activity
20182022
most citedAssessing the validity of saliency maps for abnormality localization in medical imaging

17 citations · 32 across the 7 of their papers we have counts for

collaborators

10 papers

cs.LG2022

Towards More Efficient Data Valuation in Healthcare Federated Learning using Ensembling

Sourav Kumar, A. Lakshminarayanan, Ken Chang +5

Federated Learning (FL) wherein multiple institutions collaboratively train a machine learning model without sharing data is becoming popular. Participating institutions might not…

cs.CV20214 cited

Not Color Blind: AI Predicts Racial Identity from Black and White Retinal Vessel Segmentations

Aaron S. Coyner, Praveer Singh, James M. Brown +5

Background: Artificial intelligence (AI) may demonstrate racial bias when skin or choroidal pigmentation is present in medical images. Recent studies have shown that convolutional…

cs.LG20214 cited

Addressing catastrophic forgetting for medical domain expansion

Sharut Gupta, Praveer Singh, Ken Chang +13

Model brittleness is a key concern when deploying deep learning models in real-world medical settings. A model that has high performance at one institution may suffer a significant…

cs.LG20202 cited

The unreasonable effectiveness of Batch-Norm statistics in addressing catastrophic forgetting across medical institutions

Sharut Gupta, Praveer Singh, Ken Chang +9

Model brittleness is a primary concern when deploying deep learning models in medical settings owing to inter-institution variations, like patient demographics and intra-institutio…

cs.CV20203 cited

Towards Trainable Saliency Maps in Medical Imaging

Mehak Aggarwal, Nishanth Arun, Sharut Gupta +9

While success of Deep Learning (DL) in automated diagnosis can be transformative to the medicinal practice especially for people with little or no access to doctors, its widespread…

eess.IV2020

Federated Learning for Breast Density Classification: A Real-World Implementation

Holger R. Roth, Ken Chang, Praveer Singh +40

Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical ima…