Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets

TL;DR

SynthSeg+ is a robust AI tool designed for accurate segmentation and analysis of diverse clinical brain MRI scans, enabling large-scale neuroimaging studies despite high variability and artifacts.

Contribution

It introduces SynthSeg+ for the first time, a comprehensive AI suite capable of handling heterogeneous clinical MRI datasets for segmentation and morphometry.

Findings

Accurately replicates atrophy patterns in large ageing dataset

Performs cortical parcellation and intracranial volume estimation

Detects faulty segmentations caused by low-quality scans

Abstract

Every year, millions of brain MRI scans are acquired in hospitals, which is a figure considerably larger than the size of any research dataset. Therefore, the ability to analyse such scans could transform neuroimaging research. Yet, their potential remains untapped, since no automated algorithm is robust enough to cope with the high variability in clinical acquisitions (MR contrasts, resolutions, orientations, artefacts, subject populations). Here we present SynthSeg+, an AI segmentation suite that enables, for the first time, robust analysis of heterogeneous clinical datasets. In addition to whole-brain segmentation, SynthSeg+ also performs cortical parcellation, intracranial volume estimation, and automated detection of faulty segmentations (mainly caused by scans of very low quality). We demonstrate SynthSeg+ in seven experiments, including an ageing study on 14,000 scans, where it accurately replicates atrophy patterns observed on data of much higher quality. SynthSeg+ is publicly released as a ready-to-use tool to unlock the potential of quantitative morphometry.