This project is focused on solving one of healthcare’s toughest challenges: brain tumor analysis. Progress has been made with the segmentation aspect of the project. A novel and efficient framework for the semantic segmentation of brain tumors has been developed. It includes SEDNet, an encoder-decoder network that explores sufficiency and selective mechanisms tailored for the localized nature of brain tumors in MRI scans. This design ensures computational efficiency without compromising segmentation accuracy, making it suitable for real-time clinical applications. Our solution advances the role of AI in neuro-oncology by supporting early diagnosis for personalized treatment planning. 

This project focuses on the development of machine learning algorithms for identifying and detecting digital biomarker with early signs of Alzheimer disease progression. The goal of the project is to create a tool to be used by neurologist in identifying early-on mild cognitive patients who are more likely to progress to Alzheimer disease and can be used to discover the pattern of Alzheimer disease progression and severity for patients who already have Alzheimer disease.  Progress has begun with development of CNN architecture for discriminating between mild cognitive impairment and Alzheimer disease in order to understand the relationship that exist between the disease states before further research is carried out towards progression. 

This project focuses on developing artificial intelligence algorithms for seizure-to-body pulse associative learning to explore the relationship between epileptic seizures and physiological signals, such as human pulse. The goal is to create a predictive machine learning model for early seizure detection, ultimately improving the quality of life for people living with epilepsy. Long-term objectives include the development of AI-controlled, non-invasive wearable devices for real-time seizure monitoring and management.