Sarthak Pati
School of Medicine, Indiana University, University of Pennsylvania, Technical University of Munich, Manipal Academy of Higher Education
Research areas: Computer Science · Computer Vision and Pattern Recognition · Medical Image Segmentation Techniques · Brain Tumor Detection and Classification · Radiomics and Machine Learning in Medical Imaging
0000-0003-2243-8487
About
My research interest focusses on machine learning and application of distributed and privacy-protected computational algorithms to solve problem pertaining to medical imaging. My work has spanned across the areas of robotics, machine learning, histopathology and image processing applied to medical imaging data. By maintaining close synergy with scientists and data analysts, my work should facilitate translation of algorithms towards extensive clinical and research use.
Employment
-
School of Medicine, Indiana University Software Architect2023 - 2025
-
University of Pennsylvania Application Architect2023 - 2023
-
University of Pennsylvania Senior Application Developer2014 - 2023
Education
- 2020 - 2025
-
Technical University of Munich Master of Science2011 - 2014
-
Manipal University B.E.2006 - 2010
Projects & Funding
Projects & funding information is unavailable.
Publications (58)
- From screening to subtyping in a single glance Save
- Optimization of deep learning models for inference in low resource environments Save
- Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge Save
- An Unsupervised Brain Extraction Quality Control Approach for Efficient Neuro-Oncology Studies Save
- Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction Save
- Federated learning in digital healthcare Save
- Volumetric Breast Density Estimation From Three-Dimensional Reconstructed Digital Breast Tomosynthesis Images Using Deep Learning Save
- Privacy preservation for federated learning in health care Save
- Federated benchmarking of medical artificial intelligence with MedPerf Save
- GaNDLF: the generally nuanced deep learning framework for scalable end-to-end clinical workflows Save
- Author Correction: Federated learning enables big data for rare cancer boundary detection Save
- Leveraging 2D Deep Learning ImageNet-trained Models for Native 3D Medical Image Analysis Save
- Federated learning enables big data for rare cancer boundary detection Save
- OpenFL: the open federated learning library Save
- The federated tumor segmentation (FeTS) tool: an open-source solution to further solid tumor research Save
- The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics Save
- Expert tumor annotations and radiomics for locally advanced breast cancer in DCE-MRI for ACRIN 6657/I-SPY1 Save
- Classification of Infection and Ischemia in Diabetic Foot Ulcers Using VGG Architectures Save
- Optimization of Deep Learning Based Brain Extraction in MRI for Low Resource Environments Save
- Robust Image Population Based Stain Color Normalization: How Many Reference Slides Are Enough? Save