A Soft Label Method for Medical Image Segmentation with Multirater Annotations
Computational Intelligence and Neuroscience · 2023-01 · 2023 (1)
DOI: 10.1155/2023/1883597 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Intelligence and Neuroscience, online erschienen am 18.02.2023. Verfasst von Jichang Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science & Engineering, Shandong Normal University, No. 1 Daxue Road, Changqing District, Jinan 250358, China. Hauptthemen laut MEDLINE: Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Taishan Scholar Project of Shandong Province, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
In medical image analysis, collecting multiple annotations from different clinical raters is a typical practice to mitigate possible diagnostic errors. For such multirater labels’ learning problems, in addition to majority voting, it is a common practice to use soft labels in the form of full‐probability distributions obtained by averaging raters as ground truth to train the model, which benefits from uncertainty contained in soft labels. However, the potential information contained in soft labels is rarely studied, which may be the key to improving the performance of medical image segmentation with multirater annotations. In this work, we aim to improve soft label methods by leveraging interpretable information from multiraters. Considering that mis‐segmentation occurs in areas with weak supervision of annotations and high difficulty of images, we propose to reduce the reliance on local uncertain soft labels and increase the focus on image features. Therefore, we introduce local self‐ensembling learning with consistency regularization, forcing the model to concentrate more on features rather than annotations, especially in regions with high uncertainty measured by the pixelwise interclass variance. Furthermore, we utilize a label smoothing technique to flatten each rater’s annotation, alleviating overconfidence of structural edges in annotations. Without introducing additional parameters, our method improves the accuracy of the soft label baseline by 4.2% and 2.7% on a synthetic dataset and a fundus dataset, respectively. In addition, quantitative comparisons show that our method consistently outperforms existing multirater strategies as well as state‐of‐the‐art methods. This work provides a simple yet effective solution for the widespread multirater label segmentation problems in clinical diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Information Science & Engineering, Shandong Normal University, No. 1 Daxue Road, Changqing District, Jinan 250358, China.
ORCID-Profile: Jichang Zhang, Yuanjie Zheng, Yunfeng Shi
Förderung
- National Natural Science Foundation of China
- Taishan Scholar Project of Shandong Province
- Natural Science Foundation of Shandong Province
Zitieren
APA
Zhang, J., Zheng, Y., & Shi, Y. (2023). A Soft Label Method for Medical Image Segmentation with Multirater Annotations. Computational Intelligence and Neuroscience, 2023(1). https://doi.org/10.1155/2023/1883597
Vancouver
Zhang J, Zheng Y, Shi Y. A Soft Label Method for Medical Image Segmentation with Multirater Annotations. Computational Intelligence and Neuroscience. 2023;2023(1). doi:10.1155/2023/1883597
BibTeX
@article{Zhang2023,
author = {Zhang, Jichang and Zheng, Yuanjie and Shi, Yunfeng},
title = {A Soft Label Method for Medical Image Segmentation with Multirater Annotations},
journal = {Computational Intelligence and Neuroscience},
year = {2023},
volume = {2023},
number = {1},
doi = {10.1155/2023/1883597}
}
EUVIMED