Medical AI Promotion Institute Inc. (Head Office: Chuo-ku, Tokyo; Director: Yuki Shimahara; Representative Director: Sho Kawabe; hereinafter “MAPI”) is pleased to announce that its research, “MAPPING THE PREDICTIVE LANDSCAPE OF CHEST RADIOGRAPHS BEYOND ANATOMICAL FEATURES,” has been accepted for presentation in the Scientific Poster session at the 112th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA 2026).

In this study, a Vision Transformer (*) was trained using self-supervised learning on 548,190 chest X-ray images. The resulting model was then applied to a separate patient population to extract image features, and the associations between these features and patient demographics, laboratory test results, and outcomes were analyzed.

We invite you to learn more about this research at RSNA 2026. During the conference, MAPI also plans to exhibit at a booth, where we will showcase “MAPI GATEWAY,” our system designed to support the anonymization of medical imaging data, as well as our re-facing technology. The booth number and Scientific Poster location are currently being finalized and will be announced once confirmed.

MAPI will continue to contribute to the advancement of medical data utilization and medical AI research in Japan, working toward a future in which AI is seamlessly integrated into everyday clinical practice and a wide variety of high-quality medical AI solutions are widely available.

(*) An AI model for image recognition

【Company Overview】
Company Name: Medical AI Promotion Institute Inc.
Representatives: Yuki Shimahara, Sho Kawabe
Head Office: Life Science Building 9, 4F, 12-9 Nihonbashi-Odemmacho, Chuo-ku, Tokyo, Japan
Established: November 8, 2023
Business: Development and operation of the “Next-Generation Medical Database Business,” which processes and sells medical data
URL: https://mapi-jp.org
Facebook: https://www.facebook.com/iryoaisuishinkiko
X: https://twitter.com/iryoai_mapi

【Contact】
Public Relations, Medical AI Promotion Institute
Email: pr@mapi-jp.org