Dataset Information

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation.

ABSTRACT: White matter hyperintensities (WMHs) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI-based segmentation methods are often sensitive to acquisition protocols, scanners, noise-level, and image contrast, failing to generalize to other populations and out-of-distribution datasets. Given these concerns, we propose a novel Bayesian 3D convolutional neural network with a U-Net architecture that automatically segments WMH, provides uncertainty estimates of the segmentation output for quality control, and is robust to changes in acquisition protocols. We also provide a second model to differentiate deep and periventricular WMH. Four hundred thirty-two subjects were recruited to train the CNNs from four multisite imaging studies. A separate test set of 158 subjects was used for evaluation, including an unseen multisite study. We compared our model to two established state-of-the-art techniques (BIANCA and DeepMedic), highlighting its accuracy and efficiency. Our Bayesian 3D U-Net achieved the highest Dice similarity coefficient of 0.89 ± 0.08 and the lowest modified Hausdorff distance of 2.98 ± 4.40 mm. We further validated our models highlighting their robustness on "clinical adversarial cases" simulating data with low signal-to-noise ratio, low resolution, and different contrast (stemming from MRI sequences with different parameters). Our pipeline and models are available at: https://hypermapp3r.readthedocs.io.

SUBMITTER: Mojiri Forooshani P

PROVIDER: S-EPMC8996363 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation.

Mojiri Forooshani Parisa P Biparva Mahdi M Ntiri Emmanuel E EE Ramirez Joel J Boone Lyndon L Holmes Melissa F MF Adamo Sabrina S Gao Fuqiang F Ozzoude Miracle M Scott Christopher J M CJM Dowlatshahi Dar D Lawrence-Dewar Jane M JM Kwan Donna D Lang Anthony E AE Marcotte Karine K Leonard Carol C Rochon Elizabeth E Heyn Chris C Bartha Robert R Strother Stephen S Tardif Jean-Claude JC Symons Sean S Masellis Mario M Swartz Richard H RH Moody Alan A Black Sandra E SE Goubran Maged M

Human brain mapping 20220128 7

White matter hyperintensities (WMHs) are frequently observed on structural neuroimaging of elderly populations and are associated with cognitive decline and increased risk of dementia. Many existing WMH segmentation algorithms produce suboptimal results in populations with vascular lesions or brain atrophy, or require parameter tuning and are computationally expensive. Additionally, most algorithms do not generate a confidence estimate of segmentation quality, limiting their interpretation. MRI- ...[more]

PMID: 35088930

Similar Datasets

Project description:IntroductionWhite matter hyperintensities (WMHs) are frequently observed on magnetic resonance (MR) images in older adults, commonly appearing as areas of high signal intensity on fluid-attenuated inversion recovery (FLAIR) MR scans. Elevated WMH volumes are associated with a greater risk of dementia and stroke, even after accounting for vascular risk factors. Manual segmentation, while considered the ground truth, is both labor-intensive and time-consuming, limiting the generation of annotated WMH datasets. Un-annotated data are relatively available; however, the requirement of annotated data poses a challenge for developing supervised machine learning models.MethodsTo address this challenge, we implemented a multi-stage semi-supervised learning (M3SL) approach that first uses un-annotated data segmented by traditional processing methods ("bronze" and "silver" quality data) and then uses a smaller number of "gold"-standard annotations for model refinement. The M3SL approach enabled fine-tuning of the model weights with the gold-standard annotations. This approach was integrated into the training of a U-Net model for WMH segmentation. We used data from three scanner vendors (over more than five scanners) and from both cognitively normal (CN) adult and patients cohorts [with mild cognitive impairment and Alzheimer's disease (AD)].ResultsAn analysis of WMH segmentation performance across both scanner and clinical stage (CN, MCI, AD) factors was conducted. We compared our results to both conventional and transfer-learning deep learning methods and observed better generalization with M3SL across different datasets. We evaluated several metrics (F-measure, IoU, and Hausdorff distance) and found significant improvements with our method compared to conventional (p < 0.001) and transfer-learning (p < 0.001).DiscussionThese findings suggest that automated, non-machine learning, tools have a role in a multi-stage learning framework and can reduce the impact of limited annotated data and, thus, enhance model performance.

Dataset Information

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation.

Publications

Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets