BE-WISER: Class-Aware Weak Slice-Level Supervision for Breast MRI

Bhandary Panambur A, Nguyen TT, Islam S, Uder M, Bickelhaupt S, Maier A, Bayer S (2026)

Publication Status: In review

Publication Type: Unpublished / Preprint

Future Publication Type: Journal article

Publication year: 2026

Original Authors: Adarsh Bhandary Panambur, Tri-Thien Nguyen, Saahil Islam, Michael Uder, Sebastian Bickelhaupt, Andreas Maier, Siming Bayer

DOI: 10.21203/rs.3.rs-9855612/v1

Abstract

Purpose: Breast MRI is sensitive for cancer assessment, but deep learning models often require dense lesion annotations. This study evaluates whether weak slice-level supervision can be extended from binary lesion localization to class-aware slice semantics. 

Methods: We propose BE-WISER, a weakly supervised framework that builds on the recently proposed BE-WISE approach by extending binary slice-level lesion localization to three-class slice semantics. BE-WISER models each slice as normal, benign, or malignant and combines a Swin Transformer slice encoder, attention-based multiple-instance learning for breast-level classification, and a class-aware slice head for weak lesion localization. Gaussian targets from a single radiologist-indicated lesion slice provide weak supervision, and radiologist review was used to assess the clinical plausibility of predicted high-probability slices. 

Results: On the independent ODELIA test set, BE-WISER with focal loss achieved the best breast-level performance, with an AUC of 0.864 and an ODELIA score of 0.699. This improved over BE-WISE with focal loss by 1.2 and 2.6 percentage points, respectively. For localization, BE-WISER achieved the lowest mean slice distance of 2.505 slices and the highest Hit@1 of 0.632. Radiologist review indicated that highprobability slices corresponded well to lesion-relevant slices. 

Conclusion: BE-WISER demonstrates that pathology-aware slice semantics improve weakly supervised breast MRI diagnosis and lesion localization while preserving clinically interpretable slice-level evidence.

Authors with CRIS profile

How to cite

APA:

Bhandary Panambur, A., Nguyen, T.-T., Islam, S., Uder, M., Bickelhaupt, S., Maier, A., & Bayer, S. (2026). BE-WISER: Class-Aware Weak Slice-Level Supervision for Breast MRI. (Unpublished, In review).

MLA:

Bhandary Panambur, Adarsh, et al. BE-WISER: Class-Aware Weak Slice-Level Supervision for Breast MRI. Unpublished, In review. 2026.

BibTeX: Download