Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and Beyond

Bhat S, Georgescu B, Bhandary Panambur A, Zinnen M, Nguyen TT, Mansoor A, Elbarbary K, Bayer S, Ghesu FC, Grbic S, Maier A (2025)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2025

Publisher: Springer, Cham

Series: Lecture Notes in Computer Science

Book Volume: 15965

Pages Range: 205-215

Conference Proceedings Title: 28th International Conference of Medical Image Computing and Computer Assisted Intervention – MICCAI 2025

Event location: Daejeon

ISBN: 978-3-032-04977-3

URI: https://link.springer.com/chapter/10.1007/978-3-032-04978-0_20#chapter-info

DOI: 10.1007/978-3-032-04978-0_20

Abstract

Detecting abnormalities in medical images poses unique challenges due to differences in feature representations and the intricate relationship between anatomical structures and abnormalities. This is especially evident in mammography, where dense breast tissue can obscure lesions, complicating radiological interpretation. Despite leveraging anatomical and semantic context, existing detection methods struggle to learn effective class-specific features, limiting their applicability across different tasks and imaging modalities. In this work, we introduce Exemplar Med-DETR, a novel multi-modal contrastive detector that enables feature-based detection. It employs cross-attention with inherently derived, intuitive class-specific exemplar features and is trained with an iterative strategy. We achieve state-of-the-art performance across three distinct imaging modalities from four public datasets. On Vietnamese dense breast mammograms, we attain an  mAP50 of 0.7 for mass detection and 0.55 for calcifications, yielding an absolute improvement of 16% points from previous state-of-the-art. Additionally, a radiologist-supported evaluation of 100 mammograms from an out-of-distribution Chinese cohort demonstrates a twofold gain in lesion detection performance. For chest X-rays and angiography, we achieve an  mAP50 of 0.25 for mass and 0.37 for stenosis detection, improving results by 4% and 7% points, respectively. These results highlight the potential of our approach to advance robust and generalizable detection systems for medical imaging.

Authors with CRIS profile

Involved external institutions

Siemens AG, Healthcare Sector Germany (DE) Siemens Healthineers Germany (DE)

How to cite

APA:

Bhat, S., Georgescu, B., Bhandary Panambur, A., Zinnen, M., Nguyen, T.-T., Mansoor, A.,... Maier, A. (2025). Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and Beyond. In 28th International Conference of Medical Image Computing and Computer Assisted Intervention – MICCAI 2025 (pp. 205-215). Daejeon, KR: Springer, Cham.

MLA:

Bhat, Sheethal, et al. "Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and Beyond." Proceedings of the MICCAI 2025, Daejeon Springer, Cham, 2025. 205-215.

BibTeX: Download