Back to all papers

Benign Share Benefit to Malignant: Balanced Mixing on Feature Space for Imbalanced Breast Cancer Classification.

June 30, 2026pubmed logopapers

Authors

Raswa FH,Fadlurrohman M,Pham BT,Candradewi I,Su MH,Huang CI,Li KC,Chen SL,Li YH,Wang JC

Affiliations (8)

  • Department of Computer Science and Information Engineering, National Central University, Taoyuan 320317, Taiwan.
  • Department of Computer Science and Electronics, Universitas Gadjah Mada, Yogyakarta 55281, Indonesia.
  • Department of Data Science, Soochow University, Taipei 100006, Taiwan.
  • Department of Management Information Systems, National Chung Hsing University, Taichung 402202, Taiwan.
  • Department of Information Management, Chung Yuan Christian University, Taoyuan 320314, Taiwan.
  • Department of Electronic Engineering, Chung Yuan Christian University, Taoyuan 320314, Taiwan.
  • Research Center for Semiconductor Materials and Advanced Optics, Chung Yuan Christian University, Taoyuan 320314, Taiwan.
  • AI Research Center, Hon Hai Research Institute, Taipei 114065, Taiwan.

Abstract

A deep learning model with an imbalanced mammography dataset can bias models toward common benign BI-RADS categories and reduce recognition of less frequent malignant or high-risk categories. To address this issue, we propose B2M (Benign Share Benefit to Malignant), a model-agnostic framework for imbalance-aware multi-class BI-RADS classification in C-View mammography. B2M uses a two-phase training strategy that combines dual sampling with feature-space mixing. In Phase I, the model is trained with dual sampling, integrating instance-based and class-balanced sampling to increase minority-class representation while preserving majority-class diversity. In Phase II, the model is fine-tuned with feature-space mixing using samples from the two sampling streams. A soft-target regularization objective supervises the mixed features using labels from both streams, encouraging smoother decision boundaries across BI-RADS categories. We evaluated B2M on an imbalanced mammography cohort from the C-View EMBED dataset using stratified 5-fold cross-validation across multiple CNN backbones. C-View is a synthesized 2D mammographic image generated from 3D digital breast tomosynthesis data, capturing DBT-derived structural information while requiring less memory and computation than processing the full 3D image volume. Among these experiments, ResNeXt-50 with B2M achieved the highest balanced accuracy and Macro-F1 scores compared with the evaluated oversampling and mixing-based methods. This improvement requires an offline training-time overhead of approximately 2.81×, but it does not increase inference cost. Overall, the results suggest that B2M may be useful for imbalanced multi-class BI-RADS classification in C-View mammography. However, the findings are based on the EMBED cohort, and further validation, including external and prospective evaluation, is needed before clinical use.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.