Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR
Bhat S, Georgescu B, Mansoor A, Zinnen M, Sahu P, Ghesu FC, Grbic S, Maier A (2028)
Publication Language: English
Publication Status: In review
Publication Type: Unpublished / Preprint
Future Publication Type: Journal article
Publication year: 2028
Publisher: Medical Image Analysis
Abstract
Reducing annotation requirements remains a key challenge in developing ro bust medical object detectors. To address this, Vision-Language (VL) ob ject detection methods leverage grounding text information to enable pow erful zero-shot and few-shot object detectors in the natural image domain [1, 2, 3, 4]. However, transferring these methods to the medical domain is challenging due to the absence of comparable quality and quantity of the grounding data. Regardless, significant contextual and non-imaging informa tion exists in medical images that remains underutilized. Few-shot learning (FSL) techniques partially address this limitation but struggle to general ize to unseen medical findings and require extensive retraining when new findings are introduced [5, 6]. To overcome these challenges, we extend our prior EM-DETR framework [7] and introduce a scalable FS detection ap proach designed for efficient abnormality detection in Chest X-Ray (CXR) images under minimal supervision. The proposed architecture incorporates exemplar-based feature generation and domain-aware contrastive optimiza tion, enabling effective adaptation to novel disease findings without exhaus tive retraining. Our method achieves near state-of-the-art (SOTA) detection performance using less than 10% of the annotated data, demonstrating its potential for practical, annotation-efficient clinical deployment across both proprietary and public CXR datasets.
Authors with CRIS profile
Sheethal Bhat
Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) (LME)
Mathias Zinnen
Lehrstuhl für Informatik 5 (Mustererkennung)
Andreas Maier
Lehrstuhl für Informatik 5 (Mustererkennung)
Involved external institutions
Germany (DE)How to cite
APA:
Bhat, S., Georgescu, B., Mansoor, A., Zinnen, M., Sahu, P., Ghesu, F.C.,... Maier, A. (2028). Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR. (Unpublished, In review).
MLA:
Bhat, Sheethal, et al. Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR. Unpublished, In review. 2028.
BibTeX: Download