, training data requirements, optimization strategies, and evaluation methodologies. A detailed taxonomy of medical VLMs is discussed, including contrastive, generative, and foundation-based models. The chapter further explores key applications such as diagnosis, segmentation, report generation, visual question answering, and clinical decision support. Critical challenges and future research directions toward robust, human-centered, and clinically validated multimodal AI systems are outlined.
- 27 March 2026
- Published by IGI Global Scientific Publishing
- p. 85-118
Biomedical Applications of Deep Learning in Hyperspectral Oncology
Hyperspectral imaging is an emerging optical modality in oncology that enables non-invasive, label-free tissue characterization by capturing spatially resolved spectral information across a broad wavelength range. Malignant transformation induces biochemical and microstructural changes that alter tissue optical properties, which can be detected through hyperspectral imaging. This chapter presents the physical principles of hyperspectral imaging for cancer diagnosis and reviews computational analysis approaches, with a particular focus on deep learning–based methods for interpreting high-dimensional spectral–spatial data. Applications of hyperspectral imaging are discussed across major cancer types, including brain, breast, colorectal, head and neck, lung, and skin cancers. Current challenges and future research directions are outlined, highlighting the potential of deep learning–enhanced hyperspectral imaging to support precision oncology and image-guided cancer care.
- 27 March 2026
- Published by IGI Global Scientific Publishing
- p. 85-118
Biomedical Applications of Deep Learning in Hyperspectral Oncology
Hyperspectral imaging is an emerging optical modality in oncology that enables non-invasive, label-free tissue characterization by capturing spatially resolved spectral information across a broad wavelength range. Malignant transformation induces biochemical and microstructural changes that alter tissue optical properties, which can be detected through hyperspectral imaging. This chapter presents the physical principles of hyperspectral imaging for cancer diagnosis and reviews computational analysis approaches, with a particular focus on deep learning–based methods for interpreting high-dimensional spectral–spatial data. Applications of hyperspectral imaging are discussed across major cancer types, including brain, breast, colorectal, head and neck, lung, and skin cancers. Current challenges and future research directions are outlined, highlighting the potential of deep learning–enhanced hyperspectral imaging to support precision oncology and image-guided cancer care.
- 29 August 2025
- Published by IGI Global Scientific Publishing
- p. 161-218
Transformers for Medical Image Segmentation
Recent advances in transformer-based deep learning architectures have significantly enhanced medical image segmentation by enabling precise delineation of anatomical structures across various imaging modalities and clinical contexts. Transformers leverage self-attention mechanisms to model long-range dependencies and global context, overcoming the limitations of convolutional neural networks with localized receptive fields. This chapter reviews the application of transformers in segmentation tasks such as brain tumors, retinal vessels, and skin lesions, highlighting innovations in architecture, performance benchmarks, and evaluation metrics. Comparative analyses reveal trends in accuracy, robustness, and efficiency, while addressing challenges like computational demands, limited annotated data, and clinical interpretability. Future directions include lightweight architectures, multimodal integration, and clinical validation. These developments illustrate the transformative role of transformers in precision medicine and AI-driven healthcare.
- 29 August 2025
- Published by IGI Global Scientific Publishing
- p. 161-218
Transformers for Medical Image Segmentation
Recent advances in transformer-based deep learning architectures have significantly enhanced medical image segmentation by enabling precise delineation of anatomical structures across various imaging modalities and clinical contexts. Transformers leverage self-attention mechanisms to model long-range dependencies and global context, overcoming the limitations of convolutional neural networks with localized receptive fields. This chapter reviews the application of transformers in segmentation tasks such as brain tumors, retinal vessels, and skin lesions, highlighting innovations in architecture, performance benchmarks, and evaluation metrics. Comparative analyses reveal trends in accuracy, robustness, and efficiency, while addressing challenges like computational demands, limited annotated data, and clinical interpretability. Future directions include lightweight architectures, multimodal integration, and clinical validation. These developments illustrate the transformative role of transformers in precision medicine and AI-driven healthcare.
- Open Access
- 29 June 2025
- Published by Atlantis Press SARL
- p. 310-321
Advances in LiDAR-Camera Fusion for Object Detection in Autonomous Driving
- 29 June 2025
- Published by Atlantis Press SARL
- p. 310-321
Open AccessAdvances in LiDAR-Camera Fusion for Object Detection in Autonomous Driving
- 8 May 2025
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (3)
A Review of U‐Net‐Based Deep Learning Models for Skin Lesion Segmentation
Automated skin lesion segmentation is crucial for early and accurate skin cancer diagnosis. Deep learning, particularly U‐Net, has revolutionized the field of automatic skin lesion segmentation. This review comprehensively examines U‐Net and its variants employed for automated skin lesion segmentation. It outlines the foundational U‐Net architecture and explores diverse architectural innovations, including attention mechanisms, advanced skip connections, residual and dilated convolutions, transformer models, and hybrid models. The review highlights how these adaptations address inherent challenges in skin lesion segmentation, including data limitations and lesion heterogeneity. It also discusses the commonly used datasets, evaluation metrics, and compares model performance and computational cost. Finally, it addresses the existing challenges and outlines future research directions to advance automated skin cancer diagnosis.
- 8 May 2025
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (3)
A Review of U‐Net‐Based Deep Learning Models for Skin Lesion Segmentation
Automated skin lesion segmentation is crucial for early and accurate skin cancer diagnosis. Deep learning, particularly U‐Net, has revolutionized the field of automatic skin lesion segmentation. This review comprehensively examines U‐Net and its variants employed for automated skin lesion segmentation. It outlines the foundational U‐Net architecture and explores diverse architectural innovations, including attention mechanisms, advanced skip connections, residual and dilated convolutions, transformer models, and hybrid models. The review highlights how these adaptations address inherent challenges in skin lesion segmentation, including data limitations and lesion heterogeneity. It also discusses the commonly used datasets, evaluation metrics, and compares model performance and computational cost. Finally, it addresses the existing challenges and outlines future research directions to advance automated skin cancer diagnosis.
- Top Cited Papers
- 22 January 2025
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 123
Advancements in medical image segmentation: A review of transformer models
- 22 January 2025
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 123
Top Cited PapersAdvancements in medical image segmentation: A review of transformer models
- 18 April 2024
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 117
Grey Wolf optimized SwinUNet based transformer framework for liver segmentation from CT images
- 18 April 2024
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 117
Grey Wolf optimized SwinUNet based transformer framework for liver segmentation from CT images
- 8 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (28) , 71833-71862
Literature survey on deep learning methods for liver segmentation from CT images: a comprehensive review
- 8 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (28) , 71833-71862
Literature survey on deep learning methods for liver segmentation from CT images: a comprehensive review
- 5 July 2022
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (6) , 1846-1860
Early cervical cancer diagnosis using Sooty tern‐optimized CNN‐LSTM classifier
- 5 July 2022
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (6) , 1846-1860
Early cervical cancer diagnosis using Sooty tern‐optimized CNN‐LSTM classifier
- 18 July 2020
- Published by Springer Nature
- p. 57-67
Automated Detection of Retinal Hemorrhage Based on Supervised Classifiers and Implementation in Hardware
- 18 July 2020
- Published by Springer Nature
- p. 57-67
Automated Detection of Retinal Hemorrhage Based on Supervised Classifiers and Implementation in Hardware