Research & Publications
Advancing cancer care through CT-based radiomics and deep learning
📚 View Google Scholar ProfileUnder Submission
(2)Automated Segmentation of Head and Neck Cancer from CT Images Using 3D Convolutional Neural Networks
International Conference on Artificial Intelligence for Healthcare (AIHC), 2025
Metaheuristic-Driven Machine Learning Pipelines for Radiomics-Based Prediction of Locoregional Recurrence in Head and Neck Cancer
International Conference on Artificial Intelligence for Healthcare (AIHC), 2025
Novel metaheuristic optimization approach for radiomics feature selection and machine learning pipeline optimization in predicting locoregional recurrence for head and neck cancer patients.
Conference Presentations
(2)Before We Treat, Can We Tell? A Locoregional Recurrence Signature in Head & Neck
15th Research Day, Christian Medical College, Vellore, Tamil Nadu, India, 2025
Prospective radiomics-based prediction model for identifying patients at high risk of locoregional recurrence before treatment initiation in head and neck cancer.
Can CT Radiomics Predict Recurrence in Head and Neck Cancer? Early Results from a Prospective Imaging Trial
14th Research Day, Christian Medical College, Vellore, Tamil Nadu, India, 2024
Prospective CT radiomics study for one-year locoregional recurrence prediction in head and neck cancer; Naive Bayes showed the best train-test balance in early results.
Book Chapters
(1)Cancer Survival Prediction Using Artificial Intelligence: Current Status and Future Prospects
Data Science in the Medical Field, Academic Press (Elsevier), 2024. ISBN: 978-0-443-24029-4
Comprehensive overview of AI and machine learning approaches for cancer survival prediction, spanning imaging and clinical data, with emphasis on explainability and clinical integration.
Under Preparation
(1)A Prognosis Prediction of Breast Cancer using Multimodal Gated Attention Convolution Neural Network by Integrating Multi-dimensional Data (MGAttCNNMD)
Novel multimodal deep learning architecture leveraging gated attention mechanisms for integrating multi-dimensional clinical and imaging data for breast cancer prognosis prediction.