Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation
Ryu Tadokoro (Tohoku University),* Ryosuke Yamada (University of Tsukuba, National Institute of Advanced Industrial Science and Technology (AIST)), Kodai Nakashima (CyberAgent, Univ. of Tsukuba, AIST), Ryo Nakamura (Fukuoka University, National Institute of Advanced Industrial Science and Technology (AIST)), Hirokatsu Kataoka (National Institute of Advanced Industrial Science and Technology (AIST))
The 34th British Machine Vision Conference
Abstract
The construction of 3D medical image datasets presents several issues, including requiring significant financial costs in data collection and specialized expertise for annotation, as well as strict privacy concerns for patient confidentiality compared to natural image datasets. Therefore, it has become a pressing issue in 3D medical image segmentation to enable data-efficient learning with limited 3D medical data and supervision. A promising approach is pre-training, but improving its performance in 3D medical image segmentation is difficult due to the small size of existing 3D medical image datasets. We thus present the Primitive Geometry Segment Pre-training (PrimGeoSeg) method to enable the learning of 3D semantic features by pre-training segmentation tasks using only primitive geometric objects for 3D medical image segmentation. PrimGeoSeg performs more accurate and efficient 3D medical image segmentation without manual data collection and annotation. Further, experimental results show that PrimGeoSeg on SwinUNETR improves performance over learning from scratch on BTCV, MSD (Task06), and BraTS datasets by 3.7%, 4.4%, and 0.3%, respectively. Remarkably, the performance was equal to or better than state-of-the-art self-supervised learning despite the equal number of pre-training data. From experimental results, we conclude that effective pre-training can be achieved by looking at primitive geometric objects only. Code and dataset are available at https://github.com/SUPER-TADORY/PrimGeoSeg.Video
Citation
@inproceedings{Tadokoro_2023_BMVC,
author = {Ryu Tadokoro and Ryosuke Yamada and Kodai Nakashima and Ryo Nakamura and Hirokatsu Kataoka},
title = {Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0152.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by