EVENet: Evidence-based Ensemble Learning for Uncertainty-aware Brain Parcellation Using Diffusion MRI

2024-09-11

Computerized Medical Imaging and Graphics

AI Summary

To address insufficient uncertainty modeling in diffusion MRI (dMRI)-based brain tissue segmentation, this paper proposes EVENet—the first evidence-based deep learning network for single-pass, uncertainty-quantified segmentation. EVENet jointly leverages multi-parametric dMRI data and employs a five-branch parallel architecture integrated with Dempster–Shafer evidence theory to produce voxel-wise probabilistic outputs without Monte Carlo sampling. Anatomical plausibility is enhanced via FreeSurfer-derived structural priors. Evaluated across multi-center, multi-disease cohorts—including schizophrenia, bipolar disorder, and four other neuropsychiatric conditions—as well as cross-protocol dMRI data, EVENet achieves significant improvements in segmentation accuracy and lesion localization performance. The method enhances clinical interpretability through principled uncertainty estimation and demonstrates superior robustness to acquisition variability and pathological heterogeneity.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

In this study, we developed an Evidence-based Ensemble Neural Network, namely EVENet, for anatomical brain parcellation using diffusion MRI. The key innovation of EVENet is the design of an evidential deep learning framework to quantify predictive uncertainty at each voxel during a single inference. To do so, we design an evidence-based ensemble learning framework for uncertainty-aware parcellation to leverage the multiple dMRI parameters derived from diffusion MRI. Using EVENet, we obtained accurate parcellation and uncertainty estimates across different datasets from healthy and clinical populations and with different imaging acquisitions. The overall network includes five parallel subnetworks, where each is dedicated to learning the FreeSurfer parcellation for a certain diffusion MRI parameter. An evidence-based ensemble methodology is then proposed to fuse the individual outputs. We perform experimental evaluations on large-scale datasets from multiple imaging sources, including high-quality diffusion MRI data from healthy adults and clinically diffusion MRI data from participants with various brain diseases (schizophrenia, bipolar disorder, attention-deficit/hyperactivity disorder, Parkinson's disease, cerebral small vessel disease, and neurosurgical patients with brain tumors). Compared to several state-of-the-art methods, our experimental results demonstrate highly improved parcellation accuracy across the multiple testing datasets despite the differences in dMRI acquisition protocols and health conditions. Furthermore, thanks to the uncertainty estimation, our EVENet approach demonstrates a good ability to detect abnormal brain regions in patients with lesions, enhancing the interpretability and reliability of the segmentation results.

Problem

• Diffusion MRI
• Brain Region Segmentation
• Uncertainty Quantification

Innovation

• DDEvENet
• Diffusion MRI Segmentation
• Uncertainty Estimation