Multi-institutional classification of lesions in breast MRI: a comparison of one-stage and two-stage methods
Purpose: Breast magnetic resonance imaging (MRI) is widely used for diagnostic imaging in breast cancer, creating a need for automated image analysis to assist early detection and diagnosis. We approach the task of lesion suspiciousness classification in breast MRI. Approach: Using a multi-centric data collection of 3792 patients, we compare a two-stage classification model based on nnU-Net and a three-dimensional (3D) Swin Transformer with the one-stage classifiers nnDetection and RadYOLO, our 3D extension of YOLO11. Results: In a fivefold leave-sites-out cross-validation scheme, the mean (standard deviation) across folds of the lesion classification area under the receiver operating curve (ROC-AUC) is 0.754 (0.086) for the two-stage model, 0.693 (0.108) for nnDetection, 0.737 (0.074) for RadYOLO, and 0.755 (0.064) for RadYOLO with a separate classification output. Conclusions: Although classification performance does not differ conclusively across methods, RadYOLO achieves 3 to 10 times shorter inference times.
Authors
- Kazuki Oyama (ORCID: https://orcid.org/0000-0002-8069-2638)
- Heinrich von Busch (ORCID: https://orcid.org/0000-0003-0469-1622)
- Hendrik Laue (ORCID: https://orcid.org/0000-0003-4271-3861)
- Makarius Wenzel (ORCID: https://orcid.org/0000-0002-3753-8280)
- Edyta Szurowska (ORCID: https://orcid.org/0000-0002-7042-4381)
- Dieter H. Szolar (ORCID: https://orcid.org/0000-0001-9228-0166)
- Miri Sklair‐Levy (ORCID: https://orcid.org/0000-0003-3460-258X)
- Robert Grimm (ORCID: https://orcid.org/0000-0002-1233-8215)
- Sabine Ohlmeyer (ORCID: https://orcid.org/0000-0001-9163-8840)
- Torbjörn Vik (ORCID: https://orcid.org/0009-0009-5013-3833)
- Uwe M Fischer
- Athina D. Vourtsi
- Pratiksha Yadav (ORCID: https://orcid.org/0000-0002-6290-4502)
- Nachiko Uchiyama
- Kai Geissler (ORCID: https://orcid.org/0009-0008-9709-0335)
Institutions
- Siemens (Germany) (DE)
- Shinshu University (JP)
- Sheba Medical Center (IL)
- National Cancer Centre Japan (JP)
- Universitätsklinikum Erlangen (DE)
- Dr. D. Y. Patil Medical College, Hospital and Research Centre (IN)
- Dr. D.Y. Patil Vidyapeeth, Pune (IN)
- Shinshu University Hospital (JP)
- Fraunhofer Institute for Digital Medicine (DE)
- Siemens Healthineers (Germany) (DE)
- Gdańsk Medical University (PL)
Publication Details
- Journal
- Journal of medical imaging
- Published
- 2026-10-26
- DOI
- https://doi.org/10.1117/1.jmi.13.5.054504
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00