The American College of Radiology Data Science Institute (ACR DSI) has released a series of standardized artificial intelligence (AI) use cases that will accelerate the adoption of AI for medical imaging.
The use cases will increase adoption by ensuring that AI algorithms address relevant clinical questions, can be implemented across multiple electronic workflow systems, enable ongoing quality assessment, and comply with legal, regulatory, and ethical requirements.
The use cases will make it easier for developers to create algorithms that provide specific information medical professionals need and that can be implemented into clinical practice, said Rik Primo, manager of imaging informatics strategic relationships at Siemens Healthineers.
The continually updated, freely available series of use cases is the product of a collaborative framework that enables the efficient creation, implementation, and ongoing improvement of radiological AI tools, according to the institute. Specifically, the Technology Oriented Use Cases in Healthcare - AI (TOUCH-AI) framework uses multispecialty, multi-industry expert panels to define clinically relevant use cases for the development of medical imaging, interventional radiology, and radiation oncology AI algorithms. It also establishes a methodology and provides tools and metrics for creating algorithm training, testing, and validation of datasets around these use cases, the ACR DSI said.
The TOUCH-AI framework also develops standardized pathways for implementing AI algorithms in clinical practice, creates opportunities to monitor the effectiveness of AI algorithms in clinical practice, and addresses regulatory, legal, and ethical issues regarding medical imaging, interventional radiology, and radiation oncology AI.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
