CopilotCAD: Empowering Radiologists with Report Completion Models and Quantitative Evidence from Medical Image Foundation Models
This addresses the need for AI to support rather than replace radiologists in clinical practice, though it appears incremental as it builds on existing LLMs and foundation models.
The study tackled the problem of conventional computer-aided diagnosis systems acting as standalone decision-makers by introducing an assistive co-pilot system that integrates Large Language Models and medical image analysis tools to empower radiologists, resulting in more precise and detailed diagnostic reports with enhanced patient outcomes and reduced clinician burnout.
Computer-aided diagnosis systems hold great promise to aid radiologists and clinicians in radiological clinical practice and enhance diagnostic accuracy and efficiency. However, the conventional systems primarily focus on delivering diagnostic results through text report generation or medical image classification, positioning them as standalone decision-makers rather than helpers and ignoring radiologists' expertise. This study introduces an innovative paradigm to create an assistive co-pilot system for empowering radiologists by leveraging Large Language Models (LLMs) and medical image analysis tools. Specifically, we develop a collaborative framework to integrate LLMs and quantitative medical image analysis results generated by foundation models with radiologists in the loop, achieving efficient and safe generation of radiology reports and effective utilization of computational power of AI and the expertise of medical professionals. This approach empowers radiologists to generate more precise and detailed diagnostic reports, enhancing patient outcomes while reducing the burnout of clinicians. Our methodology underscores the potential of AI as a supportive tool in medical diagnostics, promoting a harmonious integration of technology and human expertise to advance the field of radiology.