Dealing with Unreliable Annotations:A Noise-Robust Network for Semantic Segmentation through A Transformer-Improved Encoder and Convolution Decoder

Abstract

Conventional deep learning methods have shown promising results in the medical domain when trained on accurate ground truth data. Pragmatically, due to constraints like lack of time or annotator inexperience, the ground truth data obtained from clinical environments may not always be impeccably accurate. In this paper, we investigate whether the presence of noise in ground truth data can be mitigated. We propose an innovative and efficient approach that addresses the challenge posed by noise in segmentation labels. Our method consists of four key components within a deep learning framework. First, we introduce a Vision Transformer-based modified encoder combined with a convolution-based decoder for the segmentation network, capitalizing on the recent success of self-attention mechanisms. Second, we consider a public CT spine segmentation dataset and devise a preprocessing step to generate (and even exaggerate) noisy labels, simulating real-world clinical situations. Third, to counteract the influence of noisy labels, we incorporate an adaptive denoising learning strategy (ADL) into the network training. Finally, we demonstrate through experimental results that the proposed method achieves noise-robust performance, outperforming existing baseline segmentation methods across multiple evaluation metrics.

Publication DOI: https://doi.org/10.3390/app13137966
Divisions: College of Engineering & Physical Sciences
College of Engineering & Physical Sciences > School of Computer Science and Digital Technologies
Aston University (General)
Additional Information: Publisher Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Uncontrolled Keywords: computed tomography,image segmentation,noisy label,Vision Transformer,General Materials Science,Instrumentation,General Engineering,Process Chemistry and Technology,Computer Science Applications,Fluid Flow and Transfer Processes
Publication ISSN: 2076-3417
Data Access Statement: The dataset used in this study is public available at http://spineweb.digitalimaginggroup.ca/
Last Modified: 09 Oct 2025 17:58
Date Deposited: 22 Sep 2025 14:05
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://www.mdp ... 3417/13/13/7966 (Publisher URL)
PURE Output Type: Article
Published Date: 2023-07-07
Accepted Date: 2023-06-26
Authors: Wang, Ziyang (ORCID Profile 0000-0003-1605-0873)
Voiculescu, Irina

Download

[img]

Version: Published Version

License: Creative Commons Attribution


Export / Share Citation


Statistics

Additional statistics for this record