Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slices

TL;DR

This paper introduces an uncertainty-guided interactive refinement framework for fetal brain MRI segmentation, combining a novel CNN with real-time uncertainty estimation and an interactive level set method to improve efficiency and accuracy.

Contribution

It presents a new CNN-based uncertainty estimation method and an interactive level set approach, enhancing fetal brain segmentation accuracy with 30% efficiency gains.

Findings

Uncertainty estimation correlates well with mis-segmentations.

The interactive level set method improves refinement efficiency.

The framework achieves around 30% efficiency improvement.

Abstract

Segmentation of the fetal brain from stacks of motion-corrupted fetal MRI slices is important for motion correction and high-resolution volume reconstruction. Although Convolutional Neural Networks (CNNs) have been widely used for automatic segmentation of the fetal brain, their results may still benefit from interactive refinement for challenging slices. To improve the efficiency of interactive refinement process, we propose an Uncertainty-Guided Interactive Refinement (UGIR) framework. We first propose a grouped convolution-based CNN to obtain multiple automatic segmentation predictions with uncertainty estimation in a single forward pass, then guide the user to provide interactions only in a subset of slices with the highest uncertainty. A novel interactive level set method is also proposed to obtain a refined result given the initial segmentation and user interactions. Experimental results show that: (1) our proposed CNN obtains uncertainty estimation in real time which correlates well with mis-segmentations, (2) the proposed interactive level set is effective and efficient for refinement, (3) UGIR obtains accurate refinement results with around 30% improvement of efficiency by using uncertainty to guide user interactions. Our code is available online.