Kakao Brain has unveiled a web-based research tool powered by KARA-CXR AI for analyzing chest X-ray images, delivering rapid preliminary radiology reports upon image upload. The tool allows users to receive both simple and detailed AI interpretations, upload multiple DICOM files at once, and share reports within their research group or medical community. Additionally, the technology ensures compliance with security standards by anonymizing and safeguarding personal information in DICOM files.
In 2022, Kakao Brain initiated the development of KARA-CXR in collaboration with 11 leading university hospitals and major medical institutions, including Ewha Womans University Medical Center, Ajou University Hospital, and Soonchunhyang Medical Center, among others. KARA-CXR has analyzed more than 16 million chest X-ray images and readings. Utilizing Kakao Brain’s specialized large-scale generative AI model for healthcare, the research team is gearing up to publish their findings in reputable academic journals.
Kakao Brain is pursuing European Union certification and approval from the U.S. FDA and Korean Ministry of Food and Drug Safety. Their aim is to expand the AI-powered radiology solution to address inefficiencies in interpretation and reporting processes, alleviate radiologist shortages, and ease the growing workload on healthcare professionals. KARA-CXR, currently an RUO tool, is available solely for research purposes and is not intended for diagnostic or treatment purposes.
Kakao Brain CEO Kim Il-doo says, “As KARA-CXR was developed using high-quality data and the latest technology involving large-scale learning and generative AI, I hope that it will eventually play a great role in enhancing the workflow for the radiologists, not to mention improving the efficiency of chest X-ray image interpretation.”
“We are planning to go beyond generating AI interpretations of chest X-rays by expanding the algorithms to include interactive functions that support a variety of medical imaging tests, by utilizing the advanced large-scale multi-modal generative AI technology,” he adds.
