Anant Madabhushi, PhD
NEPTUNE Ancillary Studies Grant Awardee
Dr. Anant Madabhushi, PhD is the Director of the Center for Computational Imaging and Personalized Diagnostics (CCIPD) and F. Alex Nason Professor II, Department of Biomedical Engineering, Case Western Reserve University. Dr. Madabhushi has authored over 270 peer-reviewed publications in leading international journals and conferences and has 25 issued patents pending in the areas of computer vision and medical image analysis for precision medicine of cancer. Dr. Madabhushi has had a long and productive history working in translational research and also in commercialization of biomedical technology. He was co-founder of Ibris Inc., a digital pathology based company in 2010.
Cleveland, Ohio
Case Western Reserve University
Lay Summary of the Project:
Conventional pathologic assessment of nephrotic syndrome (NS) fails to fully capture structural features that reflect mechanisms and predict outcomes. The Nephrotic Syndrome Study Network (NEPTUNE) pathologists have established a Digital Pathology Repository (DPR) of whole slide kidney biopsy images (WSI) and have developed methods to standardize visual assessment, resulting in increased reproducibility and accuracy. Dr. Madabhushi will study if computational annotation of primitives, attained with this pilot study, will enable discovery of visual and sub-visual features that can be used in future studies for discovery of molecular mechanisms and therapeutic targets, and clinically relevant categorization of NS. Consequently, we propose to develop and test foundational Apps (tool-box) of the NEPTUNE Digital Pathology-based Analytic hiSto-omicS intErrogation plaTform (NDP-ASSET) for segmentation of normal and pathologic (primary and secondary) classes of structural primitives. Convolutional neural network-based, deep learning (DL) algorithms will be trained for machine-based annotation of primitives in WSI of normal and diseased kidneys, and subsequently validated in an independent replication set. To demonstrate utility of the deeply annotated structural data, we will develop and apply tools for sub-visual feature extraction to test whether the sub-visual features can predict APOL1 risk genotypes in African American NEPTUNE patients.