A Learning Strategy for Contrast-agnostic MRI Segmentation

• URL: http://arxiv.org/abs/2003.01995v3
• Date: Thu, 8 Apr 2021 11:47:24 GMT
• Title: A Learning Strategy for Contrast-agnostic MRI Segmentation
• Authors: Benjamin Billot, Douglas Greve, Koen Van Leemput, Bruce Fischl, Juan Eugenio Iglesias, Adrian V. Dalca
• Abstract summary: We present a deep learning strategy that enables, for the first time, contrast-agnostic semantic segmentation of unpreprocessed brain MRI scans. Our proposed learning method, SynthSeg, generates synthetic sample images of widely varying contrasts on the fly during training. We evaluate our approach on four datasets comprising over 1,000 subjects and four types of MR contrast.
• Score: 8.264160978159634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a deep learning strategy that enables, for the first time, contrast-agnostic semantic segmentation of completely unpreprocessed brain MRI scans, without requiring additional training or fine-tuning for new modalities. Classical Bayesian methods address this segmentation problem with unsupervised intensity models, but require significant computational resources. In contrast, learning-based methods can be fast at test time, but are sensitive to the data available at training. Our proposed learning method, SynthSeg, leverages a set of training segmentations (no intensity images required) to generate synthetic sample images of widely varying contrasts on the fly during training. These samples are produced using the generative model of the classical Bayesian segmentation framework, with randomly sampled parameters for appearance, deformation, noise, and bias field. Because each mini-batch has a different synthetic contrast, the final network is not biased towards any MRI contrast. We comprehensively evaluate our approach on four datasets comprising over 1,000 subjects and four types of MR contrast. The results show that our approach successfully segments every contrast in the data, performing slightly better than classical Bayesian segmentation, and three orders of magnitude faster. Moreover, even within the same type of MRI contrast, our strategy generalizes significantly better across datasets, compared to training using real images. Finally, we find that synthesizing a broad range of contrasts, even if unrealistic, increases the generalization of the neural network. Our code and model are open source at https://github.com/BBillot/SynthSeg.

Related papers

• Maximizing domain generalization in fetal brain tissue segmentation: the role of synthetic data generation, intensity clustering and real image fine-tuning [1.1443262816483672]
  Recent approaches based on domain randomization, like SynthSeg, have shown a great potential for single source domain generalization. We show how to maximize the out-of-domain (OOD) generalization potential of SynthSeg-based methods in fetal brain MRI.
  arXiv  Detail & Related papers  (2024-11-11T10:17:44Z)
• Diffusion-based Data Augmentation for Nuclei Image Segmentation [68.28350341833526]
  We introduce the first diffusion-based augmentation method for nuclei segmentation. The idea is to synthesize a large number of labeled images to facilitate training the segmentation model. The experimental results show that by augmenting 10% labeled real dataset with synthetic samples, one can achieve comparable segmentation results.
  arXiv  Detail & Related papers  (2023-10-22T06:16:16Z)
• Better Generalization of White Matter Tract Segmentation to Arbitrary Datasets with Scaled Residual Bootstrap [1.30536490219656]
  White matter (WM) tract segmentation is a crucial step for brain connectivity studies. We propose a WM tract segmentation approach that improves the generalization with scaled residual bootstrap.
  arXiv  Detail & Related papers  (2023-09-25T09:31:34Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis [52.41439725865149]
  Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective synthesis model. We propose a Multi-scale Transformer Network (MT-Net) with edge-aware pre-training for cross-modality MR image synthesis.
  arXiv  Detail & Related papers  (2022-12-02T11:40:40Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• SynthStrip: Skull-Stripping for Any Brain Image [7.846209440615028]
  We introduce SynthStrip, a rapid, learning-based brain-extraction tool. By leveraging anatomical segmentations, SynthStrip generates a synthetic training dataset with anatomies, intensity distributions, and artifacts that far exceed the realistic range of medical images. We show substantial improvements in accuracy over popular skull-stripping baselines - all with a single trained model.
  arXiv  Detail & Related papers  (2022-03-18T14:08:20Z)
• Learning with Neighbor Consistency for Noisy Labels [69.83857578836769]
  We present a method for learning from noisy labels that leverages similarities between training examples in feature space. We evaluate our method on datasets evaluating both synthetic (CIFAR-10, CIFAR-100) and realistic (mini-WebVision, Clothing1M, mini-ImageNet-Red) noise.
  arXiv  Detail & Related papers  (2022-02-04T15:46:27Z)
• An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systems [73.48927855855219]
  Recent advances in deep learning have resulted in image compression algorithms that outperform JPEG and JPEG 2000 on the standard Kodak benchmark. In this paper, we perform the first large-scale comparison of recent state-of-the-art hybrid neural compression algorithms.
  arXiv  Detail & Related papers  (2022-01-27T19:47:51Z)
• SynthSeg: Domain Randomisation for Segmentation of Brain MRI Scans of any Contrast and Resolution [7.070890465817133]
  Convolutional neural networks (CNNs) have difficulties generalising to unseen target domains. We introduce SynthSeg, the first segmentation CNN to brain MRI scans of any contrast and resolution. We demonstrate SynthSeg on 5,500 scans of 6 modalities and 10 resolutions, where it exhibits unparalleled generalisation.
  arXiv  Detail & Related papers  (2021-07-20T15:22:16Z)
• SynthMorph: learning contrast-invariant registration without acquired images [8.0963891430422]
  We introduce a strategy for learning image registration without acquired imaging data. We show that this strategy enables robust and accurate registration of arbitrary MRI contrasts.
  arXiv  Detail & Related papers  (2020-04-21T20:29:39Z)

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.