Sarthak Pati
University of Pennsylvania
11 Papers
17 Citations
Sarthak Pati is an academic researcher from University of Pennsylvania. The author has contributed to research in topics: Computer science & Fluid-attenuated inversion recovery. The author has an hindex of 3, co-authored 11 publications.
Chat about Author
Papers
Standardization in Quantitative Imaging: A Multicenter Comparison of Radiomic Features from Different Software Packages on Digital Reference Objects and Patient Data Sets
Michael F. McNitt-Gray,Sandy Napel,Akshay Jaggi,Sarah A. Mattonen,Sarah A. Mattonen,Lubomir M. Hadjiiski,Mark Muzi,Dmitry B. Goldgof,Yoganand Balagurunathan,Larry Pierce,Paul E. Kinahan,Ella F. Jones,A. Nguyen,A. Virkud,Heang Ping Chan,Nastaran Emaminejad,M Wahi-Anwar,M. Daly,Mahmoud A. Abdalah,Hao Yang,Lin Lu,Wenbing Lv,Arman Rahmim,Aimilia Gastounioti,Sarthak Pati,Spyridon Bakas,Despina Kontos,Binsheng Zhao,Jayashree Kalpathy-Cramer,Keyvan Farahani +29 more
- 01 Jun 2020
TL;DR: Assessment of radiomic features when computed by several groups by using different software packages under very tightly controlled conditions highlights the value of feature definition standardization as well as the need to further clarify definitions for some features.
•Posted Content
OpenFL: An open-source framework for Federated Learning.
G. Anthony Reina,Alexey Gruzdev,Patrick Foley,Olga Perepelkina,Mansi Sharma,Igor Davidyuk,Ilya Trushkin,Maksim Radionov,Aleksandr Mokrov,Dmitry Agapov,Jason Martin,Brandon Edwards,Micah J. Sheller,Sarthak Pati,Prakash Narayana Moorthy,Hans Shih-Han Wang,Prashant Shah,Spyridon Bakas +17 more
TL;DR: OpenFL as mentioned in this paper is an open-source framework for training ML algorithms using the data-private collaborative learning paradigm of FL, which can be easily extended to other ML and deep learning frameworks.
49
•Posted Content
The Federated Tumor Segmentation (FeTS) Challenge.
Sarthak Pati,Ujjwal Baid,Maximilian Zenk,Brandon Edwards,Micah J. Sheller,G. Anthony Reina,Patrick Foley,Alexey Gruzdev,Jason Martin,Shadi Albarqouni,Yong Chen,Russell T. Shinohara,Annika Reinke,David Zimmerer,John Freymann,Justin Kirby,Christos Davatzikos,Rivka R. Colen,Aikaterini Kotrotsou,Daniel S. Marcus,Mikhail Milchenko,Arash Nazeri,Hassan M. Fathallah-Shaykh,Roland Wiest,Andras Jakab,Marc-André Weber,Abhishek Mahajan,Lena Maier-Hein,Jens Kleesiek,Bjoern H. Menze,Klaus H. Maier-Hein,Spyridon Bakas +31 more
TL;DR: The first challenge on federated learning, namely the Federated Tumor Segmentation (FeTS) challenge 2021, was proposed in this article, where the objective is to identify the optimal weight aggregation approach towards the training of a consensus model that has gained knowledge from multiple geographically distinct institutions.
33
Reproducibility analysis of multi-institutional paired expert annotations and radiomic features of the Ivy Glioblastoma Atlas Project (Ivy GAP) dataset
Sarthak Pati,Ruchika Verma,Hamed Akbari,Michel Bilello,Virginia Hill,Chiharu Sako,Ramon Correa,Niha Beig,Ludovic Venet,Siddhesh Thakur,Prashant Serai,Prashant Serai,Sung Min Ha,Geri Blake,Russell T. Shinohara,Pallavi Tiwari,Spyridon Bakas +16 more
TL;DR: This work addresses two critical challenges with regard to developing robust radiomic approaches: the lack of availability of reliable segmentation labels for GBM tumor sub-compartments, and identifying "reproducible" radiomic features that are robust to segmentation variability across readers/sites.
32
Multi-institutional noninvasive in vivo characterization of IDH, 1p/19q, and EGFRvIII in glioma using neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk).
Saima Rathore,Suyash Mohan,Spyridon Bakas,Chiharu Sako,Chaitra Badve,Sarthak Pati,Ashish Singh,Dimitrios Bounias,Phuc Ngo,Hamed Akbari,Aimilia Gastounioti,Mark Bergman,Michel Bilello,Russell T. Shinohara,Paul A. Yushkevich,Donald M. O'Rourke,Andrew E. Sloan,Andrew E. Sloan,Despina Kontos,MacLean Nasrallah,Jill S. Barnholtz-Sloan,Christos Davatzikos +21 more
- 31 Dec 2020
TL;DR: In this article, a method for noninvasive detection of radiogenomic markers of IDH both in lower-grade gliomas (WHO grade II and III tumors) and glioblastoma (who grade IV) was developed.
17