Benign Share Benefit to Malignant: Balanced Mixing on Feature Space for Imbalanced Breast Cancer Classification
Bioengineering · 30.06.2026 · 13 (7) · 765
DOI: 10.3390/bioengineering13070765 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 30.06.2026. Verfasst von Farchan Hakim Raswa und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Information Engineering, National Central University, Taoyuan 320317, Taiwan. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- 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.
ORCID-Profile: Farchan Hakim Raswa, Ika Candradewi, Afiahayati, Ming-Hsiang Su, Chung-I Huang, Kuo-Chen Li, Shih-Lun Chen, Yung-Hui Li
Zitieren
APA
Raswa, F. H., Fadlurrohman, M., Pham, B. T., Candradewi, I., Afiahayati, Su, M. H., Huang, C. I., Li, K. C., Chen, S. L., Li, Y. H., & Wang, J. C. (2026). Benign Share Benefit to Malignant: Balanced Mixing on Feature Space for Imbalanced Breast Cancer Classification. Bioengineering, 13(7), 765. https://doi.org/10.3390/bioengineering13070765
Vancouver
Raswa FH, Fadlurrohman M, Pham BT, Candradewi I, Afiahayati, Su MH, et al. Benign Share Benefit to Malignant: Balanced Mixing on Feature Space for Imbalanced Breast Cancer Classification. Bioengineering. 2026;13(7):765. doi:10.3390/bioengineering13070765
BibTeX
@article{Raswa2026,
author = {Raswa, Farchan Hakim and Fadlurrohman, Muhammad and Pham, Bach-Tung and Candradewi, Ika and Afiahayati and Su, Ming-Hsiang and Huang, Chung-I and Li, Kuo-Chen and Chen, Shih-Lun and Li, Yung-Hui and Wang, Jia-Ching},
title = {Benign Share Benefit to Malignant: Balanced Mixing on Feature Space for Imbalanced Breast Cancer Classification},
journal = {Bioengineering},
year = {2026},
volume = {13},
number = {7},
pages = {765},
doi = {10.3390/bioengineering13070765}
}
EUVIMED