A Learning Strategy for Contrast-agnostic MRI Segmentation

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.

arXiv comment19 pages, 5 figures

References in corpus (5)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Domain-adversarial neural networks to address the appearance variability of histopathology images
• A Lifelong Learning Approach to Brain MR Segmentation Across Scanners and Protocols
• Pulse Sequence Resilient Fast Brain Segmentation

Cited by in corpus (9)

• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets
• A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections
• Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
• Towards contrast-agnostic soft segmentation of the spinal cord
• NeXtQSM -- A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data
• Harmonization and the Worst Scanner Syndrome
• Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
• The role of MRI physics in brain segmentation CNNs: achieving acquisition invariance and instructive uncertainties