Universal Segmentation of 33 Anatomies

• URL: http://arxiv.org/abs/2203.02098v1
• Date: Fri, 4 Mar 2022 02:29:54 GMT
• Title: Universal Segmentation of 33 Anatomies
• Authors: Pengbo Liu, Yang Deng, Ce Wang, Yuan Hui, Qian Li, Jun Li, Shiwei Luo, Mengke Sun, Quan Quan, Shuxin Yang, You Hao, Honghu Xiao, Chunpeng Zhao, Xinbao Wu, and S. Kevin Zhou
• Abstract summary: We present an approach for learning a single model that universally segments 33 anatomical structures. We learn such a model from a union of multiple datasets, with each dataset containing the images that are partially labeled. We evaluate our model on multiple open-source datasets, proving that our model has a good generalization performance.
• Score: 19.194539991903593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the paper, we present an approach for learning a single model that universally segments 33 anatomical structures, including vertebrae, pelvic bones, and abdominal organs. Our model building has to address the following challenges. Firstly, while it is ideal to learn such a model from a large-scale, fully-annotated dataset, it is practically hard to curate such a dataset. Thus, we resort to learn from a union of multiple datasets, with each dataset containing the images that are partially labeled. Secondly, along the line of partial labelling, we contribute an open-source, large-scale vertebra segmentation dataset for the benefit of spine analysis community, CTSpine1K, boasting over 1,000 3D volumes and over 11K annotated vertebrae. Thirdly, in a 3D medical image segmentation task, due to the limitation of GPU memory, we always train a model using cropped patches as inputs instead a whole 3D volume, which limits the amount of contextual information to be learned. To this, we propose a cross-patch transformer module to fuse more information in adjacent patches, which enlarges the aggregated receptive field for improved segmentation performance. This is especially important for segmenting, say, the elongated spine. Based on 7 partially labeled datasets that collectively contain about 2,800 3D volumes, we successfully learn such a universal model. Finally, we evaluate the universal model on multiple open-source datasets, proving that our model has a good generalization performance and can potentially serve as a solid foundation for downstream tasks.

Related papers

• ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [104.34751911174196]
  We build a large-scale dataset of 3DGS using ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories. We introduce textbftextitGaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
  arXiv  Detail & Related papers  (2024-08-20T14:49:14Z)
• Label-Efficient 3D Brain Segmentation via Complementary 2D Diffusion Models with Orthogonal Views [10.944692719150071]
  We propose a novel 3D brain segmentation approach using complementary 2D diffusion models. Our goal is to achieve reliable segmentation quality without requiring complete labels for each individual subject.
  arXiv  Detail & Related papers  (2024-07-17T06:14:53Z)
• One model to use them all: Training a segmentation model with complementary datasets [38.73145509617609]
  We propose a method to combine partially annotated datasets, which provide complementary annotations, into one model. Our approach successfully combines 6 classes into one model, increasing the overall Dice Score by 4.4%. By including information on multiple classes, we were able to reduce confusion between stomach and colon by 24%.
  arXiv  Detail & Related papers  (2024-02-29T16:46:49Z)
• One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts [62.55349777609194]
  We aim to build up a model that can Segment Anything in radiology scans, driven by Text prompts, termed as SAT. We build up the largest and most comprehensive segmentation dataset for training, by collecting over 22K 3D medical image scans. We have trained SAT-Nano (110M parameters) and SAT-Pro (447M parameters) demonstrating comparable performance to 72 specialist nnU-Nets trained on each dataset/subsets.
  arXiv  Detail & Related papers  (2023-12-28T18:16:00Z)
• SegViz: A Federated Learning Framework for Medical Image Segmentation from Distributed Datasets with Different and Incomplete Annotations [3.6704226968275258]
  We developed SegViz, a learning framework for aggregating knowledge from distributed medical image segmentation datasets. SegViz was trained to build a model capable of segmenting both liver and spleen aggregating knowledge from both these nodes. Our results demonstrate SegViz as an essential first step towards training clinically translatable multi-task segmentation models.
  arXiv  Detail & Related papers  (2023-01-17T18:36:57Z)
• Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats [80.12253291709673]
  We propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model.
  arXiv  Detail & Related papers  (2022-12-29T22:22:49Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU [87.48110331544885]
  We propose a novel training methodology to train and scale the existing semantic segmentation models. We demonstrate a clear benefit of our approach on a dataset with 1284 classes, bootstrapped from LVIS and COCO annotations, with three times better mIoU than the DeeplabV3+ model.
  arXiv  Detail & Related papers  (2020-12-14T13:12:38Z)
• Universal Medical Image Segmentation using 3D Fabric Image Representation Encoding Networks [8.691611603448152]
  This work proposes one such network, Fabric Image Representation. Network (FIRENet), for simultaneous 3D multi-dataset segmentation. In this study, FIRENet was first applied to 3D universal bone segmentation involving multiple datasets of the human knee, shoulder and hip joints.
  arXiv  Detail & Related papers  (2020-06-28T11:35:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.