GroundingDINO for Open-Set Lesion Detection in Medical Imaging
Roughley SJ, Müller J, Gao S, Gao Z, Ligero M, Blums R, Crispin-Ortuzar M, Schnabel J, Kainz B, Bercea CI, Machado IP (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 16534 LNCS
Pages Range: 37-46
Conference Proceedings Title: Lecture Notes in Computer Science
Event location: Daejeon
ISBN: 9783032241818
DOI: 10.1007/978-3-032-24182-5_4
Abstract
Open-world anomaly detection is a task in which machine learning is well-positioned to advance cancer diagnosis, potentially leading to significantly improved survival rates. For a model to be used in clinical settings, it must demonstrate high performance, robustness, and generalisability. A common approach to achieving high generalisability is to incorporate information from broader representations within the model. In this work, we investigate the application of GroundingDINO to medical anomaly detection and localisation, evaluating both its overall performance and the influence of text prompts. We find that GroundingDINO outperforms the YOLOv11n model even with minimal use of contextual information. When exploring methods to introduce more contextual information, we observe that specifying the organ within the prompt improves closed-set performance on rarer lesion classes. However, adding visual descriptions of lesions during training leads to a significant performance drop on those subsets, indicating that the model memorises prompt-image pairs rather than learning meaningful semantic relationships. Our work highlights a critical limitation of GroundingDINO in medical imaging and proposes targeted modifications to the model architecture or training strategies as promising directions for utilising richer semantic prompts to improve anomaly detection.
Authors with CRIS profile
Johanna Müller
Professur für Image Data Exploration and Analysis
Bernhard Kainz
Professur für Image Data Exploration and Analysis
Involved external institutions
Technische Universität München (TUM)
Germany (DE)
University of Cambridge
United Kingdom (GB)
Technische Universität Dresden
Germany (DE)
Germany (DE)
University of Cambridge
United Kingdom (GB)
Technische Universität Dresden
Germany (DE)
How to cite
APA:
Roughley, S.J., Müller, J., Gao, S., Gao, Z., Ligero, M., Blums, R.,... Machado, I.P. (2026). GroundingDINO for Open-Set Lesion Detection in Medical Imaging. In Naren Akash, Cosmin Bercea, Amar Kumar (Eds.), Lecture Notes in Computer Science (pp. 37-46). Daejeon, KR: Springer Science and Business Media Deutschland GmbH.
MLA:
Roughley, Samuel J., et al. "GroundingDINO for Open-Set Lesion Detection in Medical Imaging." Proceedings of the 2nd MICCAI Student Board Empowering Medical Information Computing and Research Through Early-Career Guidance and Expertise Workshop, MSB EMERGE 2025, Held in Conjunction with 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025, Daejeon Ed. Naren Akash, Cosmin Bercea, Amar Kumar, Springer Science and Business Media Deutschland GmbH, 2026. 37-46.
BibTeX: Download