Context-aware virtual adversarial training for anatomically-plausible segmentation

• URL: http://arxiv.org/abs/2107.05532v2
• Date: Tue, 13 Jul 2021 13:36:51 GMT
• Title: Context-aware virtual adversarial training for anatomically-plausible segmentation
• Authors: Ping Wang and Jizong Peng and Marco Pedersoli and Yuanfeng Zhou and Caiming Zhang and Christian Desrosiers
• Abstract summary: We present a Context-aware Virtual Adversarial Training (CaVAT) method for generating anatomically plausible segmentation. We use adversarial training to generate examples violating the constraints, so the network can learn to avoid making such incorrect predictions. Experiments on two clinically-relevant datasets show our method to produce segmentations that are both accurate and anatomically-plausible in terms of region connectivity.
• Score: 24.81862697703223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions. To solve this problem, we present a Context-aware Virtual Adversarial Training (CaVAT) method for generating anatomically plausible segmentation. Unlike approaches focusing solely on accuracy, our method also considers complex topological constraints like connectivity which cannot be easily modeled in a differentiable loss function. We use adversarial training to generate examples violating the constraints, so the network can learn to avoid making such incorrect predictions on new examples, and employ the Reinforce algorithm to handle non-differentiable segmentation constraints. The proposed method offers a generic and efficient way to add any constraint on top of any segmentation network. Experiments on two clinically-relevant datasets show our method to produce segmentations that are both accurate and anatomically-plausible in terms of region connectivity.

Related papers

• DAM-Seg: Anatomically accurate cardiac segmentation using Dense Associative Networks [3.776159955137874]
  We propose a novel transformer-based architecture that leverages dense associative networks to learn and retain specific patterns inherent to cardiac inputs. Our approach restricts the network to a limited set of patterns. During forward propagation, a weighted sum of these patterns is used to enforce anatomical correctness in the output. Experimental results indicate that our model consistently outperforms baseline approaches across all metrics.
  arXiv  Detail & Related papers  (2025-02-21T01:15:10Z)
• SLoRD: Structural Low-Rank Descriptors for Shape Consistency in Vertebrae Segmentation [13.225110742269543]
  We propose a contour-based network for automatic and precise segmentation of vertebrae from CT images. Specifically, a contour-based network is proposed based on Structural Low-Rank Descriptors for shape consistency, termed SLoRD. For a more precise representation of contour descriptors, we adopt the spherical coordinate system and devise the spherical centroid.
  arXiv  Detail & Related papers  (2024-07-11T14:39:54Z)
• Topologically Faithful Multi-class Segmentation in Medical Images [43.6770098513581]
  We propose a general loss function for topologically faithful multi-class segmentation. We project the N-class segmentation problem to N single-class segmentation tasks. Our loss formulation significantly enhances topological correctness in cardiac, cell, artery-vein, and Circle of Willis segmentation.
  arXiv  Detail & Related papers  (2024-03-16T19:11:57Z)
• Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation [73.83178465971552]
  The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection. We propose optimization trajectory distillation, a unified approach to address the two technical challenges from a new perspective.
  arXiv  Detail & Related papers  (2023-07-27T08:58:05Z)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• A novel shape-based loss function for machine learning-based seminal organ segmentation in medical imaging [1.0312968200748116]
  Deep convolutional neural networks have exhibited promising performance in accurate and automatic seminal segmentation. A novel shape-based cost function is proposed which encourages/constrains the network to learn/capture the underlying shape features.
  arXiv  Detail & Related papers  (2022-03-07T12:26:30Z)
• Belief function-based semi-supervised learning for brain tumor segmentation [23.21410263735263]
  Deep learning makes it possible to detect and segment a lesion field using annotated data. However, obtaining precisely annotated data is very challenging in the medical domain. In this paper, we address the uncertain boundary problem by a new evidential neural network with an information fusion strategy.
  arXiv  Detail & Related papers  (2021-01-29T22:39:16Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)
• Contour Transformer Network for One-shot Segmentation of Anatomical Structures [26.599337546171732]
  We present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. On segmentation tasks of four different anatomies, we demonstrate that our one-shot learning method significantly outperforms non-learning-based methods. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved to surpass the fully supervised methods.
  arXiv  Detail & Related papers  (2020-12-02T19:42:18Z)
• Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images [51.893494939675314]
  We propose a novel weakly supervised segmentation framework based on partial points annotation. We show that our method can achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-10T15:41:29Z)
• Differentiable Causal Discovery from Interventional Data [141.41931444927184]
  We propose a theoretically-grounded method based on neural networks that can leverage interventional data. We show that our approach compares favorably to the state of the art in a variety of settings.
  arXiv  Detail & Related papers  (2020-07-03T15:19:17Z)

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.