Relation U-Net

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Sheng, Bao, Rina, Grant, P. Ellen, Ou, Yangming
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916567992762368
author He, Sheng
Bao, Rina
Grant, P. Ellen
Ou, Yangming
author_facet He, Sheng
Bao, Rina
Grant, P. Ellen
Ou, Yangming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Relation U-Net
He, Sheng
Bao, Rina
Grant, P. Ellen
Ou, Yangming
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Relation U-Net
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.09101