Segmentation of MRI head anatomy using deep volumetric networks and multiple spatial priors

TL;DR

This paper introduces a novel deep volumetric network that integrates multiple spatial priors to improve MRI head anatomy segmentation, especially in cases with abnormalities like lesions.

Contribution

The study presents the Multiprior network, combining spatial, morphological, and contextual priors, enhancing segmentation accuracy over existing methods for abnormal brain anatomies.

Findings

Multiprior network outperforms existing segmentation tools like SPM, FSL, and DeepMedic.

Adding a tissue probability map (TPM) significantly boosts segmentation performance.

The approach generalizes well to clinical cases with disorders of consciousness.

Abstract

Purpose: Conventional automated segmentation of the head anatomy in MRI distinguishes different brain and non-brain tissues based on image intensities and prior tissue probability maps (TPM). This works well for normal head anatomies, but fails in the presence of unexpected lesions. Deep convolutional neural networks leverage instead spatial patterns and can learn to segment lesions, but often ignore prior probabilities. Approach: We add three sources of prior information to a three-dimensional convolutional network, namely, spatial priors with a TPM, morphological priors with conditional random fields, and spatial context with a wider field-of-view at lower resolution. We train and test these networks on 3D images of 43 stroke patients and 4 healthy individuals which have been manually segmented. Results: We demonstrate the benefits of each sources of prior information, and we show that the new architecture, which we call Multiprior network, improves the performance of existing segmentation software, such as SPM, FSL, and DeepMedic for abnormal anatomies. The relevance of the different priors was compared and the TPM was found to be most beneficial. The benefit of adding a TPM is generic in that it can boost the performance of established segmentation networks such as the DeepMedic and a UNet. We also provide an out-of-sample validation and clinical application of the approach on an additional 47 patients with disorders of consciousness. We make the code and trained networks freely available. Conclusions: Biomedical images follow imaging protocols that can be leveraged as prior information into deep convolutional neural networks to improve performance. The network segmentations match human manual corrections performed in 3D, and are comparable in performance to human segmentations obtained from scratch in 2D for abnormal brain anatomies.

Figures