Adversarial Deep Learning for Simultaneous Segmentation of Ventricular and White Matter Hyperintensities in Clinical MRI

TL;DR

This paper introduces a deep learning framework that simultaneously segments ventricles and white matter hyperintensities in clinical MRI, effectively differentiating normal from pathological hyperintensities with high accuracy and efficiency.

Contribution

The study presents a novel adversarial deep learning architecture that improves simultaneous segmentation and differentiation of brain structures in MRI, outperforming existing methods.

Findings

Achieved high Dice scores (up to 0.852) across all classes.

Outperformed baseline methods on local clinical data.

Reduced processing time to approximately 4 seconds per case.

Abstract

Purpose: Multiple sclerosis (MS) diagnosis requires accurate assessment of white matter hyperintensities (WMH) and ventricular changes on brain MRI. Current methods treat these structures independently, struggle to differentiate normal from pathological hyperintensities, and perform poorly on anisotropic clinical data. We present a deep learning framework that simultaneously segments ventricles and WMH while distinguishing normal periventricular hyperintensities from pathological MS lesions. Methods: We developed a 2D pix2pix architecture trained on FLAIR scans from 300 MS patients combined with the MSSEG2016 benchmark (15 patients). Five architectural variants were compared through systematic ablation using 5-fold cross-validation with patient-level stratification, progressively integrating adversarial training, attention-weighted discrimination, and adaptive hybrid loss. Performance was assessed against six established methods using Dice coefficient, Hausdorff distance, precision, and recall. Results: The final architecture (V5) achieved mean Dice 0.852+/-0.004 and HD95 4.87+/-0.13mm across all classes. Per-class performance: ventricles (Dice 0.907+/-0.002, HD95 3.00+/-0.51mm), abnormal WMH (Dice 0.825+/-0.009, HD95 4.51+/-0.32mm), normal WMH (Dice 0.677+/-0.007). V5 outperformed all baselines on local data for both ventricle and WMH segmentation. Ablation analysis confirmed adversarial training provided the largest single gain (+0.109 Dice). End-to-end processing required ~4 seconds per case-up to 36x faster than baseline methods. Conclusions: This systematically validated framework combines adversarial training, attention-weighted discrimination, and adaptive loss scheduling to achieve improved accuracy, clinically relevant lesion differentiation, and computational efficiency suitable for routine clinical workflows.