China creates AI to read cancer images with a capacity to analyze multiple essential organs to assist in diagnosis.
A Chinese research team has created the country’s first versatile AI model capable of analyzing medical images from over 20 human organs, including the lungs, breasts, and liver.
Known as PathOrchestra, this large language model marks a significant breakthrough in AI-assisted disease diagnosis, shifting from models focused on specific cancers to a versatile one capable of addressing multiple types.
Researchers from Air Force Medical University, Tsinghua University, and SenseTime utilized China’s largest domestic dataset, containing nearly 300,000 whole-slide digital pathology images, amounting to 300 terabytes of data.
Using self-supervised learning, PathOrchestra “cross-learned” to analyze more than 20 different organs and successfully performed numerous clinical tasks, such as pan-cancer classification, lesion identification and detection, multi-cancer subtype differentiation, and biomarker assessment.
China creates AI to read cancer images, with a variety in pathological images presenting a significant challenge for AI applications, earning it the title of the “jewel in the crown” of image processing, according to Wang Zhe, a professor from Air Force Medical University’s Basic Medical Science Academy.
PathOrchestra achieved an accuracy rate exceeding 95 percent in nearly 50 clinical tasks, including lymphoma subtype diagnosis and bladder cancer screening, as reported by the university in a news release on Tuesday.
As China’s team creates AI to read cancer images, the model is expected to significantly reduce the workload of pathologists and improve the efficiency of medical image review, according to the researchers.
Among the more than 1,300 AI large language models worldwide, 36 percent originate from China, the second-largest proportion after the United States, as noted in a white paper on the global digital economy released by the China Academy of Information and Communications Technology at this month’s Global Digital Economy Conference 2024.
Related Posts:
Remote Robot-Assisted Lung Cancer Surgery in Xinjiang, China
