Multi-institutional classification of lesions in breast MRI: a comparison of one-stage and two-stage methods
Year: 2026
Type: article
Abstract: 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.
Source: Journal of medical imaging
Authors: Kai Geissler, Laurens Müller-Groh, Hans Meine, Torbjörn Vik, Hendrik Laue, Susanne Diekmann, Robert Grimm, Heinrich von Busch, Uwe Fischer, Dieter Szolar, Sabine Ohlmeyer, Edyta Szurowska, Nachiko Uchiyama, Kazuki Oyama, Noemi Schmidt, Pratiksha Yadav, Miri Sklair-Levy, Athina Vourtsi, Markus Wenzel
Institutions: Fraunhofer Institute for Digital Medicine, Siemens Healthineers (Germany), Universitätsmedizin Göttingen, Universitätsklinikum Erlangen, Gdańsk Medical University, Shinshu University, University Hospital of Basel, Dr. D. Y. Patil Medical College, Hospital and Research Centre, Sheba Medical Center
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7223693040