Third paper published in AJR
Authors
Eun Kyoung Hong¹, Hae Won Kim², Ok Kyu Song¹, Kyu-Chong Lee³, Dong Kyu Kim⁴, Jae-Bock Jo⁵, Jungbin Kim⁶, Seungho Lee⁷, Woong Bae⁵, Byungseok Roh⁸
¹ Mass General Brigham, Boston, USA
² St. Mary's Hospital, Seoul, South Korea
³ Korea University College of Medicine, Seoul, South Korea
⁴ Severence Hospital, Seoul, South Korea
⁵ Soombit.AI, Seoul, South Korea
⁶ Kakaobrain, Seoul, South Korea
⁷ Seoul National University Hospital, Seoul, South Korea
⁸ Kakao corp, Seoul, South Korea
Abstract
Background: Chest radiographs play a crucial role in tuberculosis screening in high-prevalence regions, although widespread radiographic screening requires expertise that may be unavailable in settings with limited medical resources.
Objectives: To evaluate a multimodal generative artificial intelligence (AI) model for detecting tuberculosis-associated abnormalities on chest radiography in patients undergoing tuberculosis screening.
Published in American Journal of Roentgenology
https://ajronline.org/doi/10.2214/AJR.25.33059