Institute of Automation, Chinese Academy of Sciences

Review Maps Path From Foundation Models to Accountable Clinical AI in Medical Imaging

- A July 2026 review from Chinese Academy of Sciences and Beihang University researchers outlines four development paths for medical imaging foundation models, from image-representation pre-training to dynamic visual sequence modelling. - The review argues the field's next milestone should be evidence that a model works safely within a defined clinical role, not further increases in parameter counts. - A separate structured critical review of 80 sources concludes LLM-based clinical decision support is not supported for routine autonomous use and requires mandatory clinician supervision. - Both reviews call for prospective validation, reporting standards such as CLAIM, TRIPOD+AI and CONSORT-AI, and human-in-the-loop governance before clinical deployment.