EUVIMEDEUVIMED entdecken
Crossref

CLID: A contrastive learning approach for multi-class classification of breast cancer histopathological images with imbalanced distribution

Wenxiu Li iD, Lingyu Shi, Huixing He

Journal of X-Ray Science and Technology · 2026-07 · 34 (4) · 489-502

DOI: 10.1177/08953996261451158 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, online erschienen am 22.05.2026. Verfasst von Wenxiu Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Artificial Intelligence Engineering and Applications, Shanghai University of Finance and Economics Zhejiang College, Jinhua, China. Hauptthemen laut MEDLINE: Breast Neoplasms, Image Processing, Computer-Assisted, Machine Learning. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Science and Technology Program of Guizhou Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Globally, breast cancer is recognized as the leading form of malignant tumor in women, significantly impacting public health on an international scale. However, current breast cancer classification methods often overlook the imbalanced data distribution within breast cancer datasets. This leads to models being biased toward majority-class samples during classification, while underperforming on minority-class samples, thereby reducing overall classification accuracy. Moreover, multi-classification approaches can provide physicians with richer diagnostic information and better support the development of treatment strategies. To address these challenges, we introduce a breast cancer multi-classification algorithm, CLID (Contrastive Learning for Imbalanced Distribution), which utilizes contrastive learning to address the problem of imbalanced data distribution. Specifically, a preprocessed convolutional neural network is employed to extract features from histopathological images. Learnable archetype vectors are employed to model inter-category similarities, and a contrastive learning loss function is used to train the model. Experimental results on the BreakHis and BRACS datasets demonstrate that the proposed method achieves superior performance compared with existing approaches and representative imbalance-aware learning strategies, showing strong robustness under different magnifications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsImage Processing, Computer-AssistedMachine LearningFemaleClassification AlgorithmsHumansConvolutional Neural NetworksAlgorithms

Stichwörter der Autor:innen

breast cancercontrastive learninghistopathologyimbalanced distributionmulti-class classification

Autor:innen und Institutionen

  • Key Laboratory of Artificial Intelligence Engineering and Applications, Shanghai University of Finance and Economics Zhejiang College, Jinhua, China.
  • State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, China.
  • School of Computer Science and Engineering, Guangzhou Institute of Science and Technology, Guangzhou, China.

ORCID-Profile: Wenxiu Li

Förderung

  • Science and Technology Program of Guizhou Province

Zitieren

APA

Li, W., Shi, L., & He, H. (2026). CLID: A contrastive learning approach for multi-class classification of breast cancer histopathological images with imbalanced distribution. Journal of X-Ray Science and Technology, 34(4), 489-502. https://doi.org/10.1177/08953996261451158

Vancouver

Li W, Shi L, He H. CLID: A contrastive learning approach for multi-class classification of breast cancer histopathological images with imbalanced distribution. Journal of X-Ray Science and Technology. 2026;34(4):489-502. doi:10.1177/08953996261451158

BibTeX
@article{Li2026,
  author = {Li, Wenxiu and Shi, Lingyu and He, Huixing},
  title = {CLID: A contrastive learning approach for multi-class classification of breast cancer histopathological images with imbalanced distribution},
  journal = {Journal of X-Ray Science and Technology},
  year = {2026},
  volume = {34},
  number = {4},
  pages = {489--502},
  doi = {10.1177/08953996261451158}
}
Kostenlos starten →