Large-scale pre-training holds the promise to advance 3D medical object detection, a crucial component of accurate computer-aided diagnosis. Yet, it remains underexplored compared to segmentation, where pre-training has already demonstrated significant benefits. Existing pre-training approaches for 3D object detection rely on 2D medical data or natural image pre-training, failing to fully leverage 3D volumetric information. In this work, we present the first systematic study of how existing pre-training methods can be integrated into state-of-the-art detection architectures, covering both CNNs and Transformers. Our results show that pre-training consistently improves detection performance across various tasks and datasets. Notably, reconstruction-based self-supervised pre-training outperforms supervised pre-training, while contrastive pre-training provides no clear benefit for 3D medical object detection. Our code is publicly available at: https://github.com/MIC-DKFZ/nnDetection-finetuning.
@article{arxiv.2509.15947,
title = {The Missing Piece: A Case for Pre-Training in 3D Medical Object Detection},
author = {Katharina Eckstein and Constantin Ulrich and Michael Baumgartner and Jessica Kächele and Dimitrios Bounias and Tassilo Wald and Ralf Floca and Klaus H. Maier-Hein},
journal= {arXiv preprint arXiv:2509.15947},
year = {2025}
}