Efficient Model Monitoring for Quality Control in Cardiac Image Segmentation
This addresses the bottleneck of ensuring continuous high performance for translating deep learning into clinical cardiac image segmentation, though it is incremental as it builds on existing anomaly detection methods.
The paper tackled the problem of monitoring cardiac image segmentation models without ground truth by proposing an anomaly detection framework that derives surrogate quality measures, and demonstrated its accuracy and scalability by reproducing challenge rankings.
Deep learning methods have reached state-of-the-art performance in cardiac image segmentation. Currently, the main bottleneck towards their effective translation into clinics requires assuring continuous high model performance and segmentation results. In this work, we present a novel learning framework to monitor the performance of heart segmentation models in the absence of ground truth. Formulated as an anomaly detection problem, the monitoring framework allows deriving surrogate quality measures for a segmentation and allows flagging suspicious results. We propose two different types of quality measures, a global score and a pixel-wise map. We demonstrate their use by reproducing the final rankings of a cardiac segmentation challenge in the absence of ground truth. Results show that our framework is accurate, fast, and scalable, confirming it is a viable option for quality control monitoring in clinical practice and large population studies.