Exploring Cycle Consistency Learning in Interactive Volume Segmentation

• URL: http://arxiv.org/abs/2303.06493v2
• Date: Sat, 9 Mar 2024 17:02:28 GMT
• Title: Exploring Cycle Consistency Learning in Interactive Volume Segmentation
• Authors: Qin Liu, Meng Zheng, Benjamin Planche, Zhongpai Gao, Terrence Chen, Marc Niethammer, and Ziyan Wu
• Abstract summary: We interactively approach medical volume segmentation via two decoupled modules: interaction-to-segmentation and segmentation propagation. We propose a simple yet effective cycle consistency loss that regularizes an intermediate segmentation by referencing the accurate segmentation in the starting slice. With cycle consistency training, the propagation network is better regularized than in standard forward-only training approaches.
• Score: 39.000842538436714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic medical volume segmentation often lacks clinical accuracy, necessitating further refinement. In this work, we interactively approach medical volume segmentation via two decoupled modules: interaction-to-segmentation and segmentation propagation. Given a medical volume, a user first segments a slice (or several slices) via the interaction module and then propagates the segmentation(s) to the remaining slices. The user may repeat this process multiple times until a sufficiently high volume segmentation quality is achieved. However, due to the lack of human correction during propagation, segmentation errors are prone to accumulate in the intermediate slices and may lead to sub-optimal performance. To alleviate this issue, we propose a simple yet effective cycle consistency loss that regularizes an intermediate segmentation by referencing the accurate segmentation in the starting slice. To this end, we introduce a backward segmentation path that propagates the intermediate segmentation back to the starting slice using the same propagation network. With cycle consistency training, the propagation network is better regularized than in standard forward-only training approaches. Evaluation results on challenging AbdomenCT-1K and OAI-ZIB datasets demonstrate the effectiveness of our method.

Related papers

• Meta-Decomposition: Dynamic Segmentation Approach Selection in IoT-based Activity Recognition [6.887244952811574]
  Internet of Things (IoT) devices generate heterogeneous data over time. Many IoT applications, including IoT-based activity recognition, aim to address the limitations of individual events and streamline the process. However, this step introduces at least two families of uncontrollable biases. We propose to redefine the segmentation problem as a special case of a decomposition problem, including three key components: a decomposer, resolutions, and a composer.
  arXiv  Detail & Related papers  (2024-04-17T20:50:28Z)
• Unsupervised Segmentation of Fetal Brain MRI using Deep Learning Cascaded Registration [2.494736313545503]
  Traditional deep learning-based automatic segmentation requires extensive training data with ground-truth labels. We propose a novel method based on multi-atlas segmentation, that accurately segments multiple tissues without relying on labeled data for training. Our method employs a cascaded deep learning network for 3D image registration, which computes small, incremental deformations to the moving image to align it precisely with the fixed image.
  arXiv  Detail & Related papers  (2023-07-07T13:17:12Z)
• Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation [84.58210297703714]
  We propose a self-supervised correction learning paradigm for semi-supervised biomedical image segmentation. We design a dual-task network, including a shared encoder and two independent decoders for segmentation and lesion region inpainting. Experiments on three medical image segmentation datasets for different tasks demonstrate the outstanding performance of our method.
  arXiv  Detail & Related papers  (2023-01-12T08:19:46Z)
• Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images [0.0]
  Medical image segmentation often requires segmenting multiple elliptical objects on a single image. In this paper, we present a general approach to improving the semantic segmentation performance of neural networks. We show that our approach improves robustness and pixel-level recall while achieving segmentation in line with the state of the art.
  arXiv  Detail & Related papers  (2022-06-21T12:18:02Z)
• Interactive Segmentation for COVID-19 Infection Quantification on Longitudinal CT scans [40.721386089781895]
  Consistent segmentation of COVID-19 patient's CT scans across multiple time points is essential to assess disease progression and response to therapy accurately. Existing automatic and interactive segmentation models for medical images only use data from a single time point (static) We propose a new single network model for interactive segmentation that fully utilizes all available past information to refine the segmentation of follow-up scans.
  arXiv  Detail & Related papers  (2021-10-03T08:06:38Z)
• UCP-Net: Unstructured Contour Points for Instance Segmentation [2.105564340986074]
  We propose a novel approach to interactive segmentation based on unconstrained contour clicks for initial segmentation and segmentation refinement. Our method is class-agnostic and produces accurate segmentation masks (IoU > 85%) for a lower number of user interactions than state-of-the-art methods on popular segmentation datasets.
  arXiv  Detail & Related papers  (2021-09-15T22:03:37Z)
• Learning from Partially Overlapping Labels: Image Segmentation under Annotation Shift [68.6874404805223]
  We propose several strategies for learning from partially overlapping labels in the context of abdominal organ segmentation. We find that combining a semi-supervised approach with an adaptive cross entropy loss can successfully exploit heterogeneously annotated data.
  arXiv  Detail & Related papers  (2021-07-13T09:22:24Z)
• A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation [74.8791451327354]
  We propose a simple yet effective semi-supervised learning framework for semantic segmentation. A set of simple design and training techniques can collectively improve the performance of semi-supervised semantic segmentation significantly. Our method achieves state-of-the-art results in the semi-supervised settings on the Cityscapes and Pascal VOC datasets.
  arXiv  Detail & Related papers  (2021-04-15T06:01:39Z)
• DenoiSeg: Joint Denoising and Segmentation [75.91760529986958]
  We propose DenoiSeg, a new method that can be trained end-to-end on only a few annotated ground truth segmentations. We achieve this by extending Noise2Void, a self-supervised denoising scheme that can be trained on noisy images alone, to also predict dense 3-class segmentations.
  arXiv  Detail & Related papers  (2020-05-06T17:42:54Z)
• LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation [52.2074595581139]
  We introduce a one-shot segmentation method to alleviate the burden of manual annotation for medical images. The main idea is to treat one-shot segmentation as a classical atlas-based segmentation problem, where voxel-wise correspondence from the atlas to the unlabelled data is learned. We demonstrate the superiority of our method over both deep learning-based one-shot segmentation methods and a classical multi-atlas segmentation method via thorough experiments.
  arXiv  Detail & Related papers  (2020-03-16T08:36:17Z)

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.