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

NLDL 2025 Conference Submission44 Authors

Keywords: deployment, fetal ultrasound, standard plane detection

Abstract: Despite the rapid development of AI models in medical image analysis, their validation in real world clinical settings remains limited. Models are often developed without continuous feedback from clinicians, which can lead to a lack of alignment with the actual needs. To address this, we introduce a generic framework designed for deploying and testing image-based AI models early in such settings. Using this framework, we deployed a trained 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 medical practitioners, 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 real-world settings, leading to insights that can guide the refinement of the model and system based on actual user feedback.

Submission Number: 44