Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Conformal Performance Range Prediction for Segmentation Output Quality Control

About

Recent works have introduced methods to estimate segmentation performance without ground truth, relying solely on neural network softmax outputs. These techniques hold potential for intuitive output quality control. However, such performance estimates rely on calibrated softmax outputs, which is often not the case in modern neural networks. Moreover, the estimates do not take into account inherent uncertainty in segmentation tasks. These limitations may render precise performance predictions unattainable, restricting the practical applicability of performance estimation methods. To address these challenges, we develop a novel approach for predicting performance ranges with statistical guarantees of containing the ground truth with a user specified probability. Our method leverages sampling-based segmentation uncertainty estimation to derive heuristic performance ranges, and applies split conformal prediction to transform these estimates into rigorous prediction ranges that meet the desired guarantees. We demonstrate our approach on the FIVES retinal vessel segmentation dataset and compare five commonly used sampling-based uncertainty estimation techniques. Our results show that it is possible to achieve the desired coverage with small prediction ranges, highlighting the potential of performance range prediction as a valuable tool for output quality control.

Anna M. Wundram, Paul Fischer, Michael Muehlebach, Lisa M. Koch, Christian F. Baumgartner• 2024

Related benchmarks

TaskDatasetResultRank
Medical Image SegmentationISIC 2018--
193
Medical Image SegmentationJSRT--
38
Medical Image SegmentationPSFHS
Average Coverage92.6
5
Medical Image Segmentation3D-IRCAdB Liver
Average Coverage97.6
5
Medical Image SegmentationNuCLS
Average Coverage92.8
5
Medical Image SegmentationSCD
Average Coverage91.5
5
Medical Image SegmentationHC18
Average Coverage89.6
5
Medical Image SegmentationWBC JTSC
Average Coverage84.4
5
Medical Image SegmentationWBC CV
Average Coverage80.7
5
Showing 9 of 9 rows

Other info

Follow for update