Relation U-Net

TL;DR

This paper introduces Relation U-Net, a segmentation model that outputs multiple segmentation maps, their relations, and an estimated confidence score, enhancing accuracy and providing confidence estimation without ground-truth.

Contribution

The novel Relation U-Net architecture jointly models multiple input and output relations, enabling improved segmentation accuracy and confidence estimation without ground-truth.

Findings

Outperforms vanilla U-Net in accuracy on four datasets.

Provides confidence scores linearly correlated with segmentation accuracy.

Capable of estimating confidence without ground-truth.

Abstract

Towards clinical interpretations, this paper presents a new ''output-with-confidence'' segmentation neural network with multiple input images and multiple output segmentation maps and their pairwise relations. A confidence score of the test image without ground-truth can be estimated from the difference among the estimated relation maps. We evaluate the method based on the widely used vanilla U-Net for segmentation and our new model is named Relation U-Net which can output segmentation maps of the input images as well as an estimated confidence score of the test image without ground-truth. Experimental results on four public datasets show that Relation U-Net can not only provide better accuracy than vanilla U-Net but also estimate a confidence score which is linearly correlated to the segmentation accuracy on test images.