Robust Image Segmentation Quality Assessment

Leixin Zhou; Wenxiang Deng; Xiaodong Wu

Back

Robust Image Segmentation Quality Assessment

Preprint

Open access

Robust Image Segmentation Quality Assessment

Leixin Zhou, Wenxiang Deng and Xiaodong Wu

ArXiv.org

03/20/2019

Files and links (1)

url

https://arxiv.org/abs/1903.08773View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus predicting segmentation quality without ground truth would be very crucial especially in clinical practice. Recently, people proposed to train neural networks to estimate the quality score by regression. Although it can achieve promising prediction accuracy, the network suffers robustness problem, e.g. it is vulnerable to adversarial attacks. In this paper, we propose to alleviate this problem by utilizing the difference between the input image and the reconstructed image, which is conditioned on the segmentation to be assessed, to lower the chance to overfit to the undesired image features from the original input image, and thus to increase the robustness. Results on ACDC17 dataset demonstrated our method is promising.

Computer Science - Computer Vision and Pattern Recognition

Details

Title: Subtitle: Robust Image Segmentation Quality Assessment
Creators: Leixin Zhou
Wenxiang Deng
Xiaodong Wu
Resource Type: Preprint
Publication Details: ArXiv.org
ISSN: 2331-8422
Language: English
Date posted: 03/20/2019
Academic Unit: Radiation Oncology; Electrical and Computer Engineering
Record Identifier: 9984198005702771

Metrics

9 Record Views