PARE: A framework for removal of confounding effects from any distance-based dimension reduction method.

Dimension reduction tools preserving similarity and graph structure such as t-SNE and UMAP can capture complex biological patterns in high-dimensional data. However, these tools typically are not designed to separate effects of interest from unwanted effects due to confounders. We introduce the partial embedding (PARE) framework, which enables removal of confounders from any distance-based dimension reduction method. We then develop partial t-SNE and partial UMAP and apply these methods to genomic and neuroimaging data. For lower-dimensional visualization, our results show that the PARE framework can remove batch effects in single-cell sequencing data as well as separate clinical and technical variability in neuroimaging measures. We demonstrate that the PARE framework extends dimension reduction methods to highlight biological patterns of interest while effectively removing confounding effects.

Synaptic Protein Loss in Extracellular Vesicles Reflects Brain and Retinal Atrophy in People With Multiple Sclerosis.

OBJECTIVES: To assess whether the rate of change in synaptic proteins isolated from neuronally enriched extracellular vesicles (NEVs) is associated with brain and retinal atrophy in people with multiple sclerosis (MS). METHODS: People with MS were followed with serial blood draws, MRI (MRI), and optical coherence tomography (OCT) scans. NEVs were immunocaptured from plasma, and synaptopodin and synaptophysin proteins were measured using ELISA. Subject-specific rates of change in synaptic proteins, as well as brain and retinal atrophy, were determined and correlated. RESULTS: A total of 50 people with MS were included, 46 of whom had MRI and 45 had OCT serially. The rate of change in NEV synaptopodin was associated with whole brain (rho = 0.31; p = 0.04), cortical gray matter (rho = 0.34; p = 0.03), peripapillary retinal nerve fiber layer (rho = 0.37; p = 0.01), and ganglion cell/inner plexiform layer (rho = 0.41; p = 0.006) atrophy. The rate of change in NEV synaptophysin was also correlated with whole brain (rho = 0.31; p = 0.04) and cortical gray matter (rho = 0.31; p = 0.049) atrophy. DISCUSSION: NEV-derived synaptic proteins likely reflect neurodegeneration and may provide additional circulating biomarkers for disease progression in MS.

Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI.

Clinical magnetic resonance images (MRIs) lack a standard intensity scale due to differences in scanner hardware and the pulse sequences used to acquire the images. When MRIs are used for quantification, as in the evaluation of white matter lesions (WMLs) in multiple sclerosis, this lack of intensity standardization becomes a critical problem affecting both the staging and tracking of the disease and its treatment. This paper presents a study of harmonization on WML segmentation consistency, which is evaluated using an object detection classification scheme that incorporates manual delineations from both the original and harmonized MRIs. A cohort of ten people scanned on two different imaging platforms was studied. An expert rater, blinded to the image source, manually delineated WMLs on images from both scanners before and after harmonization. It was found that there is closer agreement in both global and per-lesion WML volume and spatial distribution after harmonization, demonstrating the importance of image harmonization prior to the creation of manual delineations. These results could lead to better truth models in both the development and evaluation of automated lesion segmentation algorithms.

Development of Medical Imaging Data Standardization for Imaging-Based Observational Research: OMOP Common Data Model Extension.

The rapid growth of artificial intelligence (AI) and deep learning techniques require access to large inter-institutional cohorts of data to enable the development of robust models, e.g., targeting the identification of disease biomarkers and quantifying disease progression and treatment efficacy. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) has been designed to accommodate a harmonized representation of observational healthcare data. This study proposes the Medical Imaging CDM (MI-CDM) extension, adding two new tables and two vocabularies to the OMOP CDM to address the structural and semantic requirements to support imaging research. The tables provide the capabilities of linking DICOM data sources as well as tracking the provenance of imaging features derived from those images. The implementation of the extension enables phenotype definitions using imaging features and expanding standardized computable imaging biomarkers. This proposal offers a comprehensive and unified approach for conducting imaging research and outcome studies utilizing imaging features.

Bile acid metabolites predict multiple sclerosis progression and supplementation is safe in progressive disease.

Background: Bile acid metabolism is altered in multiple sclerosis (MS) and tauroursodeoxycholic acid (TUDCA) supplementation ameliorated disease in mouse models of MS. Methods: Global metabolomics was performed in an observational cohort of people with MS followed by pathway analysis to examine relationships between baseline metabolite levels and subsequent brain and retinal atrophy. A double-blind, placebo-controlled trial, was completed in people with progressive MS (PMS), randomized to receive either TUDCA (2g daily) or placebo for 16 weeks. Participants were followed with serial clinical and laboratory assessments. Primary outcomes were safety and tolerability of TUDCA, and exploratory outcomes included changes in clinical, laboratory and gut microbiome parameters. Results: In the observational cohort, higher primary bile acid levels at baseline predicted slower whole brain, brain substructure and specific retinal layer atrophy. In the clinical trial, 47 participants were included in our analyses (21 in placebo arm, 26 in TUDCA arm). Adverse events did not significantly differ between arms (p=0.77). The TUDCA arm demonstrated increased serum levels of multiple bile acids. No significant differences were noted in clinical or fluid biomarker outcomes. Central memory CD4+ and Th1/17 cells decreased, while CD4+ naïve cells increased in the TUDCA arm compared to placebo. Changes in the composition and function of gut microbiota were also noted in the TUDCA arm compared to placebo. Conclusion: Bile acid metabolism in MS is linked with brain and retinal atrophy. TUDCA supplementation in PMS is safe, tolerable and has measurable biological effects that warrant further evaluation in larger trials with a longer treatment duration.

HACA3: A unified approach for multi-site MR image harmonization.

The lack of standardization and consistency of acquisition is a prominent issue in magnetic resonance (MR) imaging. This often causes undesired contrast variations in the acquired images due to differences in hardware and acquisition parameters. In recent years, image synthesis-based MR harmonization with disentanglement has been proposed to compensate for the undesired contrast variations. The general idea is to disentangle anatomy and contrast information from MR images to achieve cross-site harmonization. Despite the success of existing methods, we argue that major improvements can be made from three aspects. First, most existing methods are built upon the assumption that multi-contrast MR images of the same subject share the same anatomy. This assumption is questionable, since different MR contrasts are specialized to highlight different anatomical features. Second, these methods often require a fixed set of MR contrasts for training (e.g., both T1-weighted and T2-weighted images), limiting their applicability. Lastly, existing methods are generally sensitive to imaging artifacts. In this paper, we present Harmonization with Attention-based Contrast, Anatomy, and Artifact Awareness (HACA3), a novel approach to address these three issues. HACA3 incorporates an anatomy fusion module that accounts for the inherent anatomical differences between MR contrasts. Furthermore, HACA3 can be trained and applied to any combination of MR contrasts and is robust to imaging artifacts. HACA3 is developed and evaluated on diverse MR datasets acquired from 21 sites with varying field strengths, scanner platforms, and acquisition protocols. Experiments show that HACA3 achieves state-of-the-art harmonization performance under multiple image quality metrics. We also demonstrate the versatility and potential clinical impact of HACA3 on downstream tasks including white matter lesion segmentation for people with multiple sclerosis and longitudinal volumetric analyses for normal aging subjects. Code is available at https://github.com/lianruizuo/haca3.

Intersite brain MRI volumetric biases persist even in a harmonized multisubject study of multiple sclerosis.

BACKGROUND AND PURPOSE: Multicenter study designs involving a variety of MRI scanners have become increasingly common. However, these present the issue of biases in image-based measures due to scanner or site differences. To assess these biases, we imaged 11 volunteers with multiple sclerosis (MS) with scan and rescan data at four sites. METHODS: Images were acquired on Siemens or Philips scanners at 3 Tesla. Automated white matter lesion detection and whole-brain, gray and white matter, and thalamic volumetry were performed, as well as expert manual delineations of T1 magnetization-prepared rapid acquisition gradient echo and T2 fluid-attenuated inversion recovery lesions. Random-effect and permutation-based nonparametric modeling was performed to assess differences in estimated volumes within and across sites. RESULTS: Random-effect modeling demonstrated model assumption violations for most comparisons of interest. Nonparametric modeling indicated that site explained >50% of the variation for most estimated volumes. This expanded to >75% when data from both Siemens and Philips scanners were included. Permutation tests revealed significant differences between average inter- and intrasite differences in most estimated brain volumes (P < .05). The automatic activation of spine coil elements during some acquisitions resulted in a shading artifact in these images. Permutation tests revealed significant differences between thalamic volume measurements from acquisitions with and without this artifact. CONCLUSION: Differences in brain volumetry persisted across MR scanners despite protocol harmonization. These differences were not well explained by variance component modeling; however, statistical innovations for mitigating intersite differences show promise in reducing biases in multicenter studies of MS.

Deconfounded Dimension Reduction via Partial Embeddings.

Dimension reduction tools preserving similarity and graph structure such as t-SNE and UMAP can capture complex biological patterns in high-dimensional data. However, these tools typically are not designed to separate effects of interest from unwanted effects due to confounders. We introduce the partial embedding (PARE) framework, which enables removal of confounders from any distance-based dimension reduction method. We then develop partial t-SNE and partial UMAP and apply these methods to genomic and neuroimaging data. Our results show that the PARE framework can remove batch effects in single-cell sequencing data as well as separate clinical and technical variability in neuroimaging measures. We demonstrate that the PARE framework extends dimension reduction methods to highlight biological patterns of interest while effectively removing confounding effects.

Deep gray matter substructure volumes and depressive symptoms in a large multiple sclerosis cohort.

BACKGROUND: Consistent findings on underlying brain features or specific structural atrophy patterns contributing to depression in multiple sclerosis (MS) are limited. OBJECTIVE: To investigate how deep gray matter (DGM) features predict depressive symptom trajectories in MS patients. METHODS: We used data from the MS Partners Advancing Technology and Health Solutions (MS PATHS) network in which standardized patient information and outcomes are collected. We performed whole-brain segmentation using SLANT-CRUISE. We assessed if DGM structures were associated with elevated depressive symptoms over follow-up and with depressive symptom phenotypes. RESULTS: We included 3844 participants (average age: 46.05 ± 11.83 years; 72.7% female) of whom 1905 (49.5%) experienced ⩾1 periods of elevated depressive symptoms over 2.6 ± 0.9 years mean follow-up. Higher caudate, putamen, accumbens, ventral diencephalon, thalamus, and amygdala volumes were associated with lower odds of elevated depressive symptoms over follow-up (odds ratio (OR) range per 1 SD (standard deviation) increase in volume: 0.88-0.94). For example, a 1 SD increase in accumbens or caudate volume was associated with 12% or 10% respective lower odds of having a period of elevated depressive symptoms over follow-up (for accumbens: OR: 0.88; 95% confidence interval (CI): 0.83-0.93; p < 0.001; for caudate: OR: 0.90; 95% CI: 0.85-0.96; p = 0.003). CONCLUSION: Lower DGM volumes were associated with depressive symptom trajectories in MS.

Trans-Synaptic Degeneration Following Acute Optic Neuritis in Multiple Sclerosis.

OBJECTIVE: To explore longitudinal changes in brain volumetric measures and retinal layer thicknesses following acute optic neuritis (AON) in people with multiple sclerosis (PwMS), to investigate the process of trans-synaptic degeneration, and determine its clinical relevance. METHODS: PwMS were recruited within 40 days of AON onset (n = 49), and underwent baseline retinal optical coherence tomography and brain magnetic resonance imaging followed by longitudinal tracking for up to 5 years. A comparator cohort of PwMS without a recent episode of AON were similarly tracked (n = 73). Mixed-effects linear regression models were used. RESULTS: Accelerated atrophy of the occipital gray matter (GM), calcarine GM, and thalamus was seen in the AON cohort, as compared with the non-AON cohort (-0.76% vs -0.22% per year [p = 0.01] for occipital GM, -1.83% vs -0.32% per year [p = 0.008] for calcarine GM, -1.17% vs -0.67% per year [p = 0.02] for thalamus), whereas rates of whole-brain, cortical GM, non-occipital cortical GM atrophy, and T2 lesion accumulation did not differ significantly between the cohorts. In the AON cohort, greater AON-induced reduction in ganglion cell+inner plexiform layer thickness over the first year was associated with faster rates of whole-brain (r = 0.32, p = 0.04), white matter (r = 0.32, p = 0.04), and thalamic (r = 0.36, p = 0.02) atrophy over the study period. Significant relationships were identified between faster atrophy of the subcortical GM and thalamus, with worse visual function outcomes after AON. INTERPRETATION: These results provide in-vivo evidence for anterograde trans-synaptic degeneration following AON in PwMS, and suggest that trans-synaptic degeneration may be related to clinically-relevant visual outcomes. ANN NEUROL 2023;93:76-87.

Bi-directional Synthesis of Pre- and Post-contrast MRI via Guided Feature Disentanglement.

Magnetic resonance imaging (MRI) with gadolinium contrast is widely used for tissue enhancement and better identification of active lesions and tumors. Recent studies have shown that gadolinium deposition can accumulate in tissues including the brain, which raises safety concerns. Prior works have tried to synthesize post-contrast T1-weighted MRIs from pre-contrast MRIs to avoid the use of gadolinium. However, contrast and image representations are often entangled during the synthesis process, resulting in synthetic post-contrast MRIs with undesirable contrast enhancements. Moreover, the synthesis of pre-contrast MRIs from post-contrast MRIs which can be useful for volumetric analysis is rarely investigated in the literature. To tackle pre- and post- contrast MRI synthesis, we propose a BI-directional Contrast Enhancement Prediction and Synthesis (BICEPS) network that enables disentanglement of contrast and image representations via a bi-directional image-to-image translation(I2I)model. Our proposed model can perform both pre-to-post and post-to-pre contrast synthesis, and provides an interpretable synthesis process by predicting contrast enhancement maps from the learned contrast embedding. Extensive experiments on a multiple sclerosis dataset demonstrate the feasibility of applying our bidirectional synthesis and show that BICEPS outperforms current methods.

Generalizing deep learning brain segmentation for skull removal and intracranial measurements.

Total intracranial volume (TICV) and posterior fossa volume (PFV) are essential covariates for brain volumetric analyses with structural magnetic resonance imaging (MRI). Detailed whole brain segmentation provides a non-invasive way to measure brain regions. Furthermore, increasing neuroimaging data are distributed in a skull-stripped manner for privacy protection. Therefore, generalizing deep learning brain segmentation for skull removal and intracranial measurements is an appealing task. However, data availability is challenging due to a limited set of manually traced atlases with whole brain and TICV/PFV labels. In this paper, we employ U-Net tiles to achieve automatic TICV estimation and whole brain segmentation simultaneously on brains w/and w/o the skull. To overcome the scarcity of manually traced whole brain volumes, a transfer learning method is introduced to estimate additional TICV and PFV labels during whole brain segmentation in T1-weighted MRI. Specifically, U-Net tiles are first pre-trained using large-scale BrainCOLOR atlases without TICV and PFV labels, which are created by multi-atlas segmentation. Then the pre-trained models are refined by training the additional TICV and PFV labels using limited BrainCOLOR atlases. We also extend our method to handle skull-stripped brain MR images. From the results, our method provides promising whole brain segmentation and volume estimation results for both brains w/and w/o skull in terms of mean Dice similarity coefficients and mean surface distance and absolute volume similarity. This method has been made available in open source (https://github.com/MASILab/SLANTbrainSeg_skullstripped).

Matrix decomposition for modeling lesion development processes in multiple sclerosis.

Our main goal is to study and quantify the evolution of multiple sclerosis lesions observed longitudinally over many years in multi-sequence structural magnetic resonance imaging (sMRI). To achieve that, we propose a class of functional models for capturing the temporal dynamics and spatial distribution of the voxel-specific intensity trajectories in all sMRI sequences. To accommodate the hierarchical data structure (observations nested within voxels, which are nested within lesions, which, in turn, are nested within study participants), we use structured functional principal component analysis. We propose and evaluate the finite sample properties of hypothesis tests of therapeutic intervention effects on lesion evolution while accounting for the multilevel structure of the data. Using this novel testing strategy, we found statistically significant differences in lesion evolution between treatment groups.

Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory.

In magnetic resonance (MR) imaging, a lack of standardization in acquisition often causes pulse sequence-based contrast variations in MR images from site to site, which impedes consistent measurements in automatic analyses. In this paper, we propose an unsupervised MR image harmonization approach, CALAMITI (Contrast Anatomy Learning and Analysis for MR Intensity Translation and Integration), which aims to alleviate contrast variations in multi-site MR imaging. Designed using information bottleneck theory, CALAMITI learns a globally disentangled latent space containing both anatomical and contrast information, which permits harmonization. In contrast to supervised harmonization methods, our approach does not need a sample population to be imaged across sites. Unlike traditional unsupervised harmonization approaches which often suffer from geometry shifts, CALAMITI better preserves anatomy by design. The proposed method is also able to adapt to a new testing site with a straightforward fine-tuning process. Experiments on MR images acquired from ten sites show that CALAMITI achieves superior performance compared with other harmonization approaches.

Autoencoder based self-supervised test-time adaptation for medical image analysis.

Deep neural networks have been successfully applied to medical image analysis tasks like segmentation and synthesis. However, even if a network is trained on a large dataset from the source domain, its performance on unseen test domains is not guaranteed. The performance drop on data obtained differently from the network's training data is a major problem (known as domain shift) in deploying deep learning in clinical practice. Existing work focuses on retraining the model with data from the test domain, or harmonizing the test domain's data to the network training data. A common practice is to distribute a carefully-trained model to multiple users (e.g., clinical centers), and then each user uses the model to process their own data, which may have a domain shift (e.g., varying imaging parameters and machines). However, the lack of availability of the source training data and the cost of training a new model often prevents the use of known methods to solve user-specific domain shifts. Here, we ask whether we can design a model that, once distributed to users, can quickly adapt itself to each new site without expensive retraining or access to the source training data? In this paper, we propose a model that can adapt based on a single test subject during inference. The model consists of three parts, which are all neural networks: a task model (T) which performs the image analysis task like segmentation; a set of autoencoders (AEs); and a set of adaptors (As). The task model and autoencoders are trained on the source dataset and can be computationally expensive. In the deployment stage, the adaptors are trained to transform the test image and its features to minimize the domain shift as measured by the autoencoders' reconstruction loss. Only the adaptors are optimized during the testing stage with a single test subject thus is computationally efficient. The method was validated on both retinal optical coherence tomography (OCT) image segmentation and magnetic resonance imaging (MRI) T1-weighted to T2-weighted image synthesis. Our method, with its short optimization time for the adaptors (10 iterations on a single test subject) and its additional required disk space for the autoencoders (around 15 MB), can achieve significant performance improvement. Our code is publicly available at: https://github.com/YufanHe/self-domain-adapted-network.

Cognitive impairment, the central vein sign, and paramagnetic rim lesions in RIS.

OBJECTIVE: The central vein sign (CVS) and "paramagnetic rim lesions" (PRL) are emerging imaging biomarkers in multiple sclerosis (MS) reflecting perivenular demyelination and chronic, smoldering inflammation. The objective of this study was to assess relationships between cognitive impairment (CI) and the CVS and PRL in radiologically isolated syndrome (RIS). METHODS: Twenty-seven adults with RIS underwent 3.0 T MRI of the brain and cervical spinal cord (SC) and cognitive assessment using the minimal assessment of cognitive function in MS battery. The CVS and PRL were assessed in white-matter lesions (WMLs) on T2*-weighted segmented echo-planar magnitude and phase images. Multivariable linear regression evaluated relationships between CI and MRI measures. RESULTS: Global CI was present in 9 (33%) participants with processing speed and visual memory most frequently affected. Most participants (93%) had ⩾ 40% CVS + WML (a threshold distinguishing MS from other WM disorders); 63% demonstrated PRL. Linear regression revealed that CVS + WML predicted performance on verbal memory(ß =-0.024, p = 0.03) while PRL predicted performance on verbal memory (ß = -0.040, p = 0.04) and processing speed (ß = -0.039, p = 0.03). CONCLUSIONS: CI is common in RIS and is associated with markers of perivenular demyelination and chronic inflammation in WML, such as CVS + WML and PRL. A prospective follow-up of this cohort will ascertain the importance of CI, CVS, and PRL as risk factors for conversion from RIS to MS.

Five-year longitudinal changes in quantitative spinal cord MRI in multiple sclerosis.

BACKGROUND: The spinal cord (SC) is highly relevant to disability in multiple sclerosis (MS), but few studies have evaluated longitudinal changes in quantitative spinal cord magnetic resonance imaging (SC-MRI). OBJECTIVES: The aim of this study was to characterize the relationships between 5-year changes in SC-MRI with disability in MS. METHODS: In total, 75 MS patients underwent 3 T SC-MRI and clinical assessment (expanded disability status scale (EDSS) and MS functional composite (MSFC)) at baseline, 2 and 5 years. SC-cross-sectional area (CSA) and diffusion-tensor indices (fractional anisotropy (FA), mean, perpendicular, parallel diffusivity (MD, λ⊥, λ||) and magnetization transfer ratio (MTR)) were extracted at C3-C4. Mixed-effects regression incorporating subject-specific slopes assessed longitudinal change in SC-MRI measures. RESULTS: SC-CSA and MTR decreased (p = 0.009, p = 0.03) over 5.1 years. There were moderate correlations between 2- and 5-year subject-specific slopes of SC-MRI indices and follow-up EDSS scores (Pearson's r with FA = -0.23 (p < 0.001); MD = 0.31 (p < 0.001); λ⊥ = 0.34 (p < 0.001); λ|| = -0.12 (p = 0.05), MTR = -0.37 (p < 0.001); SC-CSA = -0.47 (p < 0.001) at 5 years); MSFC showed similar trends. The 2- and 5-year subject-specific slopes were robustly correlated (r = 0.93-0.97 for FA, λ⊥, SC-CSA and MTR, all ps < 0.001). CONCLUSION: In MS, certain quantitative SC-MRI indices change over 5 years, reflecting ongoing tissue changes. Subject-specific trajectories of SC-MRI index change at 2 and 5 years are strongly correlated and highly relevant to follow-up disability. These findings suggest that individual dynamics of change should be accounted for when interpreting longitudinal SC-MRI measures and that measuring short-term change is predictive of long-term clinical disability.

Joint Image and Label Self-Super-Resolution.

We propose a method to jointly super-resolve an anisotropic image volume along with its corresponding voxel labels without external training data. Our method is inspired by internally trained superresolution, or self-super-resolution (SSR) techniques that target anisotropic, low-resolution (LR) magnetic resonance (MR) images. While resulting images from such methods are quite useful, their corresponding LR labels-derived from either automatic algorithms or human raters-are no longer in correspondence with the super-resolved volume. To address this, we develop an SSR deep network that takes both an anisotropic LR MR image and its corresponding LR labels as input and produces both a super-resolved MR image and its super-resolved labels as output. We evaluated our method with 50 T 1-weighted brain MR images 4× down-sampled with 10 automatically generated labels. In comparison to other methods, our method had superior Dice across all labels and competitive metrics on the MR image. Our approach is the first reported method for SSR of paired anisotropic image and label volumes.

Frequency and phase correction of J-difference edited MR spectra using deep learning.

PURPOSE: To investigate whether a deep learning-based (DL) approach can be used for frequency-and-phase correction (FPC) of MEGA-edited MRS data. METHODS: Two neural networks (1 for frequency, 1 for phase) consisting of fully connected layers were trained and validated using simulated MEGA-edited MRS data. This DL-FPC was subsequently tested and compared to a conventional approach (spectral registration [SR]) and to a model-based SR implementation (mSR) using in vivo MEGA-edited MRS datasets. Additional artificial offsets were added to these datasets to further investigate performance. RESULTS: The validation showed that DL-based FPC was capable of correcting within 0.03 Hz of frequency and 0.4°of phase offset for unseen simulated data. DL-based FPC performed similarly to SR for the unmanipulated in vivo test datasets. When additional offsets were added to these datasets, the networks still performed well. However, although SR accurately corrected for smaller offsets, it often failed for larger offsets. The mSR algorithm performed well for larger offsets, which was because the model was generated from the in vivo datasets. In addition, the computation times were much shorter using DL-based FPC or mSR compared to SR for heavily distorted spectra. CONCLUSION: These results represent a proof of principle for the use of DL for preprocessing MRS data.

SMORE: A Self-Supervised Anti-Aliasing and Super-Resolution Algorithm for MRI Using Deep Learning.

High resolution magnetic resonance (MR) images are desired in many clinical and research applications. Acquiring such images with high signal-to-noise (SNR), however, can require a long scan duration, which is difficult for patient comfort, is more costly, and makes the images susceptible to motion artifacts. A very common practical compromise for both 2D and 3D MR imaging protocols is to acquire volumetric MR images with high in-plane resolution, but lower through-plane resolution. In addition to having poor resolution in one orientation, 2D MRI acquisitions will also have aliasing artifacts, which further degrade the appearance of these images. This paper presents an approach SMORE1 based on convolutional neural networks (CNNs) that restores image quality by improving resolution and reducing aliasing in MR images.2 This approach is self-supervised, which requires no external training data because the high-resolution and low-resolution data that are present in the image itself are used for training. For 3D MRI, the method consists of only one self-supervised super-resolution (SSR) deep CNN that is trained from the volumetric image data. For 2D MRI, there is a self-supervised anti-aliasing (SAA) deep CNN that precedes the SSR CNN, also trained from the volumetric image data. Both methods were evaluated on a broad collection of MR data, including filtered and downsampled images so that quantitative metrics could be computed and compared, and actual acquired low resolution images for which visual and sharpness measures could be computed and compared. The super-resolution method is shown to be visually and quantitatively superior to previously reported methods.