Supervisor Name: Dr Venkateswarlu Gonuguntla

Goal of the project: This research develops ‘a. AI-based methods for tracking the development of cognitive impairment and b. MRI structural and functional networks fusion technologies for Alzheimer's disease diagnosis.’ The project's tasks include collecting data from many imaging modalities, analysing data from single and multiple modalities, and developing a GUI for AD early detection.

Significance of the study: The substantial increase in incidence of dementia is a significant global issue. There are currently no simple, effective therapies available. A timely and accurate AD diagnosis is the only way to have any hope for the treatment process. The intended research will be highly beneficial in the diagnosis of AD and may also be used to comprehend other neurological illnesses. A successful deployment will result in fresh perspectives on the mechanisms at play and a deeper comprehension of how MCI turns into AD.

Skills: In this research, signal processing and graph neural network techniques are primarily used for medical imaging analysis.

Supervisor Name: Dr Venkateswarlu Gonuguntla

Goal of the project: ‘The development of EEG-based brain mapping technologies for the analysis and decoding of various neural illnesses will be the main goal of this research’. The project's tasks include gathering EEG data, signal processing, and interpreting EEG data using network theory and graph theory, as well as using deep learning and machine learning to analyse EEG data.

Significance of the study: Implementing the proposed research successfully will improve the quality of treating brain disorders and assist doctors in making quick, informed judgements. Numerous neuroscience disciplines can also use the proposed technique.

Skills: This research makes use of expertise in deep learning, graph theory, machine learning, signal processing, and more.

Supervisor Name: Dr Venkateswarlu Gonuguntla

Goal of the project: ‘The purpose of this study is to integrate a multi-modality system using fMRI, EMG, and IMU into the present rehabilitation and therapy regimens’. The project's objectives are to: 1. collect fMRI, EMG, and IMU data to monitor the brain, muscles, and movement activities of a stroke patient; 2. develop methods for determining changes in the brain's, muscles', and motion activities at different points; and 3. present an evaluation tool that is simple to integrate into existing treatment plans.

Significance of the study: The technology for tracking the progress of functional recovery and brain remodelling in stroke patients will advance significantly as a result of this work. Doctors will be able to spot even the smallest alterations in performed actions and brain reconfiguration with the help of the developed multi-sensor system. This study will raise the bar for stroke rehabilitation therapy, enabling doctors to make prompt and accurate decisions. The system created will significantly affect society and the economy.

Skills: This project calls for expertise in machine learning, deep learning, image processing, and signal processing.

Supervisor Name: Dr. Sourav Bhaduri, Assistant Professor

This research develops ‘a. AI/ML and signal/image processing methods for the assessment of brain tumour heterogeneities and treatment response using multi modal MRI parameters and b. Study of Dynamic Contrast Enhanced (DCE) MRI based perfusion Imaging, Diffusion Tensor Imaging (DTI) for measurement of diffusion and high speed/high resolution multi-voxel MR spectroscopic imaging (MRSI) imaging to quantify neurometabolites in different types of brain tumours.’ The project's tasks include collecting data from the above mentioned imaging modalities, develop/implement signal/image processing algorithms, analysing data and developing a GUI toolbox for assessing treatment response in brain tumours. In this research, signal/image processing, advanced MR physics, AI/ML based techniques will be used for medical imaging analysis. MR pulse sequence development will be also be performed to develop/implement faster and accurate methods for data acquisition and advanced data reconstruction algorithms will also be developed/implemented.

Supervisor Name: Dr. Sourav Bhaduri, Assistant Professor

This research develops ‘methods for outer volume brain lipid suppression suppression for preservation and accurate quantification of Lactate peaks (in brain tumour cases) and other main neuro-metabolites in proton MR spectrocopy signals (both healthy and brain tumour cases) using advanced signal processing algorithms and AI/ML based approaches. The project's tasks include collecting proton MR spectroscopy datasets, develop/implement signal processing algorithms, analysing data and developing a GUI toolbox for lipid suppression. In this research, signal/image processing, MR physics, AI/ML based techniques will be used for medical imaging analysis. MR pulse sequence development will be also be performed to develop/implement hardware based methods for data acquisition and advanced data reconstruction algorithms will also be developed/implemented incorporating lipid suppression.

We are looking for ambitious young scientists to join this project. The ideal PhD candidate should have : some experience with (medical) signal/image processing, AI/ML, basic knowledge of MR physics and neuroimaging, strong programming skills (MATLAB, or Python) and strong interest in biomedical questions and research