Real-Time Automatic Fetal Brain Extraction in Fetal MRI by Deep Learning

Abstract

Brain segmentation is a fundamental first step in neuroimage analysis. In the case of fetal MRI, it is particularly challenging and important due to the arbitrary orientation of the fetus, organs that surround the fetal head, and intermittent fetal motion. Several promising methods have been proposed but are limited in their performance in challenging cases and in real-time segmentation. We aimed to develop a fully automatic segmentation method that independently segments sections of the fetal brain in 2D fetal MRI slices in real-time. To this end, we developed and evaluated a deep fully convolutional neural network based on 2D U-net and autocontext, and compared it to two alternative fast methods based on 1) a voxelwise fully convolutional network and 2) a method based on SIFT features, random forest and conditional random field. We trained the networks with manual brain masks on 250 stacks of training images, and tested on 17 stacks of normal fetal brain images as well as 18 stacks of extremely challenging cases based on extreme motion, noise, and severely abnormal brain shape. Experimental results show that our U-net approach outperformed the other methods and achieved average Dice metrics of 96.52% and 78.83% in the normal and challenging test sets, respectively. With an unprecedented performance and a test run time of about 1 second, our network can be used to segment the fetal brain in real-time while fetal MRI slices are being acquired. This can enable real-time motion tracking, motion detection, and 3D reconstruction of fetal brain MRI.

This work has been submitted to ISBI 2018

References in corpus (3)

• Fully Convolutional Networks for Semantic Segmentation
• Automatic segmentation of MR brain images with a convolutional neural network
• Auto-context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging

Cited by in corpus (17)

• CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection
• Deformable Slice-to-Volume Registration for Motion Correction in Fetal Body MRI
• Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slices
• AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI
• Rapid head-pose detection for automated slice prescription of fetal-brain MRI
• UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation
• Retrospective Motion Correction of MR Images using Prior-Assisted Deep Learning
• A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI
• Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency
• Multi-task learning for joint weakly-supervised segmentation and aortic arch anomaly classification in fetal cardiac MRI
• Real-time Deep Pose Estimation with Geodesic Loss for Image-to-Template Rigid Registration
• Longitudinal analysis of fetal MRI in patients with prenatal spina bifida repair
• Automatic brain tissue segmentation in fetal MRI using convolutional neural networks