Style transfer generative adversarial networks to harmonize multisite MRI to a single reference image to avoid overcorrection.

Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for high-powered brain imaging analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing site-related image variation. However, most statistical approaches may over-correct for technical, scanning-related, variation as they cannot distinguish between confounded image-acquisition based variability and site-related population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisition-based variability. To overcome this limitation, we consider site-related magnetic resonance (MR) imaging harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori. We trained our model using data from five large-scale multisite datasets with varied demographics. Results demonstrated that our style-encoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brain-age estimates, and case-control effect sizes before and after the harmonization. We showed that our harmonization removed the site-related variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising tool for ongoing collaborative studies. Source code is released in USC-IGC/style_transfer_harmonization (github.com).

The Genetic Architecture of the Human Corpus Callosum and its Subregions.

The corpus callosum (CC) is the largest set of white matter fibers connecting the two hemispheres of the brain. In humans, it is essential for coordinating sensorimotor responses, performing associative/executive functions, and representing information in multiple dimensions. Understanding which genetic variants underpin corpus callosum morphometry, and their shared influence on cortical structure and susceptibility to neuropsychiatric disorders, can provide molecular insights into the CC's role in mediating cortical development and its contribution to neuropsychiatric disease. To characterize the morphometry of the midsagittal corpus callosum, we developed a publicly available artificial intelligence based tool to extract, parcellate, and calculate its total and regional area and thickness. Using the UK Biobank (UKB) and the Adolescent Brain Cognitive Development study (ABCD), we extracted measures of midsagittal corpus callosum morphometry and performed a genome-wide association study (GWAS) meta-analysis of European participants (combined N = 46,685). We then examined evidence for generalization to the non-European participants of the UKB and ABCD cohorts (combined N = 7,040). Post-GWAS analyses implicate prenatal intracellular organization and cell growth patterns, and high heritability in regions of open chromatin, suggesting transcriptional activity regulation in early development. Results suggest programmed cell death mediated by the immune system drives the thinning of the posterior body and isthmus. Global and local genetic overlap, along with causal genetic liability, between the corpus callosum, cerebral cortex, and neuropsychiatric disorders such as attention-deficit/hyperactivity and bipolar disorders were identified. These results provide insight into variability of corpus callosum development, its genetic influence on the cerebral cortex, and biological mechanisms related to neuropsychiatric dysfunction.

The Influence of Brain MRI Defacing Algorithms on Brain-Age Predictions via 3D Convolutional Neural Networks.

In brain imaging research, it is becoming standard practice to remove the face from the individual's 3D structural MRI scan to ensure data privacy standards are met. Face removal - or 'defacing' - is being advocated for large, multi-site studies where data is transferred across geographically diverse sites. Several methods have been developed to limit the loss of important brain data by accurately and precisely removing non-brain facial tissue. At the same time, deep learning methods such as convolutional neural networks (CNNs) are increasingly being used in medical imaging research for diagnostic classification and prognosis in neurological diseases. These neural networks train predictive models based on patterns in large numbers of images. Because of this, defacing scans could remove informative data. Here, we evaluated 4 popular defacing methods to identify the effects of defacing on 'brain age' prediction - a common benchmarking task of predicting a subject's chronological age from their 3D T1-weighted brain MRI. We compared brain-age calculations using defaced MRIs to those that were directly brain extracted, and those with both brain and face. Significant differences were present when comparing average per-subject error rates between algorithms in both the defaced brain data and the extracted facial tissue. Results also indicated brain age accuracy depends on defacing and the choice of algorithm. In a secondary analysis, we also examined how well comparable CNNs could predict chronological age from the facial region only (the extracted portion of the defaced image), as well as visualize areas of importance in facial tissue for predictive tasks using CNNs. We obtained better performance in age prediction when using the extracted face portion alone than images of the brain, suggesting the need for caution when defacing methods are used in medical image analysis.

The Influence of Brain MRI Defacing Algorithms on Brain-Age Predictions via 3D Convolutional Neural Networks.

In brain imaging research, it is becoming standard practice to remove the face from the individual's 3D structural MRI scan to ensure data privacy standards are met. Face removal - or 'defacing' - is being advocated for large, multi-site studies where data is transferred across geographically diverse sites. Several methods have been developed to limit the loss of important brain data by accurately and precisely removing non-brain facial tissue. At the same time, deep learning methods such as convolutional neural networks (CNNs) are increasingly being used in medical imaging research for diagnostic classification and prognosis in neurological diseases. These neural networks train predictive models based on patterns in large numbers of images. Because of this, defacing scans could remove informative data. Here, we evaluated 4 popular defacing methods to identify the effects of defacing on 'brain age' prediction - a common benchmarking task of predicting a subject's chronological age from their 3D T1-weighted brain MRI. We compared brain-age calculations using defaced MRIs to those that were directly brain extracted, and those with both brain and face. Significant differences were present when comparing average per-subject error rates between algorithms in both the defaced brain data and the extracted facial tissue. Results also indicated brain age accuracy depends on defacing and the choice of algorithm. In a secondary analysis, we also examined how well comparable CNNs could predict chronological age from the facial region only (the extracted portion of the defaced image), as well as visualize areas of importance in facial tissue for predictive tasks using CNNs. We obtained better performance in age prediction when using the extracted face portion alone than images of the brain, suggesting the need for caution when defacing methods are used in medical image analysis.

A Comprehensive Corpus Callosum Segmentation Tool for Detecting Callosal Abnormalities and Genetic Associations from Multi Contrast MRIs.

Structural alterations of the midsagittal corpus callosum (midCC) have been associated with a wide range of brain disorders. The midCC is visible on most MRI contrasts and in many acquisitions with a limited field-of-view. Here, we present an automated tool for segmenting and assessing the shape of the midCC from T1w, T2w, and FLAIR images. We train a UNet on images from multiple public datasets to obtain midCC segmentations. A quality control algorithm is also built-in, trained on the midCC shape features. We calculate intraclass correlations (ICC) and average Dice scores in a test-retest dataset to assess segmentation reliability. We test our segmentation on poor quality and partial brain scans. We highlight the biological significance of our extracted features using data from over 40,000 individuals from the UK Biobank; we classify clinically defined shape abnormalities and perform genetic analyses.

A Comprehensive Corpus Callosum Segmentation Tool for Detecting Callosal Abnormalities and Genetic Associations from Multi Contrast MRIs.

Structural alterations of the midsagittal corpus callosum (midCC) have been associated with a wide range of brain disorders. The midCC is visible on most MRI contrasts and in many acquisitions with a limited field-of-view. Here, we present an automated tool for segmenting and assessing the shape of the midCC from T1w, T2w, and FLAIR images. We train a UNet on images from multiple public datasets to obtain midCC segmentations. A quality control algorithm is also built-in, trained on the midCC shape features. We calculate intraclass correlations (ICC) and average Dice scores in a test-retest dataset to assess segmentation reliability. We test our segmentation on poor quality and partial brain scans. We highlight the biological significance of our extracted features using data from over 40,000 individuals from the UK Biobank; we classify clinically defined shape abnormalities and perform genetic analyses.

REGION SPECIFIC AUTOMATIC QUALITY ASSURANCE FOR MRI-DERIVED CORTICAL SEGMENTATIONS.

Quality control (QC) is a vital step for all scientific data analyses and is critically important in the biomedical sciences. Image segmentation is a common task in medical image analysis, and automated tools to segment many regions from human brain MRIs are now well established. However, these methods do not always give anatomically correct labels. Traditional methods for QC tend to reject statistical outliers, which may not necessarily be inaccurate. Here, we make use of a large database of over 12,000 brain images that contain 68 parcellations of the human cortex, each of which was assessed for anatomical accuracy by a human rater. We trained three machine learning models to determine if a region was anatomically accurate (as 'pass', or 'fail') and tested the performance on an independent dataset. We found good performance for the majority of labeled regions. This work will facilitate more anatomically accurate large-scale multi-site research.

Predicting Progression from Mild Cognitive Impairment to Alzheimer's Disease using MRI-based Cortical Features and a Two-State Markov Model.

Magnetic resonance imaging (MRI) has a potential for early diagnosis of individuals at risk for developing Alzheimer's disease (AD). Cognitive performance in healthy elderly people and in those with mild cognitive impairment (MCI) has been associated with measures of cortical gyrification [1] and thickness (CT) [2], yet the extent to which sulcal measures can help to predict AD conversion above and beyond CT measures is not known. Here, we analyzed 721 participants with MCI from phases 1 and 2 of the Alzheimer's Disease Neuroimaging Initiative, applying a two-state Markov model to study the conversion from MCI to AD condition. Our preliminary results suggest that MRI-based cortical features, including sulcal morphometry, may help to predict conversion from MCI to AD.