paper-with-me

홈 › Papers

Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation

2024-01-08 · Ryu Tadokoro, Ryosuke Yamada, Kodai Nakashima, Ryo Nakamura, Hirokatsu Kataoka

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.

📄 PDF Abstract BibTeX arXiv:2401.03665

Code (1)

super-tadory/primgeoseg 공식 구현 pytorch

Tasks

Image SegmentationMedical Image SegmentationSegmentationSelf-Supervised LearningSemantic Segmentation

Similar Papers 제목 키워드 기반

Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses

2020-12-17 · CVPR 2021 1 · Yiming Qian, Hao Zhang, Yasutaka Furukawa

This paper presents Roof-GAN, a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships. Given the number of primitives, …

Generative Adversarial Network

Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction

2026-07-06 · Gregor Kobsik, Tim Elsner, Leif Kobbelt arxiv

Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding. Generative image models trained at scale have recently emerged as generalist visual learners…

Scene Understanding

PrimitiveNet: Primitive Instance Segmentation With Local Primitive Embedding Under Adversarial Metric

2021-01-01 · ICCV 2021 10 · Jingwei Huang, Yanfeng Zhang, Mingwei Sun

We present PrimitiveNet, a novel approach for high-resolution primitive instance segmentation from point clouds on a large scale. Our key idea is to transform the global segmentation problem into easier local tasks. …

Instance SegmentationSegmentationSemantic Segmentation

M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization

2023-07-17 · Che Liu, Sibo Cheng, Chen Chen, Mengyun Qiao 외

Medical vision-language models enable co-learning and integrating features from medical imaging and clinical text. However, these models are not easy to train and the latent representation space can be complex. Here we p…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+3

Plane Geometry Diagram Parsing

2022-05-19 · Ming-Liang Zhang, Fei Yin, Yi-Han Hao, Cheng-Lin Liu

Geometry diagram parsing plays a key role in geometry problem solving, wherein the primitive extraction and relation parsing remain challenging due to the complex layout and between-primitive relationship. In this paper,…

Geometry Problem SolvingGraph Neural NetworkInstance SegmentationMathematical Question Answering+3