Deep infant brain segmentation from multi-contrast MRI

TL;DR

This paper introduces BabySeg, a deep learning framework for infant brain MRI segmentation that handles diverse protocols and improves accuracy and efficiency over existing methods.

Contribution

BabySeg employs domain randomization and flexible feature pooling to achieve robust, multi-protocol infant brain segmentation with a single model.

Findings

Achieves state-of-the-art segmentation accuracy across age groups.

Supports multiple MRI protocols and input types with a single model.

Operates faster than many existing segmentation tools.

Abstract

Segmentation of magnetic resonance images (MRI) facilitates analysis of human brain development by delineating anatomical structures. However, in infants and young children, accurate segmentation is challenging due to development and imaging constraints. Pediatric brain MRI is notoriously difficult to acquire, with inconsistent availability of imaging modalities, substantial non-head anatomy in the field of view, and frequent motion artifacts. This has led to specialized segmentation models that are often limited to specific image types or narrow age groups, or that are fragile for more variable images such as those acquired clinically. We address this method fragmentation with BabySeg, a deep learning brain segmentation framework for infants and young children that supports diverse MRI protocols, including repeat scans and image types unavailable during training. Our approach builds on recent domain randomization techniques, which synthesize training images far beyond realistic bounds to promote dataset shift invariance. We also describe a mechanism that enables models to flexibly pool and interact features from any number of input scans. We demonstrate state-of-the-art performance that matches or exceeds the accuracy of several existing methods for various age cohorts and input configurations using a single model, in a fraction of the runtime required by many existing tools.