Biomedical Imaging and Computational Modelling
Neurological disorder identification using psychophysiological data
Psychophysiological chronic disorders lead to both physical disorders and emotional factors such as anxiety and stress. This requires the patients to live under medical treatments in their lives. Most of them have a genetic influence and observable in children at an early age. Therefore, the early identification of a disorder is important to reduce the negative consequences of adulthood. The machine learning and deep learning techniques have been actively applied in recent years based on neuroimaging inputs such as electroencephalogram, magnetic resonance imaging to find feasible computational solutions. However, the recent studies are lacking the support for multiple disorders rather focusing only on single disorder though there are commonalities among many of the psychophysiological chronic disorders. Thus, a generic neuroscience decision support system framework with the aid of learning models can be designed and implemented to identify the disorders when neuroimaging inputs are given.
Attention Deficit Hyperactivity Disorder classification using fMRI and eye moment data
Autism Spectrum Disorder classification (EEG, thermal data, fMRI)
Alzheimer’s Disease Identification with Functional and Structural Neuroimaging Modalities
Parkinson's Disease Identification with EEG signals : A QCNN based Approach
Overall Survival Prediction of Glioma Patients with Genomics
Brain Tumor Segmentation and Edge Detection with MRI data: Self-Supervised Learning Approach
Cervical Cancer Screening using Pap Smear images: Segmentation from Explainability