Applied scientist and interdisciplinary researcher working at the intersection of AI/ML, medical image analysis, neuroimaging, digital pathology and digital health systems. Over the last two decades, I’ve worked across academia, clinical research, and large-scale industrial AI, developing computational methods that bring together deep learning, diffusion MRI, brain network modeling, quantitative pathology, multimodal clinical data, and cloud-edge AI pipelines.

My work focuses on building reproducible, scalable imaging workflows that help clinicians interpret complex MRI, pathology, and clinical information. At the National Institutes of Health (NIH), I contributed to neuroimaging studies of neurodegenerative disorders, strengthening my interest in translational neuroscience. At Flagship Biosciences, I expanded into digital pathology developing automated analysis pipelines, applying ML to whole-slide imaging, and supporting biomarker discovery for clinical trials. I enjoy translating advanced algorithms into practical tools that improve imaging analytics, automate pipelines, supporting diagnostic workflows, or enabling more robust modeling of neurological conditions.

I’ve had the opportunity to present my work at international conferences, collaborate with multidisciplinary teams, and publish research spanning deep learning, neuroimaging, and translational data science. I’ve also spent many years designing cloud-native AI architectures, automating pipelines, and leading teams as a mentor, architect, and hands-on technical contributor.

I completed my Ph.D. at Vanderbilt University, where I developed expertise in diffusion microstructure and cortical surface–based analysis, along with a deep appreciation for interdisciplinary and collaborative research. I continue to build on that foundation by exploring how computing, neuroscience, and health technologies can converge to solve meaningful, human-centered problems.

I’m passionate about ethical AI, inclusive mentorship, and creating technologies that improve people’s lives. Whether analyzing brain images, building AI systems, or guiding students and teams, I’m driven by curiosity, interdisciplinary collaboration, and a commitment to making complex ideas accessible and impactful.

Research Area

Magnetic resonance imaging has lot of potential in understanding the structure and function of the brain through in vivo images. These brain images however have so much variability across individuals. In addition, same person scanned at different time points or at different scanners or conditions also yield different results. Understanding the biological changes while addressing the confounding factors is a crucial area in studying healthy and disease conditions. My research area is towards building and automating image processing tools and workflows to aid reproducibility and support clinical diagnosis.  

Contribution to Science

Description 

Empirical model reproducibility is performed on diffusion data, more specifically on NODDI model as the optimized NODDI protocol can be carried out in a clinical setting. Moreover, as we delve into understanding brain tissue microstructure including GM, this model was chosen as it disentangles neurite density and orientation dispersion estimates yielding more specific markers.

Citations 

1. Parvathaneni P, Nath V, Blaber JA, Schilling KG, Hainline AE, Mojahed E, Anderson AW, Landman BA. Empirical reproducibility, sensitivity, and optimization of acquisition protocol, for Neurite Orientation Dispersion and Density Imaging using AMICO. Magn Reson Imaging. 2018 Jul;50:96-109. PubMed Central ID: PMC5970991. 

2. Nath V, Schilling KG, Parvathaneni P, Blaber J, Hainline AE, Ding Z, Anderson A, Landman BA. Empirical estimation of intravoxel structure with persistent angular structure and Q-ball models of diffusion weighted MRI. J Med Imaging (Bellingham). 2018 Jan;5(1):014005. PubMed Central ID: PMC5838516. 

3. Nath V, Schilling KG, Hainline AE, Parvathaneni P, Blaber JA, Lyu I, Anderson AW, Kang H, Newton AT, Rogers BP, Landman BA. SHARD: Spherical Harmonic-based Robust Outlier Detection for HARDI Methods. Proc SPIE Int Soc Opt Eng. 2018 Mar;10574 PubMed Central ID: PMC5991608. 

4. Schilling KG, Nath V, Blaber JA, Parvathaneni P, Anderson AW, Landman BA. Empirical consideration of the effects of acquisition parameters and analysis model on clinically feasible q-ball imaging. Magn Reson Imaging. 2017 Jul;40:62-74. PubMed Central ID: PMC5500983. 

Description 

The gray matter surface based spatial statistics (GSBSS) approach was developed using gray matter surfaces to overcome the challenges of alignment issues and partial volume effects in low-resolution images like diffusion/functional MRI. Application of this technique was shown in diffusion MRI in psychosis population. This effort will facilitate getting the corresponding metrics of interest from each modality (T1, fMRI, DWI) in subject space and map them onto a target surface template in MNI space by making use of high resolution T1 images for cortical surface segmentation and registration.

Citations 

1. Parvathaneni P, Lyu I, Huo Y, Rogers BP, Schilling KG, Nath V, Blaber JA, Hainline AE, Anderson AW, Woodward ND, Landman BA. Improved gray matter surface based spatial statistics in neuroimaging studies. Magn Reson Imaging. 2019 Sep;61:285-295. PubMed Central ID: PMC6689417. 

2. Parvathaneni P, Rogers BP, Huo Y, Schilling KG, Hainline AE, Anderson AW, Woodward ND, Landman BA. Gray Matter Surface based Spatial Statistics (GS-BSS) in Diffusion Microstructure. Med Image Comput Comput Assist Interv. 2017 Sep;10433:638-646. PubMed Central ID: PMC5722235. 

Description 

We presented on how the cortical surface features are integrated into a deep neural network to achieve improved brain sulcal curve labeling and cortical parcellation tasks for achieving improved speed, higher accuracy and better consistency in large-scale brain MRI datasets.

Citations 

1. Parvathaneni P, Nath V, McHugo M, Huo Y, Resnick SM, Woodward ND, Landman BA, Lyu I. Improving human cortical sulcal curve labeling in large scale cross-sectional MRI using deep neural networks. J Neurosci Methods. 2019 Aug 1;324:108311. PubMed Central ID: PMC6663093. 

2. Huo Y, Xu Z, Xiong Y, Aboud K, Parvathaneni P, Bao S, Bermudez C, Resnick SM, Cutting LE, Landman BA. 3D whole brain segmentation using spatially localized atlas network tiles. Neuroimage. 2019 Jul 1;194:105-119. PubMed Central ID: PMC6536356. 

3. Parvathaneni P, Bao S, Nath V, Woodward ND, Claassen DO, Cascio CJ, Zald DH, Huo Y, Landman BA, Lyu I. Cortical Surface Parcellation using Spherical Convolutional Neural Networks. Med Image Comput Comput Assist Interv. 2019 Oct;11766:501-509. PubMed Central ID: PMC6892466.