Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI

• URL: http://arxiv.org/abs/2011.07592v1
• Date: Sun, 15 Nov 2020 17:50:23 GMT
• Title: Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI
• Authors: Peter M. Full, Fabian Isensee, Paul F. J\"ager, and Klaus Maier-Hein
• Abstract summary: We study challenges and opportunities of domain transfer across images from multiple clinical centres and scanner vendors. In this work, we build upon a fixed U-Net architecture configured by the nnU-net framework to investigate various data augmentation techniques and batch normalization layers.
• Score: 0.8858288982748155
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cardiac magnetic resonance imaging (cMRI) is an integral part of diagnosis in many heart related diseases. Recently, deep neural networks have demonstrated successful automatic segmentation, thus alleviating the burden of time-consuming manual contouring of cardiac structures. Moreover, frameworks such as nnU-Net provide entirely automatic model configuration to unseen datasets enabling out-of-the-box application even by non-experts. However, current studies commonly neglect the clinically realistic scenario, in which a trained network is applied to data from a different domain such as deviating scanners or imaging protocols. This potentially leads to unexpected performance drops of deep learning models in real life applications. In this work, we systematically study challenges and opportunities of domain transfer across images from multiple clinical centres and scanner vendors. In order to maintain out-of-the-box usability, we build upon a fixed U-Net architecture configured by the nnU-net framework to investigate various data augmentation techniques and batch normalization layers as an easy-to-customize pipeline component and provide general guidelines on how to improve domain generalizability abilities in existing deep learning methods. Our proposed method ranked first at the Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge (M&Ms).

Related papers

• Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention [1.1155836879100416]
  We propose a Modality-agnostic Domain Generalizable Network (MADGNet) for medical image segmentation. MFMSA block refines the process of spatial feature extraction, particularly in capturing boundary features. E-SDM mitigates information loss in multi-task learning with deep supervision.
  arXiv  Detail & Related papers  (2024-05-10T07:34:36Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation [62.49837463676111]
  We propose a novel scheme of episodic training with task augmentation on medical imaging classification. Motivated by the limited number of source domains in real-world medical deployment, we consider the unique task-level overfitting.
  arXiv  Detail & Related papers  (2021-06-13T03:56:59Z)
• Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration [12.861503169117208]
  Multimodal image registration has many applications in diagnostic medical imaging and image-guided interventions. The ability to register peri-procedurally acquired diagnostic images into the intraprocedural environment can potentially improve the intra-procedural tumor targeting. We propose an anatomy-preserving domain adaptation to segmentation network (APA2Seg-Net) for learning segmentation without target modality ground truth.
  arXiv  Detail & Related papers  (2021-04-14T18:07:03Z)
• Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation [2.672151045393935]
  The study of the retinal microcirculation is a key issue in the analysis of many ocular and systemic diseases, like hypertension or diabetes. FCNs usually represent the most successful approach to image segmentation. In this work, we present multimodal transfer learning-based approaches for retinal vascular segmentation.
  arXiv  Detail & Related papers  (2020-12-18T10:38:35Z)
• 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)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)
• Domain-Adversarial Learning for Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac MR Image Segmentation [3.4551186283197883]
  Domain-adversarial learning is used to train a domain-invariant 2D U-Net using labelled and unlabelled data. This approach is evaluated on both seen and unseen domains from the M&Ms challenge dataset.
  arXiv  Detail & Related papers  (2020-08-26T19:40:55Z)
• MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data [75.73881040581767]
  We propose a novel multi-site network (MS-Net) for improving prostate segmentation by learning robust representations. Our MS-Net improves the performance across all datasets consistently, and outperforms state-of-the-art methods for multi-site learning.
  arXiv  Detail & Related papers  (2020-02-09T14:11:50Z)
• Unpaired Multi-modal Segmentation via Knowledge Distillation [77.39798870702174]
  We propose a novel learning scheme for unpaired cross-modality image segmentation. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI. We have extensively validated our approach on two multi-class segmentation problems.
  arXiv  Detail & Related papers  (2020-01-06T20:03:17Z)

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.