Cross-scanner harmonization methods for structural MRI may need further work: A comparison study

Penetrance of neurodevelopmental copy number variants is associated with variations in cortical morphology

BACKGROUND

Copy number variants (CNVs) increase risk for neurodevelopmental conditions. The neurobiological mechanisms linking these high-risk genetic variants to clinical phenotypes are largely unknown. An important question is whether brain abnormalities in individuals carrying CNVs are associated with their degree of penetrance.

METHODS

We investigated if increased CNV-penetrance for schizophrenia and other developmental disorders was associated with variations in cortical and subcortical morphology. We pooled T1-weighted brain magnetic resonance imaging and genetic data from 22 cohorts from the ENIGMA-CNV consortium. In the main analyses, we included 9,268 individuals (aged 7 to 90 years, 54% females), from which we identified 398 carriers of 36 neurodevelopmental CNVs at 20 distinct loci. A secondary analysis was performed including additional neuroimaging data from the ENIGMA-22q consortium, including 274 carriers of the 22q11.2 deletion and 291 non-carriers. CNV-penetrance was estimated through penetrance scores that were previously generated from large cohorts of patients and controls. These scores represent the probability risk to develop either schizophrenia or other developmental disorders (including developmental delay, autism spectrum disorder and congenital malformations).

RESULTS

For both schizophrenia and developmental disorders, increased penetrance scores were associated with lower surface area in the cerebral cortex and lower intracranial volume. For both conditions, associations between CNV-penetrance scores and cortical surface area were strongest in regions of the occipital lobes, specifically in the cuneus and lingual gyrus.

CONCLUSIONS

Our findings link global and regional cortical morphometric features with CNV-penetrance, providing new insights into neurobiological mechanisms of genetic risk for schizophrenia and other developmental disorders.

Rethinking MRI as a measurement device through modular and portable pipelines

The premise of MRI as a reliable measurement device is limited by proprietary barriers and inconsistent implementations, which prevent the establishment of measurement uncertainties. As a result, biomedical studies that rely on these methods are plagued by systematic variance, undermining the perceived promise of quantitative imaging biomarkers (QIBs) and hindering their clinical translation. This review explores the added value of open-source measurement pipelines in minimizing variability sources that would otherwise remain unknown. First, we introduce a tiered benchmarking framework (from black-box to glass-box) that exposes how opacity at different workflow stages propagates measurement uncertainty. Second, we provide a concise glossary to promote consistent terminology for strategies that enhance reproducibility before acquisition or enable valid post-hoc pooling of QIBs. Building on this foundation, we present two illustrative measurement workflows that decouple workflow logic from the orchestration of computational processes in an MRI measurement pipeline, rooted in the core principles of modularity and portability. Designed as accessible entry points for implementation, these examples serve as practical guides, helping users adapt the frameworks to their specific needs and facilitating collaboration. Through critical evaluation of existing approaches, we discuss how standardized workflows can help identify outstanding challenges in translating glass-box frameworks into clinical scanner environments. Ultimately, achieving this goal will require coordinated efforts from QIB developers, regulators, industry partners, and clinicians alike.

Site effects in multisite fetal brain MRI: morphological insights into early brain development

OBJECTIVE

To evaluate multisite effects on fetal brain MRI. Specifically, to identify crucial acquisition factors affecting fetal brain structural measurements and developmental patterns, while assessing the effectiveness of existing harmonization methods in mitigating site effects.

MATERIALS AND METHODS

Between May 2017 and March 2022, T2-weighted fast spin-echo sequences in-utero MRI were performed on healthy fetuses from retrospectively recruited pregnant volunteers on four different scanners at four sites. A generalized additive model (GAM) was used to quantitatively assess site effects, including field strength (FS), manufacturer (M), in-plane resolution (R), and slice thickness (ST), on subcortical volume and cortical morphological measurements, including cortical thickness, curvature, and sulcal depth. Growth models were selected to elucidate the developmental trajectories of these morphological measurements. Welch's test was performed to evaluate the influence of site effects on developmental trajectories. The comBat-GAM harmonization method was applied to mitigate site-related biases.

RESULTS

The final analytic sample consisted of 340 MRI scans from 218 fetuses (mean GA, 30.1 weeks ± 4.4 [range, 21.7-40 weeks]). GAM results showed that lower FS and lower spatial resolution led to overestimations in selected brain regions of subcortical volumes and cortical morphological measurements. Only the peak cortical thickness in developmental trajectories was significantly influenced by the effects of FS and R. Notably, ComBat-GAM harmonization effectively removed site effects while preserving developmental patterns.

CONCLUSION

Our findings pinpointed the key acquisition factors in in-utero fetal brain MRI and underscored the necessity of data harmonization when pooling multisite data for fetal brain morphology investigations.

KEY POINTS

Question How do specific site MRI acquisition factors affect fetal brain imaging? Finding Lower FS and spatial resolution overestimated subcortical volumes and cortical measurements. Cortical thickness in developmental trajectories was influenced by FS and in-plane resolution. Clinical relevance This study provides important guidelines for the fetal MRI community when scanning fetal brains and underscores the necessity of data harmonization of cross-center fetal studies.

Impact of harmonization on predicting complications in head and neck cancer after radiotherapy using MRI radiomics and machine learning techniques

BACKGROUND

Variations in medical images specific to individual scanners restrict the use of radiomics in both clinical practice and research. To create reproducible and generalizable radiomics-based models for outcome prediction and assessment, data harmonization is essential.

PURPOSE

This study aims to investigate the impact of harmonization in performance of machine learning-based radiomics model toward the prediction of radiotherapy-induced toxicity (early and late sticky saliva and xerostomia) in head and neck cancer (HNC) patients after radiation therapy usingT 1 $T_1$ andT 2 $T_2$ -weighted magnetic resonance (MR) images.

METHODS

A total of 85 HNC patients who underwent radiotherapy was studied. Radiomic features were extracted fromT 1 $T_1$ andT 2 $T_2$ -weighted MR images with standardized protocols. Data harmonization was performed using ComBat algorithm to reduce inter-center variability. Besides imaging features, both dosimetric and demographic features were extracted and used in our model. Recursive feature elimination was employed as feature selection method to identify the most important variables. Ten classification algorithms, including eXtreme Gradient Boosting (XGBoost), multilayer perceptron (MLP), support vector machines (SVM), random forest (RF), k-nearest neighbor (KNN), Naive Bayes (NB), logistic regression (LR), and decision tree (DT), boosted generalized linear model (GLMB), and stack learning (SL) were utilized and compared to develop predictive models. This evaluation comparisons were performed before and after harmonization to demonstrate its significance.

RESULTS

Our results indicate that harmonization consistently enhances predictive performance across various complications and imaging modalities. In early and late sticky saliva prediction usingT 1 $T_1$ -weighted images, the SVM and RF models achieved an impressive area under the curve (AUC) of 0.88 ± $\pm$ 0.09 and 0.97 ± $\pm$ 0.05 with harmonization versus 0.42 ± $\pm$ 0.12 and 0.83 ± $\pm$ 0.08 without harmonization, respectively. Similarly, in early and late xerostomia prediction, the model attained an AUC of 0.79 ± $\pm$ 0.15 and 0.61 ± $\pm$ 0.14 with harmonization and 0.55 ± $\pm$ 0.17 and 0.46 ± $\pm$ 0.14 without harmonization.

CONCLUSION

Our study highlights the importance of harmonization techniques in improving the performance of predictive models utilizing magnetic resonance imaging radiomics features. While harmonization consistently enhanced performance for sticky saliva and early xerostomia usingT 1 $T_1$ -weighted features, the prediction of early and late xerostomia usingT 2 $T_2$ -weighted features remains challenging. These findings try to develop accurate and reliable predictive models in medical imaging, that contribute to improve patient care and treatment outcomes.

A review of deep learning for brain tumor analysis in MRI

Recent progress in deep learning (DL) is producing a new generation of tools across numerous clinical applications. Within the analysis of brain tumors in magnetic resonance imaging, DL finds applications in tumor segmentation, quantification, and classification. It facilitates objective and reproducible measurements crucial for diagnosis, treatment planning, and disease monitoring. Furthermore, it holds the potential to pave the way for personalized medicine through the prediction of tumor type, grade, genetic mutations, and patient survival outcomes. In this review, we explore the transformative potential of DL for brain tumor care and discuss existing applications, limitations, and future directions and opportunities.

A Machine Learning Model to Harmonize Volumetric Brain MRI Data for Quantitative Neuroradiologic Assessment of Alzheimer Disease

Purpose To extend a previously developed machine learning algorithm for harmonizing brain volumetric data of individuals undergoing neuroradiologic assessment of Alzheimer disease not encountered during model training. Materials and Methods Neuroharmony is a recently developed method that uses image quality metrics as predictors to remove scanner-related effects in brain-volumetric data using random forest regression. To account for the interactions between Alzheimer disease pathology and image quality metrics during harmonization, the authors developed a multiclass extension of Neuroharmony for individuals with and without cognitive impairment. Cross-validation experiments were performed to benchmark performance against other available strategies using data from 20 864 participants with and without cognitive impairment, spanning 11 prospective and retrospective cohorts and 43 scanners. Evaluation metrics assessed the ability to remove scanner-related variations in brain volumes (marker concordance between scanner pairs) while retaining the ability to delineate different diagnostic groups (preserving disease-related signal). Results For each strategy, marker concordances between scanners were significantly better (P < .001) compared with preharmonized data. The proposed multiclass model achieved significantly higher concordance (mean, 0.75 ± 0.09 [SD]) than the Neuroharmony model trained on individuals without cognitive impairment (mean, 0.70 ± 0.11) and preserved disease-related signal (∆AUC [area under the receiver operating characteristic curve] = -0.006 ± 0.027) better than the Neuroharmony model trained on individuals with and without cognitive impairment that did not use the proposed extension (∆AUC = -0.091 ± 0.036). The marker concordance was better in scanners seen during training (concordance > 0.97) than unseen (concordance < 0.79), independent of cognitive status. Conclusion In a large-scale multicenter dataset, the proposed multiclass Neuroharmony model outperformed other available strategies for harmonizing brain volumetric data from unseen scanners in a clinical setting. Keywords: Image Postprocessing, MR Imaging, Dementia, Random Forest Supplemental material is available for this article. Published under a CC BY 4.0 license See also commentary by Haller in this issue.

IGUANe: A 3D generalizable CycleGAN for multicenter harmonization of brain MR images

In MRI studies, the aggregation of imaging data from multiple acquisition sites enhances sample size but may introduce site-related variabilities that hinder consistency in subsequent analyses. Deep learning methods for image translation have emerged as a solution for harmonizing MR images across sites. In this study, we introduce IGUANe (Image Generation with Unified Adversarial Networks), an original 3D model that leverages the strengths of domain translation and straightforward application of style transfer methods for multicenter brain MR image harmonization. IGUANe extends CycleGAN by integrating an arbitrary number of domains for training through a many-to-one architecture. The framework based on domain pairs enables the implementation of sampling strategies that prevent confusion between site-related and biological variabilities. During inference, the model can be applied to any image, even from an unknown acquisition site, making it a universal generator for harmonization. Trained on a dataset comprising T1-weighted images from 11 different scanners, IGUANe was evaluated on data from unseen sites. The assessments included the transformation of MR images with traveling subjects, the preservation of pairwise distances between MR images within domains, the evolution of volumetric patterns related to age and Alzheimer's disease (AD), and the performance in age regression and patient classification tasks. Comparisons with other harmonization and normalization methods suggest that IGUANe better preserves individual information in MR images and is more suitable for maintaining and reinforcing variabilities related to age and AD. Future studies may further assess IGUANe in other multicenter contexts, either using the same model or retraining it for applications to different image modalities. Codes and the trained IGUANe model are available at https://github.com/RocaVincent/iguane_harmonization.git.

Overview of ADNI MRI

The magnetic resonance imaging (MRI) Core has been operating since Alzheimer's Disease Neuroimaging Initiative's (ADNI) inception, providing 20 years of data including reliable, multi-platform standardized protocols, carefully curated image data, and quantitative measures provided by expert investigators. The overarching purposes of the MRI Core include: (1) optimizing and standardizing MRI acquisition methods, which have been adopted by many multicenter studies and trials worldwide and (2) providing curated images and numeric summary values from relevant MRI sequences/contrasts to the scientific community. Over time, ADNI MRI has become increasingly complex. To remain technically current, the ADNI MRI protocol has changed substantially over the past two decades. The ADNI 4 protocol contains nine different imaging types (e.g., three dimensional [3D] T1-weighted and fluid-attenuated inversion recovery [FLAIR]). Our view is that the ADNI MRI data are a greatly underutilized resource. The purpose of this paper is to educate the scientific community on ADNI MRI methods and content to promote greater awareness, accessibility, and use. HIGHLIGHTS: The MRI Core provides multi-platform standardized protocols, carefully curated image data, and quantitative analysis by expert groups. The ADNI MRI protocol has undergone major changes over the past two decades to remain technically current. As of April 25, 2024, the following numbers of image series are available: 17,141 3D T1w; 6877 FLAIR; 3140 T2/PD; 6623 GRE; 3237 dMRI; 2846 ASL; 2968 TF-fMRI; and 2861 HighResHippo (see Table 1 for abbreviations). As of April 25, 2024, the following numbers of quantitative analyses are available: FreeSurfer 10,997; BSI 6120; tensor based morphometry (TBM) and TBM-SYN 12,019; WMH 9944; dMRI 1913; ASL 925; TF-fMRI NFQ 2992; and medial temporal subregion volumes 2726 (see Table 4 for abbreviations). ADNI MRI is an underutilized resource that could be more useful to the research community.

Modeling the impact of MRI acquisition bias on structural connectomes: Harmonizing structural connectomes

One way to increase the statistical power and generalizability of neuroimaging studies is to collect data at multiple sites or merge multiple cohorts. However, this usually comes with site-related biases due to the heterogeneity of scanners and acquisition parameters, negatively impacting sensitivity. Brain structural connectomes are not an exception: Being derived from T1-weighted and diffusion-weighted magnetic resonance images, structural connectivity is impacted by differences in imaging protocol. Beyond minimizing acquisition parameter differences, removing bias with postprocessing is essential. In this work we create, from the exhaustive Human Connectome Project Young Adult dataset, a resampled dataset of different b-values and spatial resolutions, modeling a cohort scanned across multiple sites. After demonstrating the statistical impact of acquisition parameters on connectivity, we propose a linear regression with explicit modeling of b-value and spatial resolution, and validate its performance on separate datasets. We show that b-value and spatial resolution affect connectivity in different ways and that acquisition bias can be reduced using a linear regression informed by the acquisition parameters while retaining interindividual differences and hence boosting fingerprinting performance. We also demonstrate the generative potential of our model, and its generalization capability in an independent dataset reflective of typical acquisition practices in clinical settings.

SiMix: A domain generalization method for cross-site brain MRI harmonization via site mixing

Brain magnetic resonance imaging (MRI) is widely used in clinical practice for disease diagnosis. However, MRI scans acquired at different sites can have different appearances due to the difference in the hardware, pulse sequence, and imaging parameter. It is important to reduce or eliminate such cross-site variations with brain MRI harmonization so that downstream image processing and analysis is performed consistently. Previous works on the harmonization problem require the data acquired from the sites of interest for model training. But in real-world scenarios there can be test data from a new site of interest after the model is trained, and training data from the new site is unavailable when the model is trained. In this case, previous methods cannot optimally handle the test data from the new unseen site. To address the problem, in this work we explore domain generalization for brain MRI harmonization and propose Site Mix (SiMix). We assume that images of travelling subjects are acquired at a few existing sites for model training. To allow the training data to better represent the test data from unseen sites, we first propose to mix the training images belonging to different sites stochastically, which substantially increases the diversity of the training data while preserving the authenticity of the mixed training images. Second, at test time, when a test image from an unseen site is given, we propose a multiview strategy that perturbs the test image with preserved authenticity and ensembles the harmonization results of the perturbed images for improved harmonization quality. To validate SiMix, we performed experiments on the publicly available SRPBS dataset and MUSHAC dataset that comprised brain MRI acquired at nine and two different sites, respectively. The results indicate that SiMix improves brain MRI harmonization for unseen sites, and it is also beneficial to the harmonization of existing sites.

Can integration of Alzheimer's plasma biomarkers with MRI, cardiovascular, genetics, and lifestyle measures improve cognition prediction?

There is increasing interest in Alzheimer's disease related plasma biomarkers due to their accessibility and scalability. We hypothesized that integrating plasma biomarkers with other commonly used and available participant data (MRI, cardiovascular factors, lifestyle, genetics) using machine learning (ML) models can improve individual prediction of cognitive outcomes. Further, our goal was to evaluate the heterogeneity of these predictors across different age strata. This longitudinal study included 1185 participants from the Mayo Clinic Study of Aging who had complete plasma analyte work-up at baseline. We used the Quanterix Simoa immunoassay to measure neurofilament light, Aβ1-42 and Aβ1-40 (used as Aβ42/Aβ40 ratio), glial fibrillary acidic protein, and phosphorylated tau 181 (p-tau181). Participants' brain health was evaluated through gray and white matter structural MRIs. The study also considered cardiovascular factors (hyperlipidemia, hypertension, stroke, diabetes, chronic kidney disease), lifestyle factors (area deprivation index, body mass index, cognitive and physical activities), and genetic factors (APOE, single nucleotide polymorphisms, and polygenic risk scores). An ML model was developed to predict cognitive outcomes at baseline and decline (slope). Three models were created: a base model with groups of risk factors as predictors, an enhanced model included socio-demographics, and a final enhanced model by incorporating plasma and socio-demographics into the base models. Models were explained for three age strata: younger than 65 years, 65-80 years, and older than 80 years, and further divided based on amyloid positivity status. Regardless of amyloid status the plasma biomarkers showed comparable performance (R² = 0.15) to MRI (R² = 0.18) and cardiovascular measures (R² = 0.10) when predicting cognitive decline. Inclusion of cardiovascular or MRI measures with plasma in the presence of socio-demographic improved cognitive decline prediction (R² = 0.26 and 0.27). For amyloid positive individuals Aβ42/Aβ40, glial fibrillary acidic protein and p-tau181 were the top predictors of cognitive decline while Aβ42/Aβ40 was prominent for amyloid negative participants across all age groups. Socio-demographics explained a large portion of the variance in the amyloid negative individuals while the plasma biomarkers predominantly explained the variance in amyloid positive individuals (21% to 37% from the younger to the older age group). Plasma biomarkers performed similarly to MRI and cardiovascular measures when predicting cognitive outcomes and combining them with either measure resulted in better performance. Top predictors were heterogeneous between cross-sectional and longitudinal cognition models, across age groups, and amyloid status. Multimodal approaches will enhance the usefulness of plasma biomarkers through careful considerations of a study population's socio-demographics, brain and cardiovascular health.

ComBatLS: A location- and scale-preserving method for multi-site image harmonization

Recent work has leveraged massive datasets and advanced harmonization methods to construct normative models of neuroanatomical features and benchmark individuals' morphology. However, current harmonization tools do not preserve the effects of biological covariates including sex and age on features' variances; this failure may induce error in normative scores, particularly when such factors are distributed unequally across sites. Here, we introduce a new extension of the popular ComBat harmonization method, ComBatLS, that preserves biological variance in features' locations and scales. We use UK Biobank data to show that ComBatLS robustly replicates individuals' normative scores better than other ComBat methods when subjects are assigned to sex-imbalanced synthetic "sites". Additionally, we demonstrate that ComBatLS significantly reduces sex biases in normative scores compared to traditional methods. Finally, we show that ComBatLS successfully harmonizes consortium data collected across over 50 studies. R implementation of ComBatLS is available at https://github.com/andy1764/ComBatFamily.

Evaluation of Mean Shift, ComBat, and CycleGAN for Harmonizing Brain Connectivity Matrices Across Sites

Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph measures derived from these matrices before and after applying three harmonization techniques: mean shift, ComBat, and CycleGAN. The sample comprises 168 age-matched, sex-matched normal subjects from two studies: the Vanderbilt Memory and Aging Project (VMAP) and the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD). First, we plotted the graph measures and used coefficient of variation (CoV) and the Mann-Whitney U test to evaluate different methods' effectiveness in removing site effects on the matrices and the derived graph measures. ComBat effectively eliminated site effects for global efficiency and modularity and outperformed the other two methods. However, all methods exhibited poor performance when harmonizing average betweenness centrality. Second, we tested whether our harmonization methods preserved correlations between age and graph measures. All methods except for CycleGAN in one direction improved correlations between age and global efficiency and between age and modularity from insignificant to significant with p-values less than 0.05.

Evaluation of Mean Shift, ComBat, and CycleGAN for Harmonizing Brain Connectivity Matrices Across Sites

Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph measures derived from these matrices before and after applying three harmonization techniques: mean shift, ComBat, and CycleGAN. The sample comprises 168 age-matched, sex-matched normal subjects from two studies: the Vanderbilt Memory and Aging Project (VMAP) and the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD). First, we plotted the graph measures and used coefficient of variation (CoV) and the Mann-Whitney U test to evaluate different methods' effectiveness in removing site effects on the matrices and the derived graph measures. ComBat effectively eliminated site effects for global efficiency and modularity and outperformed the other two methods. However, all methods exhibited poor performance when harmonizing average betweenness centrality. Second, we tested whether our harmonization methods preserved correlations between age and graph measures. All methods except for CycleGAN in one direction improved correlations between age and global efficiency and between age and modularity from insignificant to significant with p-values less than 0.05.

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.

Effects of MRI scanner manufacturers in classification tasks with deep learning models

Deep learning has become a leading subset of machine learning and has been successfully employed in diverse areas, ranging from natural language processing to medical image analysis. In medical imaging, researchers have progressively turned towards multi-center neuroimaging studies to address complex questions in neuroscience, leveraging larger sample sizes and aiming to enhance the accuracy of deep learning models. However, variations in image pixel/voxel characteristics can arise between centers due to factors including differences in magnetic resonance imaging scanners. Such variations create challenges, particularly inconsistent performance in machine learning-based approaches, often referred to as domain shift, where the trained models fail to achieve satisfactory or improved results when confronted with dissimilar test data. This study analyzes the performance of multiple disease classification tasks using multi-center MRI data obtained from three widely used scanner manufacturers (GE, Philips, and Siemens) across several deep learning-based networks. Furthermore, we investigate the efficacy of mitigating scanner vendor effects using ComBat-based harmonization techniques when applied to multi-center datasets of 3D structural MR images. Our experimental results reveal a substantial decline in classification performance when models trained on one type of scanner manufacturer are tested with data from different manufacturers. Moreover, despite applying ComBat-based harmonization, the harmonized images do not demonstrate any noticeable performance enhancement for disease classification tasks.

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.

DSMRI: Domain Shift Analyzer for Multi-Center MRI Datasets

In medical research and clinical applications, the utilization of MRI datasets from multiple centers has become increasingly prevalent. However, inherent variability between these centers presents challenges due to domain shift, which can impact the quality and reliability of the analysis. Regrettably, the absence of adequate tools for domain shift analysis hinders the development and validation of domain adaptation and harmonization techniques. To address this issue, this paper presents a novel Domain Shift analyzer for MRI (DSMRI) framework designed explicitly for domain shift analysis in multi-center MRI datasets. The proposed model assesses the degree of domain shift within an MRI dataset by leveraging various MRI-quality-related metrics derived from the spatial domain. DSMRI also incorporates features from the frequency domain to capture low- and high-frequency information about the image. It further includes the wavelet domain features by effectively measuring the sparsity and energy present in the wavelet coefficients. Furthermore, DSMRI introduces several texture features, thereby enhancing the robustness of the domain shift analysis process. The proposed framework includes visualization techniques such as t-SNE and UMAP to demonstrate that similar data are grouped closely while dissimilar data are in separate clusters. Additionally, quantitative analysis is used to measure the domain shift distance, domain classification accuracy, and the ranking of significant features. The effectiveness of the proposed approach is demonstrated using experimental evaluations on seven large-scale multi-site neuroimaging datasets.

Temporo-basal sulcal connections: a manual annotation protocol and an investigation of sexual dimorphism and heritability

The temporo-basal region of the human brain is composed of the collateral, the occipito-temporal, and the rhinal sulci. We manually rated (using a novel protocol) the connections between rhinal/collateral (RS-CS), collateral/occipito-temporal (CS-OTS) and rhinal/occipito-temporal (RS-OTS) sulci, using the MRI of nearly 3400 individuals including around 1000 twins. We reported both the associations between sulcal polymorphisms as well with a wide range of demographics (e.g. age, sex, handedness). Finally, we also estimated the heritability, and the genetic correlation between sulcal connections. We reported the frequency of the sulcal connections in the general population, which were hemisphere dependent. We found a sexual dimorphism of the connections, especially marked in the right hemisphere, with a CS-OTS connection more frequent in females (approximately 35-40% versus 20-25% in males) and an RS-CS connection more common in males (approximately 40-45% versus 25-30% in females). We confirmed associations between sulcal connections and characteristics of incomplete hippocampal inversion (IHI). We estimated the broad sense heritability to be 0.28-0.45 for RS-CS and CS-OTS connections, with hints of dominant contribution for the RS-CS connection. The connections appeared to share some of their genetic causing factors as indicated by strong genetic correlations. Heritability appeared much smaller for the (rarer) RS-OTS connection.