CircleSnake: Instance Segmentation with Circle Representation

• URL: http://arxiv.org/abs/2211.01254v1
• Date: Wed, 2 Nov 2022 16:34:20 GMT
• Title: CircleSnake: Instance Segmentation with Circle Representation
• Authors: Ethan H. Nguyen, Haichun Yang, Zuhayr Asad, Ruining Deng, Agnes B. Fogo, and Yuankai Huo
• Abstract summary: We propose CircleSnake, a simple end-to-end circle contour deformation-based segmentation method for ball-shaped medical objects. Compared to the prevalent DeepSnake method, our contribution is three-fold. The proposed CircleSnake method is the first end-to-end circle representation deep segmentation pipeline method.
• Score: 4.009829991224921
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Circle representation has recently been introduced as a medical imaging optimized representation for more effective instance object detection on ball-shaped medical objects. With its superior performance on instance detection, it is appealing to extend the circle representation to instance medical object segmentation. In this work, we propose CircleSnake, a simple end-to-end circle contour deformation-based segmentation method for ball-shaped medical objects. Compared to the prevalent DeepSnake method, our contribution is three-fold: (1) We replace the complicated bounding box to octagon contour transformation with a computation-free and consistent bounding circle to circle contour adaption for segmenting ball-shaped medical objects; (2) Circle representation has fewer degrees of freedom (DoF=2) as compared with the octagon representation (DoF=8), thus yielding a more robust segmentation performance and better rotation consistency; (3) To the best of our knowledge, the proposed CircleSnake method is the first end-to-end circle representation deep segmentation pipeline method with consistent circle detection, circle contour proposal, and circular convolution. The key innovation is to integrate the circular graph convolution with circle detection into an end-to-end instance segmentation framework, enabled by the proposed simple and consistent circle contour representation. Glomeruli are used to evaluate the performance of the benchmarks. From the results, CircleSnake increases the average precision of glomerular detection from 0.559 to 0.614. The Dice score increased from 0.804 to 0.849. The code has been released: https://github.com/hrlblab/CircleSnake

Related papers

• Weighted Circle Fusion: Ensembling Circle Representation from Different Object Detection Results [9.540862304334969]
  We propose Weighted Circle Fusion (WCF), a simple approach for merging predictions from various circle detection models. Our method undergoes thorough evaluation on a proprietary dataset for glomerular detection in object detection within whole slide imaging (WSI) The findings reveal a performance gain of 5 %, respectively, compared to existing ensemble methods.
  arXiv  Detail & Related papers  (2024-06-27T21:34:51Z)
• AdaContour: Adaptive Contour Descriptor with Hierarchical Representation [52.381359663689004]
  Existing angle-based contour descriptors suffer from lossy representation for non-star shapes. AdaCon is able to represent shapes more accurately robustly than other descriptors.
  arXiv  Detail & Related papers  (2024-04-12T07:30:24Z)
• Circle Representation for Medical Instance Object Segmentation [6.4832235108711345]
  We introduce CircleSnake, a simple end-to-end segmentation approach that utilizes circle contour deformation for segmenting ball-shaped medical objects at the instance level. In practical applications, such as the detection of glomeruli, nuclei, and eosinophils in pathological images, CircleSnake has demonstrated superior performance and greater rotation invariance.
  arXiv  Detail & Related papers  (2024-03-18T06:25:41Z)
• CircleFormer: Circular Nuclei Detection in Whole Slide Images with Circle Queries and Attention [13.947162082687417]
  We present CircleFormer, a Transformer-based circular medical object detection with dynamic anchor circles. We evaluate our method in circular nuclei detection and segmentation on the public MoNuSeg dataset.
  arXiv  Detail & Related papers  (2023-08-30T17:01:01Z)
• CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame [60.24797081117877]
  We propose the CRIN, namely Centrifugal Rotation-Invariant Network. CRIN directly takes the coordinates of points as input and transforms local points into rotation-invariant representations. A continuous distribution for 3D rotations based on points is introduced.
  arXiv  Detail & Related papers  (2023-03-06T13:14:10Z)
• Recurrent Generic Contour-based Instance Segmentation with Progressive Learning [111.31166268300817]
  We propose a novel deep network architecture, i.e., PolySnake, for generic contour-based instance segmentation. Motivated by the classic Snake algorithm, the proposed PolySnake achieves superior and robust segmentation performance.
  arXiv  Detail & Related papers  (2023-01-21T05:34:29Z)
• CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection [62.41288479917261]
  We propose a novel feature learning model, referred to as CircleNet, to achieve feature adaptation by mimicking the process humans look at low resolution and occluded objects. Experiments on two pedestrian detection datasets, Caltech and CityPersons, show that CircleNet improves the performance of occluded and low-resolution pedestrians with significant margins.
  arXiv  Detail & Related papers  (2022-12-12T04:10:24Z)
• Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections [58.720142291102135]
  We propose a new iterative method which we term Iterative Next Boundary Detection (INBD) It intuitively models the natural growth direction, starting from the center of the shrub cross section and detecting the next ring boundary in each step. In our experiments, INBD shows superior performance to generic instance segmentation methods and is the only one with a built-in notion of chronological order.
  arXiv  Detail & Related papers  (2022-12-06T14:49:41Z)
• Circle Representation for Medical Object Detection [5.359910146589289]
  Box representation is efficacious but not necessarily optimized for biomedical objects. We propose a simple circle representation for medical object detection and introduce CircleNet. When detecting glomeruli and nuclei on pathological images, the proposed circle representation achieved superior detection performance.
  arXiv  Detail & Related papers  (2021-10-22T23:16:42Z)
• Deep Hough Voting for Robust Global Registration [52.40611370293272]
  We present an efficient framework for pairwise registration of real-world 3D scans, leveraging Hough voting in the 6D transformation parameter space. Our method outperforms state-of-the-art methods on 3DMatch and 3DLoMatch benchmarks while achieving comparable performance on KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-09-09T14:38:06Z)
• CircleNet: Anchor-free Detection with Circle Representation [10.081591705078678]
  CircleNet is a simple anchor-free detection method with circle representation for detection of the ball-shaped glomerulus. We evaluate CircleNet in the context of detection of glomerulus.
  arXiv  Detail & Related papers  (2020-06-03T18:31:51Z)

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.