Experts' Cognition-driven Safe Noisy Labels Learning for Precise Segmentation of Residual Tumor in Breast Cancer

Authors

  • Yongquan Yang Institute of Clinical Pathology, West China Hospital Sichuan University, China and Zhongjiu Flash Medical Technology Co., Ltd., China
  • Jie Chen Institute of Clinical Pathology, West China Hospital Sichuan University, China
  • Yani Wei Institute of Clinical Pathology and Department of Pathology, West China Hospital Sichuan University, China
  • Mohammad Alobaidi Department of Civil Engineering, McGill University, Canada
  • Hong Bu Institute of Clinical Pathology and Department of Pathology, West China Hospital Sichuan University, China

DOI:

https://doi.org/10.47852/bonviewJDSIS52024868

Keywords:

safe noisy label learning, safe weakly supervised learning, residual tumor segmentation, breast cancer

Abstract

Precise segmentation of residual tumor in breast cancer (PSRTBC) after neoadjuvant chemotherapy is a fundamental key technique in the treatment process of breast cancer. However, achieving PSRTBC is still a challenge, since the breast cancer tissue and tumor cells commonly have complex and varied morphological changes after neoadjuvant chemotherapy, which inevitably increases the difficulty to produce a predictive model that has good generalization with usual supervised learning (SL). To alleviate this situation, in this paper, we propose an experts’ cognition-driven safe noisy label learning (ECDSNLL) approach. In the concept of safe noisy label learning, which is a typical type of safe weakly SL, ECDSNLL is constructed by integrating the pathology experts’ cognition about identifying residual tumor in breast cancer and the artificial intelligence experts’ cognition about data modeling with provided data basis. Experimental results show that, compared with usual SL, ECDSNLL can significantly improve the lower bound of a number of UNet variants with 2.42% and 4.1% respectively in recall and fIoU for PSRTBC, while being able to achieve improvements in mean value and upper bound as well.

 

Received: 21 November 2024 | Revised: 10 January 2025 | Accepted: 23 January 2025

 

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

 

Data Availability Statement

Data available on request from the corresponding author upon reasonable request.

 

Author Contribution Statement

Yongquan Yang: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Writing – original draft, Visualization, Supervision, Project administration. Jie Chen: Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – review & editing. Yani Wei: Validation, Formal analysis, Investigation, Resources, Data curation, Writing – review & editing. Mohammad Alobaidi: Software, Validation, Formal analysis, Investigation, Writing – review & editing. Hong Bu: Validation, Formal analysis, Investigation, Resources, Writing – review & editing, Supervision, Project administration, Funding acquisition.

 


Downloads

Published

2025-03-06

Issue

Section

Research Articles

How to Cite

Yang, Y., Chen, J., Wei, Y., Alobaidi, M., & Bu, H. (2025). Experts’ Cognition-driven Safe Noisy Labels Learning for Precise Segmentation of Residual Tumor in Breast Cancer. Journal of Data Science and Intelligent Systems. https://doi.org/10.47852/bonviewJDSIS52024868