Testing of Deep Learning Model in Real World Clinical Setting: A Case Study in Obstetric Ultrasound

Despite the rapid development of AI models in medical image analysis, their validation in real-world clinical settings remains limited. To address this, we introduce a generic framework designed for testing image-based AI models in such settings. Using this framework, we deployed a model for fetal ultrasound standard plane detection and evaluated it in real-time sessions with both novice and expert users. Feedback from these sessions revealed that while the model offers potential benefits to clinicians, the need for navigational guidance was identified as a key area for improvement. These findings underscore the importance of early testing of AI models in realworld settings, leading to insights that can guide the refinement of the model and system based on user feedback. Code: https://github.com/wong-ck/deploy-fetal-us.