Master's Students

With over 2 years of experience in product design, development, and MR scanning optimization, I bring expertise in IoT technologies and compliance with global standards, and advanced imaging techniques.

Thesis work - Development of Isotropic Diffusion-Weighted Imaging for Clinical Application 

🔅 Designing and optimizing isotropic diffusion-weighted imaging sequences to improve diagnostic accuracy in fetal, overcoming motion artifacts, and enhancing resolution through innovative gradient waveforms. 

I am a Biomedical Engineer with experience in developing AI-driven solutions for medical imaging, diagnostics, and digital health. I have contributed to research in areas such as dermatological disease classification, segmentation problems, and health chat bots. I am passionate about building technology that enhances clinical decision-making and improves patient care.

Thesis work - AI based Anthropometric measurement from breast MRI images.

🔅 Breast anatomy varies significantly across individuals, posing challenges for standardized MRI coil design. Manufacturers often lack precise anatomical measurements, impacting imaging quality and comfort. Using deep learning-based segmentation, generating accurate statistical measurements to guide coil optimization. 

    I analyze Cerebrospinal Fluid (CSF) motion using engineering approaches to decode its role in brain health. My research includes medical imaging (MRI) supported by my ECE foundation in hardware/software systems.

   Thesis Work - Quantification of CSF flow in the Human Brain for the study of Normal Pressure Hydrocephalus.

🔅 My research investigates cerebrospinal fluid (CSF) dynamics in the human brain, with a focus on understanding altered flow patterns in Normal Pressure Hydrocephalus. CSF serves essential physiological functions, including mechanical protection, waste clearance, and the maintenance of biochemical stability. Through MRI-based quantification and engineering-driven analysis, I aim to develop deeper insights into CSF flow behavior and its relevance to neurological health.

This work is conducted in collaboration with Citi Neuro Centre, Hyderabad, under the co-supervision of Dr. D. Ravi Varma, Senior Consultant Interventional Neuroradiologist.

A glimpse of my work can be found here:  https://drive.google.com/drive/folders/1Un49Cs_1AANzm2ft8N88wz0-k5XV_W3X?usp=drive_link

I am working on AI-driven medical image analysis to improve the quantitative assessment of cardiac adipose tissue and its role in cardiovascular and metabolic health. My research integrates artificial intelligence, medical imaging, and biomedical engineering to develop automated and reproducible tools for clinical decision support. By combining deep learning with quantitative imaging, I aim to reduce observer variability while improving the efficiency, accuracy, and scalability of cardiac risk assessment.

Thesis Title: AI-Based Automated Quantification of Epicardial and Pericardial Adipose Tissue

This research focuses on the development of an automated framework for the segmentation and quantification of Epicardial Adipose Tissue (EAT) and Pericardial Adipose Tissue (PAT) using dual-modality cardiac imaging, including both Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). These adipose tissue depots are increasingly recognized as important imaging biomarkers associated with cardiovascular disease, metabolic syndrome, systemic inflammation, and adverse cardiac outcomes. Accurate measurement of EAT and PAT provides valuable insights into cardiometabolic risk stratification and disease progression.

Traditional manual and semi-automated quantification methods are time-consuming, operator-dependent, and prone to variability. To address these limitations, this project leverages deep learning–based segmentation models and advanced image processing techniques to enable fully automated, fast, and reproducible tissue quantification across imaging modalities. The workflow includes image preprocessing, cardiac region localization, automated tissue segmentation, and volumetric and density-based analysis. For CT imaging, quantification incorporates Hounsfield Unit–based tissue characterization, while MRI-based analysis enables radiation-free assessment and improved soft-tissue contrast for broader clinical applicability.

By supporting both CT and MRI data, the proposed dual-modality framework enhances clinical flexibility and expands accessibility across diverse imaging environments. Beyond automation, this work explores the relationship between cardiac adipose tissue distribution and cardiometabolic risk, contributing to the growing field of AI-assisted cardiovascular imaging and precision medicine.

This research is being carried out in collaboration with AIG Hospitals, Hyderabad, under the co-supervision of Dr. Bhairavi Reddy, supporting the translation of AI-based imaging tools into real-world clinical workflows.

I have a background in Mechanical Engineering with over two years of experience in the design and development of static equipment. My current work focuses on electromagnetic simulations and development of subsystems for low-field MRI systems.

I am involved in performing electromagnetic simulations to generate magnetic field maps comparable to those of conventional 1.5T MRI systems, including fringe field characterization. As part of this work, I evaluate implant safety by analyzing forces and torques induced by magnetic field interactions across different spatial positions and motion conditions, assessing structural integrity. This project is being carried out for HCLTech, focusing on analyzing implant behavior within the simulated field environments.

In parallel, I actively contribute to the development of a low-field MRI system in our lab based on permanent magnet arrays arranged in a circular Halbach configuration. My work includes shimming strategies to improve B₀ field homogeneity by optimizing magnet arrangements.

I am also responsible for the design and development of the gradient system for the low-field MRI setup, with a focus on achieving the required field characteristics for particular imaging application.

I work on generating Quantitative Susceptibility Maps (QSM) for precise estimation of iron concentration and oxygenation in the Brain. My research integrates signal processing and medical image analysis, supported by a strong foundation in biomedical engineering.

Thesis Title: Iron Quantification and Oxygenation Assessment Using Quantitative Susceptibility Mapping (QSM) in Sickle Cell Disease

My current thesis focuses on quantitative assessment of iron concentration and oxygenation using advanced MRI-based techniques. The work primarily involves Quantitative Susceptibility Mapping (QSM) for accurate estimation of tissue magnetic susceptibility, serving as a biomarker for iron deposition and oxygen-related variations in biological tissues.

I am actively involved in developing and implementing image processing pipelines for QSM, including phase processing, background field removal and susceptibility reconstruction. The aim is to achieve high-resolution, quantitative mapping for improved understanding of physiological and pathological conditions. This project is being carried out in collaboration with Dr. Richa at AIIMS Raipur.

Additionally, I am working on MRI pulse sequence development, with an emphasis on the systematic optimization of acquisition parameters to enhance image quality, signal fidelity and acquisition efficiency.