6 papers
Feature Quality and Adaptability of Medical Foundation Models: A Comparative Evaluation for Radiographic Classification and Segmentation
Frank Li, Theo Dapamede, Mohammadreza Chavoshi +12
Foundation models (FMs) promise to generalize medical imaging, but their effectiveness varies. It remains unclear how pre-training domain (medical vs. general), paradigm (e.g., tex…
Impact of Label Noise from Large Language Models Generated Annotations on Evaluation of Diagnostic Model Performance
Mohammadreza Chavoshi, Hari Trivedi, Janice Newsome +6
Large language models (LLMs) are increasingly used to generate labels from radiology reports to enable large-scale AI evaluation. However, label noise from LLMs can introduce bias…
Evaluating Vision Language Models (VLMs) for Radiology: A Comprehensive Analysis
Frank Li, Hari Trivedi, Bardia Khosravi +8
Foundation models, trained on vast amounts of data using self-supervised techniques, have emerged as a promising frontier for advancing artificial intelligence (AI) applications in…
Novel AI-Based Quantification of Breast Arterial Calcification to Predict Cardiovascular Risk
Theodorus Dapamede, Aisha Urooj, Vedant Joshi +15
Women are underdiagnosed and undertreated for cardiovascular disease. Automatic quantification of breast arterial calcification on screening mammography can identify women at risk…
Subgroup Performance of a Commercial Digital Breast Tomosynthesis Model for Breast Cancer Detection
Beatrice Brown-Mulry, Rohan Satya Isaac, Sang Hyup Lee +10
While research has established the potential of AI models for mammography to improve breast cancer screening outcomes, there have not been any detailed subgroup evaluations perform…
Emory Knee Radiograph (MRKR) Dataset
Brandon Price, Jason Adleberg, Kaesha Thomas +6
The Emory Knee Radiograph (MRKR) dataset is a large, demographically diverse collection of 503,261 knee radiographs from 83,011 patients, 40% of which are African American. This da…