Medical image segmentation with imperfect 3D bounding boxes

• URL: http://arxiv.org/abs/2108.03300v1
• Date: Fri, 6 Aug 2021 20:51:20 GMT
• Title: Medical image segmentation with imperfect 3D bounding boxes
• Authors: Ekaterina Redekop, Alexey Chernyavskiy
• Abstract summary: We focus on 3D medical images with their corresponding 3D bounding boxes which are considered as series of per-slice non-tight 2D bounding boxes. While current weakly-supervised approaches that use 2D bounding boxes as weak labels can be applied to medical image segmentation, we show that their success is limited in cases when the assumption about the tightness of the bounding boxes breaks. We propose a new bounding box correction framework which is trained on a small set of pixel-level annotations to improve the tightness of a larger set of non-tight bounding box annotations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The development of high quality medical image segmentation algorithms depends on the availability of large datasets with pixel-level labels. The challenges of collecting such datasets, especially in case of 3D volumes, motivate to develop approaches that can learn from other types of labels that are cheap to obtain, e.g. bounding boxes. We focus on 3D medical images with their corresponding 3D bounding boxes which are considered as series of per-slice non-tight 2D bounding boxes. While current weakly-supervised approaches that use 2D bounding boxes as weak labels can be applied to medical image segmentation, we show that their success is limited in cases when the assumption about the tightness of the bounding boxes breaks. We propose a new bounding box correction framework which is trained on a small set of pixel-level annotations to improve the tightness of a larger set of non-tight bounding box annotations. The effectiveness of our solution is demonstrated by evaluating a known weakly-supervised segmentation approach with and without the proposed bounding box correction algorithm. When the tightness is improved by our solution, the results of the weakly-supervised segmentation become much closer to those of the fully-supervised one.

Related papers

• Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection [38.15872244768199]
  Self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA) These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. We propose a novel pseudo label refinery framework to improve the reliability of pseudo boxes.
  arXiv  Detail & Related papers  (2024-04-30T09:20:35Z)
• 3D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projection [33.34240545722551]
  Vascular structure segmentation plays a crucial role in medical analysis and clinical applications. Existing weakly supervised methods have exhibited suboptimal performance when handling sparse vascular structure. Here, we employ maximum intensity projection (MIP) to decrease the dimensionality of 3D volume to 2D image for efficient annotation. We introduce a weakly-supervised network that fuses 2D-3D deep features via MIP to further improve segmentation performance.
  arXiv  Detail & Related papers  (2024-02-19T13:24:46Z)
• Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance [72.6809373191638]
  We propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Third, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data.
  arXiv  Detail & Related papers  (2023-12-12T18:57:25Z)
• 3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks [26.29122638813974]
  We propose a framework that can robustly learn from sparse annotation using the cross-teaching of both 3D and 2D networks. Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.
  arXiv  Detail & Related papers  (2023-07-30T15:26:17Z)
• Split, Merge, and Refine: Fitting Tight Bounding Boxes via Over-Segmentation and Iterative Search [15.29167642670379]
  We propose a novel framework for finding a set of tight bounding boxes of a 3D shape via over-segmentation and iterative merging and refinement. By thoughtful evaluation, we demonstrate full coverage, tightness, and an adequate number of bounding boxes of our method without requiring any training data or supervision.
  arXiv  Detail & Related papers  (2023-04-10T00:25:15Z)
• Weakly Supervised Image Segmentation Beyond Tight Bounding Box Annotations [5.000514512377416]
  This study investigates whether it is possible to maintain good segmentation performance when loose bounding boxes are used as supervision. The proposed polar transformation based MIL formulation works for both tight and loose bounding boxes. The results demonstrate that the proposed approach achieves state-of-the-art performance for bounding boxes at all precision levels.
  arXiv  Detail & Related papers  (2023-01-28T02:11:36Z)
• Exploring Active 3D Object Detection from a Generalization Perspective [58.597942380989245]
  Uncertainty-based active learning policies fail to balance the trade-off between point cloud informativeness and box-level annotation costs. We propose textscCrb, which hierarchically filters out the point clouds of redundant 3D bounding box labels. Experiments show that the proposed approach outperforms existing active learning strategies.
  arXiv  Detail & Related papers  (2023-01-23T02:43:03Z)
• FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection [81.79171905308827]
  We propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations. Our method consists of two stages: coarse 3D segmentation and 3D bounding box estimation. It is able to accurately detect objects in 3D space with only 2D bounding boxes and sparse point clouds.
  arXiv  Detail & Related papers  (2021-05-17T07:29:55Z)
• Unsupervised Object Detection with LiDAR Clues [70.73881791310495]
  We present the first practical method for unsupervised object detection with the aid of LiDAR clues. In our approach, candidate object segments based on 3D point clouds are firstly generated. Then, an iterative segment labeling process is conducted to assign segment labels and to train a segment labeling network. The labeling process is carefully designed so as to mitigate the issue of long-tailed and open-ended distribution.
  arXiv  Detail & Related papers  (2020-11-25T18:59:54Z)
• Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound [74.22397862400177]
  We propose a novel Frustum ultrasound based catheter segmentation method. The proposed method achieved the state-of-the-art performance with an efficiency of 0.25 second per volume.
  arXiv  Detail & Related papers  (2020-10-19T13:56:22Z)
• Dive Deeper Into Box for Object Detection [49.923586776690115]
  We propose a box reorganization method(DDBNet), which can dive deeper into the box for more accurate localization. Experimental results show that our method is effective which leads to state-of-the-art performance for object detection.
  arXiv  Detail & Related papers  (2020-07-15T07:49:05Z)

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.