Impact of Exposure Parameters on Deep Learning Models in Chest Radiography and Implications for Deployment

Radiology Artificial Intelligence 2026 Open access

Read full text
Authors: H. Shu, Shun-Ting Chang, Rodrigo Rosa Gameiro, Judy Wawira Gichoya, Leo Anthony Celi, Po‐Chih Kuo
DOI: 10.1148/ryai.250731
Cited by: 1
References: 18

Abstract

An algorithmic framework was developed to identify and quantify shortcut learning and bias driven by exposure parameters in chest radiographs, revealing hidden sources of bias in medical artificial intelligence.

Fields of Study & Subjects

COVID-19 diagnosis using AI Artificial Intelligence in Healthcare and Education Ultrasound in Clinical Applications

Publication details

Journal / source
Radiology Artificial Intelligence
Publisher
Radiological Society of North America (RSNA)
Volume
8
Issue
4
Pages
e250731–e250731
Publication date
24 June 2026
Language
EN