CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encoding
Chaudhary S, Bhat S, Maier A (2026)
Publication Language: English
Publication Status: Accepted
Publication Type: Conference contribution
Future Publication Type: Conference contribution
Publication year: 2026
Publisher: IEEE
Series: 2026 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD)
City/Town: In Print
Conference Proceedings Title: IEEE Symposium on Nuclear Science (NSS/MIC)
Event location: Granada
DOI: 10.48550/arXiv.2603.12514
Abstract
Accurate detection and localization of traumatic injuries in abdominal CT scans remains a critical challenge in emergency radiology, primarily due to severe scarcity of annotated medical data. This paper presents a label-efficient approach combining self-supervised pre-training with semi-supervised detection for 3D medical image analysis. We employ patch-based Masked Image Modeling (MIM) to pre-train a 3D U-Net encoder on 1,206 CT volumes without annotations, learning robust anatomical representations. The pretrained encoder enables two downstream clinical tasks: 3D injury detection using VDETR with Vertex Relative Position Encoding, and multi-label injury classification. For detection, semi-supervised learning with 2,000 unlabeled volumes and consistency regularization achieves 56.57% validation mAP@0.50 and 45.30% test mAP@0.50 with only 144 labeled training samples, representing a 115% improvement over supervised-only training. For classification, expanding to 2,244 labeled samples yields 94.07% test accuracy across seven injury categories using only a frozen encoder, demonstrating immediately transferable self-supervised features. Our results validate that self-supervised pre-training combined with semi-supervised learning effectively addresses label scarcity in medical imaging, enabling robust 3D object detection with limited annotations.
Authors with CRIS profile
How to cite
APA:
Chaudhary, S., Bhat, S., & Maier, A. (2026). CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encoding. In IEEE Symposium on Nuclear Science (NSS/MIC). Granada, ES: In Print: IEEE.
MLA:
Chaudhary, Shivam, Sheethal Bhat, and Andreas Maier. "CT-VDETR: Semi-supervised 3D Trauma Detection in Computed Tomography (CT) scans using Dense Vertex Relative Position Encoding." Proceedings of the 2026 IEEE NUCLEAR SCIENCE SYMPOSIUM, MEDICAL IMAGING CONFERENCE AND ROOM TEMPERATURE SEMICONDUCTOR DETECTOR CONFERENCE, Granada In Print: IEEE, 2026.
BibTeX: Download