Neuroconductor: an R platform for medical imaging analysis

Automated segmentation of ventricular volumes and subarachnoid hemorrhage from computed tomography images: Evaluation of a rule-based pipeline approach

Changes in ventricular size, related to brain edema and hydrocephalus, as well as the extent of hemorrhage are associated with adverse outcomes in patients with subarachnoid hemorrhage (SAH). Frequently, these are measured manually using consecutive non-contrast computed tomography scans. Here, we developed a rule-based approach which incorporates both intensity and spatial normalization and utilizes user-defined thresholds and anatomical templates to segment both lateral ventricle (LV) and SAH blood volumes automatically from CT images. The algorithmic segmentations were evaluated against two expert neuroradiologists on representative slices from 20 admission scans from aneurysmal SAH patients. Previous methods have been developed to automate this time-consuming task, but they lack user feedback and are hard to implement due to large-scale data and complex design processes. Our results using automatic ventricular segmentation aligned well with expert reviewers with a median Dice coefficient of 0.81, AUC of 0.91, sensitivity of 81%, and precision of 84%. Automatic segmentation of SAH blood was most reliable near the base of the brain with a median Dice coefficient of 0.51, an AUC of 0.75, precision of 68%, and sensitivity of 50%. Ultimately, we developed a rule-based method that is easily adaptable through user feedback, generates spatially normalized segmentations that are comparable regardless of brain morphology or acquisition conditions, and automatically segments LV with good overall reliability and basal SAH blood with good precision. Our approach could benefit longitudinal studies in patients with SAH by streamlining assessment of edema and hydrocephalus progression, as well as blood resorption.

T1 /T2 ratio from 3T MRI improves multiple sclerosis cortical lesion contrast

BACKGROUND AND PURPOSE

Cortical demyelinated lesions are prevalent in multiple sclerosis (MS), associated with disability, and have recently been incorporated into MS diagnostic criteria. Presently, advanced and ultrahigh-field MRIs-not routinely available in clinical practice-are the most sensitive methods for detection of cortical lesions. Approaches utilizing MRI sequences obtainable in routine clinical practice remain an unmet need. We plan to assess the sensitivity of the ratio of T1 -weighted and T2 -weighted (T1 /T2 ) signal intensity for focal cortical lesions in comparison to other high-field imaging methods.

METHODS

3-Tesla and 7-Tesla MRI collected from 10 adults with MS were included in the study. T1 /T2 images were calculated by dividing 3T T1 -weighted (T1 w) images by 3T T2 -weighted (T2 w) fluid-attenuated inversion recovery images for each participant. A total of 614 cortical lesions were identified using 7T T2 *w and T1 w images and corresponding voxels were assessed on registered 3T images. Signal intensities were compared across 3T imaging sequences, including T1 /T2 , T1 w, T2 w, and inversion recovery susceptibility-weighted imaging with enhanced T2 weighting (IR-SWIET) images.

RESULTS

T1 /T2 images demonstrated a larger contrast between median lesional and nonlesional cortical signal intensity (median ratio = 1.29, range: 1.19-1.38) when compared to T1 w (1.01, 0.97-1.10, p < .002), T2 w (1.17, 1.07-1.26, p < .002), and IR-SWIET (1.21, 1.01-1.29, p < .03).

CONCLUSION

T1 /T2 images are sensitive to cortical lesions. Approaches incorporating T1 /T2 could improve the accessibility of cortical lesion detection in research settings and clinical practice.

Lessons learned: A neuroimaging research center's transition to open and reproducible science

Human functional neuroimaging has evolved dramatically in recent years, driven by increased technical complexity and emerging evidence that functional neuroimaging findings are not generally reproducible. In response to these trends, neuroimaging scientists have developed principles, practices, and tools to both manage this complexity as well as to enhance the rigor and reproducibility of neuroimaging science. We group these best practices under four categories: experiment pre-registration, FAIR data principles, reproducible neuroimaging analyses, and open science. While there is growing recognition of the need to implement these best practices there exists little practical guidance of how to accomplish this goal. In this work, we describe lessons learned from efforts to adopt these best practices within the Brain Imaging Research Center at the University of Arkansas for Medical Sciences over 4 years (July 2018-May 2022). We provide a brief summary of the four categories of best practices. We then describe our center's scientific workflow (from hypothesis formulation to result reporting) and detail how each element of this workflow maps onto these four categories. We also provide specific examples of practices or tools that support this mapping process. Finally, we offer a roadmap for the stepwise adoption of these practices, providing recommendations of why and what to do as well as a summary of cost-benefit tradeoffs for each step of the transition.

Earth Mover’s Distance-Based Tool for Rapid Screening of Cervical Cancer Using Cervigrams

Cervical cancer is a major public health challenge that can be cured with early diagnosis and timely treatment. This challenge formed the rationale behind our design and development of an intelligent and robust image analysis and diagnostic tool/scale, namely “OM—The OncoMeter”, for which we used R (version-3.6.3) and Linux (Ubuntu-20.04) to tag and triage patients in order of their disease severity. The socio-demographic profiles and cervigrams of 398 patients evaluated at OPDs of Batra Hospital & Medical Research Centre, New Delhi, India, and Delhi State Cancer Institute (East), New Delhi, India, were acquired during the course of this study. Tested on 398 India-specific women’s cervigrams, the scale yielded significant achievements, with 80.15% accuracy, a sensitivity of 84.79%, and a specificity of 66.66%. The statistical analysis of sociodemographic profiles showed significant associations of age, education, annual income, occupation, and menstrual health with the health of the cervix, where a p-value less than (<) 0.05 was considered statistically significant. The deployment of cervical cancer screening tools such as “OM—The OncoMeter” in live clinical settings of resource-limited healthcare infrastructure will facilitate early diagnosis in a non-invasive manner, leading to a timely clinical intervention for infected patients upon detection even during primary healthcare (PHC).

Nursing Analysis Based on Medical Imaging Technology before and after Coronary Angiography in Cardiovascular Medicine

With the advancement of technology, medical imaging technology has been greatly improved. This article mainly studies the nursing before and after coronary angiography in cardiovascular medicine based on medical imaging technology. This paper proposes a multimodal medical image fusion algorithm based on multiscale decomposition and convolution sparse representation. The algorithm first decomposes the preregistered source medical image by NSST, takes the subimages of different scales as training images, and optimizes the subdictionaries of different scales; then convolution and sparse the subimages on each scale encoding to obtain the sparse coefficients of different subimages; secondly, the combination of improved L1 norm and improved spatial frequency (novel sum-modified SF (NMSF)) is used for high-frequency subimage coefficients, and the fusion of low-frequency subimages improved the rule of combining the L1 norm and the regional energy; finally, the final fused image is obtained by inverse NSST of the fused low-frequency subband and high-frequency subband. Experimental analysis found that the bifurcation angle has nothing to do with the damage of the branch vessels after the main branch stent is placed. The bifurcation angle greater than 50° is an independent predictor of MACE after stent extrusion for bifurcation lesions. Experimental results show that the proposed method has good performance in contrast enhancement, detail extraction, and information retention, and it improves the quality of the fusion image.

Harmonisation of scanner-dependent contrast variations in magnetic resonance imaging for radiation oncology, using style-blind auto-encoders

Background and purpose

Magnetic Resonance Imaging (MRI) exhibits scanner dependent contrast, which limits generalisability of radiomics and machine-learning for radiation oncology. Current deep-learning harmonisation requires paired data, retraining for new scanners and often suffers from geometry-shift which alters anatomical information. The aim of this study was to investigate style-blind auto-encoders for MRI harmonisation to accommodate unpaired training data, avoid geometry-shift and harmonise data from previously unseen scanners.

Materials and methods

A style-blind auto-encoder, using adversarial classification on the latent-space, was designed for MRI harmonisation. The public CC359 T1-w MRI brain dataset includes six scanners (three manufacturers, two field strengths), of which five were used for training. MRI from all six (including one unseen) scanner were harmonised to common contrast. Harmonisation extent was quantified via Kolmogorov-Smirnov testing of residual scanner dependence of 3D radiomic features, and compared to WhiteStripe normalisation. Anatomical content preservation was measured through change in structural similarity index on contrast-cycling (δSSIM).

Results

The percentage of radiomics features showing statistically significant scanner-dependence was reduced from 41% (WhiteStripe) to 16% for white matter and from 39% to 27% for grey matter. δSSIM < 0.0025 on harmonisation and de-harmonisation indicated excellent anatomical content preservation.

Conclusions

Our method harmonised MRI contrast effectively, preserved critical anatomical details at high fidelity, trained on unpaired data and allowed zero-shot harmonisation. Robust and clinically translatable harmonisation of MRI will enable generalisable radiomic and deep-learning models for a range of applications, including radiation oncology treatment stratification, planning and response monitoring.

Can Open Science be a Tool to Dismantle Claims of Hardwired Brain Sex Differences? Opportunities and Challenges for Feminist Researchers

Feminist scholars have long been concerned with claims of hardwired brain sex differences emanating from neuroscience and evolutionary psychology. Past criticisms of these claims have rightfully questioned the impact of this research on gender equality, pointing out how findings can be used to vindicate gender stereotypes. In this article, we appraise the brain sex differences literature through the lens of open science, a movement aimed at improving the robustness and reliability of science. In this discussion, we offer a feminist evaluation of the strategies (e.g., pre-registration, data sharing, and accountability) provided by open science, and we question whether these may be the novel and disruptive tools needed to dismantle claims about hardwired brain sex differences. We suggest that open science strategies can be useful in challenging some of these claims, and we note that promising initiatives are already being developed in neuroscience and allied fields. We end by acknowledging the distinct challenges that feminist researchers wishing to engage in open science face, particularly in the context of limited diversity. We conclude that open science presents considerable opportunity for feminist researchers, and that it will be crucial for feminists to be involved in shaping the future of this movement.

Radiomics complements clinical, radiological, and technical features to assess local control of colorectal cancer lung metastases treated with radiofrequency ablation

OBJECTIVES

Radiofrequency ablation (RFA) of lung metastases of colorectal origin can improve patient survival and quality of life. Our aim was to identify pre- and per-RFA features predicting local control of lung metastases following RFA.

METHODS

This case-control single-center retrospective study included 119 lung metastases treated with RFA in 48 patients (median age: 60 years). Clinical, technical, and radiological data before and on early CT scan (at 48 h) were retrieved. After CT scan preprocessing, 64 radiomics features were extracted from pre-RFA and early control CT scans. Log-rank tests were used to detect categorical variables correlating with post-RFA local tumor progression-free survival (LTPFS). Radiomics prognostic scores (RPS) were developed on reproducible radiomics features using Monte-Carlo cross-validated LASSO Cox regressions.

RESULTS

Twenty-six of 119 (21.8%) nodules demonstrated local progression (median delay: 11.2 months). In univariate analysis, four non-radiomics variables correlated with post-RFA-LTPFS: nodule size (> 15 mm, p < 0.001), chosen electrode (with difference between covered array and nodule diameter < 20 mm or non-expandable electrode, p = 0.03), per-RFA intra-alveolar hemorrhage (IAH, p = 0.002), and nodule location into the ablation zone (not seen or in contact with borders, p = 0.005). The highest prognostic performance was reached with the multivariate model including a RPS built on 4 radiomics features from pre-RFA and early revaluation CT scans (cross-validated concordance index= 0.74) in which this RPS remained an independent predictor (cross-validated HR = 3.49, 95% confidence interval = [1.76 - 6.96]).

CONCLUSIONS

Technical, radiological, and radiomics features of the lung metastases before RFA and of the ablation zone at 48 h can help discriminate nodules at risk of local progression that could benefit from complementary local procedure.

KEY POINTS

• The highest prognostic performance to predict post-RFA LTPFS was reached with a parsimonious model including a radiomics score built with 4 radiomics features. • Nodule size, difference between electrode diameter, use of non-expandable electrode, per-RFA hemorrhage, and a tumor not seen or in contact with the ablation zone borders at 48-h CT were correlated with post-RFA LTPFS.

The ANTsX ecosystem for quantitative biological and medical imaging

The Advanced Normalizations Tools ecosystem, known as ANTsX, consists of multiple open-source software libraries which house top-performing algorithms used worldwide by scientific and research communities for processing and analyzing biological and medical imaging data. The base software library, ANTs, is built upon, and contributes to, the NIH-sponsored Insight Toolkit. Founded in 2008 with the highly regarded Symmetric Normalization image registration framework, the ANTs library has since grown to include additional functionality. Recent enhancements include statistical, visualization, and deep learning capabilities through interfacing with both the R statistical project (ANTsR) and Python (ANTsPy). Additionally, the corresponding deep learning extensions ANTsRNet and ANTsPyNet (built on the popular TensorFlow/Keras libraries) contain several popular network architectures and trained models for specific applications. One such comprehensive application is a deep learning analog for generating cortical thickness data from structural T1-weighted brain MRI, both cross-sectionally and longitudinally. These pipelines significantly improve computational efficiency and provide comparable-to-superior accuracy over multiple criteria relative to the existing ANTs workflows and simultaneously illustrate the importance of the comprehensive ANTsX approach as a framework for medical image analysis.

QDECR: A Flexible, Extensible Vertex-Wise Analysis Framework in R

The cerebral cortex is fundamental to the functioning of the mind and body. In vivo cortical morphology can be studied through magnetic resonance imaging in several ways, including reconstructing surface-based models of the cortex. However, existing software for surface-based statistical analyses cannot accommodate "big data" or commonly used statistical methods such as the imputation of missing data, extensive bias correction, and non-linear modeling. To address these shortcomings, we developed the QDECR package, a flexible and extensible R package for group-level statistical analysis of cortical morphology. QDECR was written with large population-based epidemiological studies in mind and was designed to fully utilize the extensive modeling options in R. QDECR currently supports vertex-wise linear regression. Design matrix generation can be done through simple, familiar R formula specification, and includes user-friendly extensions for R options such as polynomials, splines, interactions and other terms. QDECR can handle unimputed and imputed datasets with thousands of participants. QDECR has a modular design, and new statistical models can be implemented which utilize several aspects from other generic modules which comprise QDECR. In summary, QDECR provides a framework for vertex-wise surface-based analyses that enables flexible statistical modeling and features commonly used in population-based and clinical studies, which have until now been largely absent from neuroimaging research.

Orchestrating privacy-protected big data analyses of data from different resources with R and DataSHIELD

Combined analysis of multiple, large datasets is a common objective in the health- and biosciences. Existing methods tend to require researchers to physically bring data together in one place or follow an analysis plan and share results. Developed over the last 10 years, the DataSHIELD platform is a collection of R packages that reduce the challenges of these methods. These include ethico-legal constraints which limit researchers' ability to physically bring data together and the analytical inflexibility associated with conventional approaches to sharing results. The key feature of DataSHIELD is that data from research studies stay on a server at each of the institutions that are responsible for the data. Each institution has control over who can access their data. The platform allows an analyst to pass commands to each server and the analyst receives results that do not disclose the individual-level data of any study participants. DataSHIELD uses Opal which is a data integration system used by epidemiological studies and developed by the OBiBa open source project in the domain of bioinformatics. However, until now the analysis of big data with DataSHIELD has been limited by the storage formats available in Opal and the analysis capabilities available in the DataSHIELD R packages. We present a new architecture ("resources") for DataSHIELD and Opal to allow large, complex datasets to be used at their original location, in their original format and with external computing facilities. We provide some real big data analysis examples in genomics and geospatial projects. For genomic data analyses, we also illustrate how to extend the resources concept to address specific big data infrastructures such as GA4GH or EGA, and make use of shell commands. Our new infrastructure will help researchers to perform data analyses in a privacy-protected way from existing data sharing initiatives or projects. To help researchers use this framework, we describe selected packages and present an online book (https://isglobal-brge.github.io/resource_bookdown).

Assessment of Repeatability, Reproducibility, and Performances of T2 Mapping-Based Radiomics Features: A Comparative Study

BACKGROUND

Magnetic resonance imaging (MRI)-based radiomics features (RFs) quantify tumors radiological phenotypes but are sensitive to postprocessing parameters, including the intensity harmonization technique (IHT), while mappings enable objective quantitative assessment.

PURPOSE

To investigate whether T2 mapping could improve repeatability, reproducibility, and performances of radiomics compared to conventional T2-weighted imaging (T2WI).

STUDY TYPE

Prospective.

SUBJECTS

Twenty-six healthy adults.

FIELD STRENGTH/SEQUENCE

Respiratory-trigged radial turbo spin echo (TSE) multiecho T2 mapping (prototype) and conventional TSE T2WI of the abdomen were acquired twice at 1.5 T.

ASSESSMENT

T2 maps were reconstructed using a two-parameter exponential fitting model. Volumes-of-interest (VOIs) were manually drawn in six tissues: liver, kidney, pancreas, muscle, bone, and spleen. After co-registration, conventional T2WIs were processed with two IHTs (standardization [std] and histogram-matching [HM]) resulting in four paired input image types: initial T2WI, T2WI_std , T2WI_HM , and T2-map. VOIs were propagated to extract 45 RFs from MRI-1 and MRI-2 of each image type (LIFEx, v5.10).

STATISTICAL TESTS

Influence of the input data type on RF values was evaluated with analysis of variance. RFs test-retest repeatability and reproducibility over multiple segmentations were evaluated with intra-class correlation coefficient (ICC). Correlations between k-means clusters and the six tissues depending on the RFs dataset were investigated with adjusted-Rand-index (ARI).

RESULTS

About 41 of 45 (91.1%) RFs were significantly influenced by the input image type (P values < 0.05), which was the most influential factor on repeatability of RFs (P-value < 0.05). Repeatability ICCs from T2-map displayed intermediate values between the initial T2WI (range: 0.407-0.736) and the T2WI_HM (range: 0.724-0.817). The number of RFs with interobserver and intraobserver reproducibility ICCs ≥ 0.90 was 37/45 (82.2%) for T2WI_HM , 33/45 (73.3%) for T2WI_std , 31/45 (68.9%) for T2 map, and 25/45 (55.6%) for the initial T2WI. T2 map provided the best tissue discrimination (ARI = 0.414 vs. 0.157 with T2WI_HM ).

DATA CONCLUSION

T2 mapping provided RFs with moderate to substantial repeatability and reproducibility ICCs, along with the most preserved discriminative information.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: 1.

Similarity-driven multi-view embeddings from high-dimensional biomedical data

Diverse, high-dimensional modalities collected in large cohorts present new opportunities for the formulation and testing of integrative scientific hypotheses. Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships to transform large scientific datasets into smaller, more well-powered and interpretable low-dimensional spaces. SiMLR contributes an objective function for identifying joint signal, regularization based on sparse matrices representing prior within-modality relationships and an implementation that permits application to joint reduction of large data matrices. We demonstrate that SiMLR outperforms closely related methods on supervised learning problems in simulation data, a multi-omics cancer survival prediction dataset and multiple modality neuroimaging datasets. Taken together, this collection of results shows that SiMLR may be applied to joint signal estimation from disparate modalities and may yield practically useful results in a variety of application domains.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Replicability, Repeatability, and Long-term Reproducibility of Cerebellar Morphometry

To identify robust and reproducible methods of cerebellar morphometry that can be used in future large-scale structural MRI studies, we investigated the replicability, repeatability, and long-term reproducibility of three fully automated software tools: FreeSurfer, CEREbellum Segmentation (CERES), and automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization (ACAPULCO). Replicability was defined as computational replicability, determined by comparing two analyses of the same high-resolution MRI data set performed with identical analysis software and computer hardware. Repeatability was determined by comparing the analyses of two MRI scans of the same participant taken during two independent MRI sessions on the same day for the Kirby-21 study. Long-term reproducibility was assessed by analyzing two MRI scans of the same participant in the longitudinal OASIS-2 study. We determined percent difference, the image intraclass correlation coefficient, the coefficient of variation, and the intraclass correlation coefficient between two analyses. Our results show that CERES and ACAPULCO use stochastic algorithms that result in surprisingly high differences between identical analyses for ACAPULCO and small differences for CERES. Changes between two consecutive scans from the Kirby-21 study were less than ± 5% in most cases for FreeSurfer and CERES (i.e., demonstrating high repeatability). As expected, long-term reproducibility was lower than repeatability for all software tools. In summary, CERES is an accurate, as demonstrated before, and reproducible tool for fully automated segmentation and parcellation of the cerebellum. We conclude with recommendations for the assessment of replicability, repeatability, and long-term reproducibility in future studies on cerebellar structure.

Visualization of Brain Statistics With R Packages ggseg and ggseg3d

There is an increased emphasis on visualizing neuroimaging results in more intuitive ways. Common statistical tools for dissemination of these results, such as bar charts, lack the spatial dimension that is inherent in neuroimaging data. Here we present two packages for the statistical software R that integrate this spatial component. The ggseg and ggseg3d packages visualize predefined brain segmentations as 2D polygons and 3D meshes, respectively. Both packages are integrated with other well-established R packages, which allows great flexibility. In this Tutorial, we describe the main data and functions in the ggseg and ggseg3d packages for visualization of brain atlases. The highlighted functions are able to display brain-segmentation plots in R. Further, the accompanying ggsegExtra package includes a wider collection of atlases and is intended for community-based efforts to develop additional compatible atlases for ggseg and ggseg3d. Overall, the ggseg packages facilitate parcellation-based visualizations in R, improve and facilitate the dissemination of results, and increase the efficiency of workflows.

Rxnat: An Open-Source R Package for XNAT-Based Repositories

The extensible neuroimaging archive toolkit (XNAT) is a common platform for storing and distributing neuroimaging data and is used by many key repositories of public neuroimaging data. Some examples include the Neuroimaging Informatics Tools and Resources Clearinghouse (NITRC, https://nitrc.org/), the ConnectomeDB for the Human Connectome Project (https://db.humanconnectome.org/), and XNAT Central (https://central.xnat.org/). We introduce Rxnat (https://github.com/adigherman/Rxnat), an open-source R package designed to interact with any XNAT-based repository. The program has similar capabilities with PyXNAT and XNATpy, which were developed for Python users. Rxnat was developed to address the increased popularity of R among neuroimaging researchers. The Rxnat package can query multiple XNAT repositories and download all or a specific subset of images for further processing. This provides a lingua franca for the large community of R analysts to interface with multiple XNAT-based publicly available neuroimaging repositories. The potential of Rxnat is illustrated using an example of neuroimaging data normalization from two neuroimaging repositories, NITRC and HCP.

Longitudinal Mapping of Cortical Thickness Measurements: An Alzheimer's Disease Neuroimaging Initiative-Based Evaluation Study

Longitudinal studies of development and disease in the human brain have motivated the acquisition of large neuroimaging data sets and the concomitant development of robust methodological and statistical tools for quantifying neurostructural changes. Longitudinal-specific strategies for acquisition and processing have potentially significant benefits including more consistent estimates of intra-subject measurements while retaining predictive power. Using the first phase of the Alzheimer's Disease Neuroimaging Initiative (ADNI-1) data, comprising over 600 subjects with multiple time points from baseline to 36 months, we evaluate the utility of longitudinal FreeSurfer and Advanced Normalization Tools (ANTs) surrogate thickness values in the context of a linear mixed-effects (LME) modeling strategy. Specifically, we estimate the residual variability and between-subject variability associated with each processing stream as it is known from the statistical literature that minimizing the former while simultaneously maximizing the latter leads to greater scientific interpretability in terms of tighter confidence intervals in calculated mean trends, smaller prediction intervals, and narrower confidence intervals for determining cross-sectional effects. This strategy is evaluated over the entire cortex, as defined by the Desikan-Killiany-Tourville labeling protocol, where comparisons are made with the cross-sectional and longitudinal FreeSurfer processing streams. Subsequent linear mixed effects modeling for identifying diagnostic groupings within the ADNI cohort is provided as supporting evidence for the utility of the proposed ANTs longitudinal framework which provides unbiased structural neuroimage processing and competitive to superior power for longitudinal structural change detection.

Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients

Intensity harmonization techniques (IHT) are mandatory to homogenize multicentric MRIs before any quantitative analysis because signal intensities (SI) do not have standardized units. Radiomics combine quantification of tumors' radiological phenotype with machine-learning to improve predictive models, such as metastastic-relapse-free survival (MFS) for sarcoma patients. We post-processed the initial T2-weighted-imaging of 70 sarcoma patients by using 5 IHTs and extracting 45 radiomics features (RFs), namely: classical standardization (IHT_std), standardization per adipose tissue SIs (IHT_fat), histogram-matching with a patient histogram (IHT_HM.1), with the average histogram of the population (IHT_HM.All) and plus ComBat method (IHT_HM.All.C), which provided 5 radiomics datasets in addition to the original radiomics dataset without IHT (No-IHT). We found that using IHTs significantly influenced all RFs values (p-values: < 0.0001-0.02). Unsupervised clustering performed on each radiomics dataset showed that only clusters from the No-IHT, IHT_std, IHT_HM.All, and IHTHM.All.C datasets significantly correlated with MFS in multivariate Cox models (p = 0.02, 0.007, 0.004 and 0.02, respectively). We built radiomics-based supervised models to predict metastatic relapse at 2-years with a training set of 50 patients. The models performances varied markedly depending on the IHT in the validation set (range of AUROC from 0.688 with IHT_std to 0.823 with IHT_HM.1). Hence, the use of intensity harmonization and the related technique should be carefully detailed in radiomics post-processing pipelines as it can profoundly affect the reproducibility of analyses.

Deep Volumetric Feature Encoding for Biomedical Images

Deep learning research has demonstrated the effectiveness of using pre-trained networks as feature encoders. The large majority of these networks are trained on 2D datasets with millions of samples and diverse classes of information. We demonstrate and evaluate approaches to transferring deep 2D feature spaces to 3D in order to take advantage of these and related resources in the biomedical domain. First, we show how VGG-19 activations can be mapped to a 3D variant of the network (VGG-19-3D). Second, using varied medical decathlon data, we provide a technique for training 3D networks to predict the encodings induced by 3D VGG-19. Lastly, we compare five different 3D networks (one of which is trained only on 3D MRI and another of which is not trained at all) across layers and patch sizes in terms of their ability to identify hippocampal landmark points in 3D MRI data that was not included in their training. We make observations about the performance, recommend different networks and layers and make them publicly available for further evaluation.

A Publicly Available, High Resolution, Unbiased CT Brain Template

Clinical imaging relies heavily on X-ray computed tomography (CT) scans for diagnosis and prognosis. Many research applications aim to perform population-level analyses, which require images to be put in the same space, usually defined by a population average, also known as a template. We present an open-source, publicly available, high-resolution CT template. With this template, we provide voxel-wise standard deviation and median images, a basic segmentation of the cerebrospinal fluid spaces, including the ventricles, and a coarse whole brain labeling. This template can be used for spatial normalization of CT scans and research applications, including deep learning. The template was created using an anatomically-unbiased template creation procedure, but is still limited by the population it was derived from, an open CT data set without demographic information. The template and derived images are available at https://github.com/muschellij2/high_res_ct_template.

Recommendations for Processing Head CT Data

Many research applications of neuroimaging use magnetic resonance imaging (MRI). As such, recommendations for image analysis and standardized imaging pipelines exist. Clinical imaging, however, relies heavily on X-ray computed tomography (CT) scans for diagnosis and prognosis. Currently, there is only one image processing pipeline for head CT, which focuses mainly on head CT data with lesions. We present tools and a complete pipeline for processing CT data, focusing on open-source solutions, that focus on head CT but are applicable to most CT analyses. We describe going from raw DICOM data to a spatially normalized brain within CT presenting a full example with code. Overall, we recommend anonymizing data with Clinical Trials Processor, converting DICOM data to NIfTI using dcm2niix, using BET for brain extraction, and registration using a publicly-available CT template for analysis.

Robust spatial extent inference with a semiparametric bootstrap joint inference procedure

Spatial extent inference (SEI) is widely used across neuroimaging modalities to adjust for multiple comparisons when studying brain-phenotype associations that inform our understanding of disease. Recent studies have shown that Gaussian random field (GRF)-based tools can have inflated family-wise error rates (FWERs). This has led to substantial controversy as to which processing choices are necessary to control the FWER using GRF-based SEI. The failure of GRF-based methods is due to unrealistic assumptions about the spatial covariance function of the imaging data. A permutation procedure is the most robust SEI tool because it estimates the spatial covariance function from the imaging data. However, the permutation procedure can fail because its assumption of exchangeability is violated in many imaging modalities. Here, we propose the (semi-) parametric bootstrap joint (PBJ; sPBJ) testing procedures that are designed for SEI of multilevel imaging data. The sPBJ procedure uses a robust estimate of the spatial covariance function, which yields consistent estimates of standard errors, even if the covariance model is misspecified. We use the methods to study the association between performance and executive functioning in a working memory functional magnetic resonance imaging study. The sPBJ has similar or greater power to the PBJ and permutation procedures while maintaining the nominal type 1 error rate in reasonable sample sizes. We provide an R package to perform inference using the PBJ and sPBJ procedures.

A dual modeling approach to automatic segmentation of cerebral T2 hyperintensities and T1 black holes in multiple sclerosis

BACKGROUND AND PURPOSE

Magnetic resonance imaging (MRI) is crucial for in vivo detection and characterization of white matter lesions (WML) in multiple sclerosis (MS). The most widely established MRI outcome measure is the volume of hyperintense lesions on T2-weighted images (T2L). Unfortunately, T2L are non-specific for the level of tissue destruction and show a weak relationship to clinical status. Interest in lesions that appear hypointense on T1-weighted images (T1L) ("black holes") has grown because T1L provide more specificity for axonal loss and a closer link to neurologic disability. The technical difficulty of T1L segmentation has led investigators to rely on time-consuming manual assessments prone to inter- and intra-rater variability. This study aims to develop an automatic T1L segmentation approach, adapted from a T2L segmentation algorithm.

MATERIALS AND METHODS

T1, T2, and fluid-attenuated inversion recovery (FLAIR) sequences were acquired from 40 MS subjects at 3 Tesla (3 T). T2L and T1L were manually segmented. A Method for Inter-Modal Segmentation Analysis (MIMoSA) was then employed.

RESULTS

Using cross-validation, MIMoSA proved to be robust for segmenting both T2L and T1L. For T2L, a Sørensen-Dice coefficient (DSC) of 0.66 and partial AUC (pAUC) up to 1% false positive rate of 0.70 were achieved. For T1L, 0.53 DSC and 0.64 pAUC were achieved. Manual and MIMoSA segmented volumes were correlated and resulted in 0.88 for T1L and 0.95 for T2L. The correlation between Expanded Disability Status Scale (EDSS) scores and manual versus automatic volumes were similar for T1L (0.32 manual vs. 0.34 MIMoSA), T2L (0.33 vs. 0.32), and the T1L/T2L ratio (0.33 vs 0.33).

CONCLUSIONS

Though originally designed to segment T2L, MIMoSA performs well for segmenting T1 black holes in patients with MS.

gganatogram: An R package for modular visualisation of anatograms and tissues based on ggplot2

Displaying data onto anatomical structures is a convenient technique to quickly observe tissue related information. However, drawing tissues is a complex task that requires both expertise in anatomy and the arts. While web based applications exist for displaying gene expression on anatograms, other non-genetic disciplines lack similar tools. Moreover, web based tools often lack the modularity associated with packages in programming languages, such as R. Here I present gganatogram, an R package used to plot modular species anatograms based on a combination of the graphical grammar of ggplot2 and the publicly available anatograms from the Expression Atlas. This combination allows for quick and easy, modular, and reproducible generation of anatograms. Using only one command and a data frame with tissue name, group, colour, and  value, this tool enables the user to visualise specific human and mouse tissues with desired colours, grouped by a variable, or displaying a desired value, such as gene-expression, pharmacokinetics, or bacterial load across selected tissues. gganatogram consists of 5 highly annotated organisms, male/female human/mouse, and a cell anatogram. It further consists of 24 other less annotated organisms from the animal and plant kingdom. I hope that this tool will be useful by the wider community in biological sciences. Community members are welcome to submit additional anatograms, which can be incorporated into the package. A stable version gganatogram has been deposited to neuroconductor, and a development version can be found on  github/jespermaag/gganatogram. An interactive shiny app of gganatogram can be found on  https://jespermaag.shinyapps.io/gganatogram/, which allows for non-R users to create anatograms.

gganatogram: An R package for modular visualisation of anatograms and tissues based on ggplot2

Displaying data onto anatomical structures is a convenient technique to quickly observe tissue related information. However, drawing tissues is a complex task that requires both expertise in anatomy and the arts. While web based applications exist for displaying gene expression on anatograms, other non-genetic disciplines lack similar tools. Moreover, web based tools often lack the modularity associated with packages in programming languages, such as R.

Here I present gganatogram, an R package used to plot modular species anatograms based on a combination of the graphical grammar of ggplot2 and the publicly available anatograms from the Expression Atlas. This combination allows for quick and easy, modular, and reproducible generation of anatograms. Using only one command and a data frame with tissue name, group, colour, and  value, this tool enables the user to visualise specific human and mouse tissues with desired colours, grouped by a variable, or displaying a desired value, such as gene-expression, pharmacokinetics, or bacterial load across selected tissues. gganatogram consists of 5 highly annotated organisms, male/female human/mouse, and a cell anatogram. It further consists of 24 other less annotated organisms from the animal and plant kingdom. I hope that this tool will be useful by the wider community in biological sciences. Community members are welcome to submit additional anatograms, which can be incorporated into the package.

A stable version gganatogram has been deposited to neuroconductor, and a development version can be found on  github/jespermaag/gganatogram. An interactive shiny app of gganatogram can be found on  https://jespermaag.shinyapps.io/gganatogram/, which allows for non-R users to create anatograms.

A practical guide to big data

Big Data is increasingly prevalent in science and data analysis. We provide a short tutorial for adapting to these changes and making the necessary adjustments to the academic culture to keep Biostatistics truly impactful in scientific research.