Breast MRI Evaluation with Weakly-informed Slice-level Explanation

Bhandary Panamburg A, Nguyen TT, Bayer S, Maier A (2026)

Publication Type: Conference contribution

Publication year: 2026

Journal

Original Authors: Adarsh Bhandary Panambur, Tri-Thien Nguyen, Siming Bayer, Andreas Maier

Pages Range: 10-17

Event location: Lübeck

ISBN: 9783658510992

DOI: 10.1007/978-3-658-51100-5_2

Abstract

Breast MRI provides superior soft-tissue contrast and lesion conspicuity compared to mammography but its large-scale deployment is hampered by the need for fine-grained annotations. We propose BE-WISE, a transformer-based framework for interpretable breast MRI classification that jointly learns breast-level diagnosis and slice-level lesion localization from minimal radiologist input. The approach integrates a Swin transformer backbone into an attention-based multiple-instance learning scheme and optimizes a unified Gaussian-based objective that couples global and local supervision. On the multicenter ODELIA Breast MRI dataset, BE-WISE with focal loss attains a test AUC of 0.8683 and an Odelia score of 0.7098, improving over the medical slice transformer baseline by more than 7% in AUC and 14% in odelia score. Slice-wise prediction profiles align with expert-indicated lesion slices, supporting the interpretability of the model. These findings indicate that weak, slice-level expert guidance can substantially enhance diagnostic performance and enable human-in-the-loop AI for breast MRI.

Authors with CRIS profile

How to cite

APA:

Bhandary Panamburg, A., Nguyen, T.-T., Bayer, S., & Maier, A. (2026). Breast MRI Evaluation with Weakly-informed Slice-level Explanation. In Proceedings of the Bildverarbeitung für die Medizin 2026 (pp. 10-17). Lübeck, DE.

MLA:

Bhandary Panamburg, Adarsh, et al. "Breast MRI Evaluation with Weakly-informed Slice-level Explanation." Proceedings of the Bildverarbeitung für die Medizin 2026, Lübeck 2026. 10-17.

BibTeX: Download