Advanced Normalization Tools Research Articles

Comparison of Diffusion-weighted MRI using Singe-Shot Echo-planar Imaging (SS-EPI) and Split Acquisition of Fast Spin Echo Signal (SPLICE) Imaging, a non-EPI technique, in Tumors of the Head and Neck.

Diffusion-weighted imaging (DWI) using single-shot echo planar imaging (DW-EPI) is susceptible to distortions around air-filled cavities and dental fillings, typical for the head and neck area. Non-EPI, Split acquisition of fast spin echo signals for diffusion imaging (DWSPLICE) could reduce these distortions and enhance image quality, thereby potentially improving recurrence assessment in squamous cell carcinoma (SCC) of the head and neck region. This study evaluated whether DW-SPLICE is a viable alternative to DW-EPI through quantitative and qualitative analyses. The DW-SPLICE sequence was incorporated into the standard 3.0T head and neck MRI protocol with DW-EPI. Retrospective analysis was conducted on two subgroups: firstly benign or malignant lesions, and secondly post-treatment SCC recurrence. In both subgroups Image quality and distortion were scored by two independent radiologists, blinded for DW-technique, and evaluated using mixed-effect linear models. Lesion apparent diffusion coefficient (ADC) values were assessed with inter-class correlation (ICC) and Bland-Altman analyses. DWI's delineation geometric similarity to T1-weighted post-contrast (T1Wc) MRI was evaluated using the Dice Similarity Coefficient (DSC) before and after registration. Recurrence in post-treatment SCC scans was evaluated by the same two radiologists blinded for DW-technique. Recurrence detection rates were then compared between DW-SPLICE and DW-EPI using mixed logistic regression at six months and at one-year post-scan follow-up data. From August 2020 to January 2022, 55 benign or malignant lesion scans (55 patients) and 74 post-treatment SCC scans (66 patients) were analyzed. DW-SPLICE scored better on image quality and showed less overall distortion than DW-EPI (0.04<p<0.001). There was high ADC measurement reliability (ICC=0.93, p<0.001), though a proportional bias was also observed (β=0.11, p=0.03), indicating the bias increases as ADC values rise. DWSPLICE exhibited greater geometric similarity to T1Wc before registration (DSC 0.63 vs 0.47, p<0.001) and outperformed DW-EPI by more accurately identifying recurrences after one year (OR=0.96, p=0.05) but not after six months (OR=0.72, p=0.13). DW-SPLICE surpasses DW-EPI on image distortion and quality and improves diagnostic reliability for detecting recurrent or residual SCC on 3T MRI of the HN. Consistent use of one method for follow-up is advised, as ADC values are not completely interchangeable. Integrating DW-SPLICE can significantly improve tumor assessments in clinical practice. ANTs = Advanced Normalization Tools; DSC = Dice Similarity Coefficient; DW-EPI = Diffusion-weighted single-shot echo planar imaging; DW-MS-EPI = Diffusion-weighted multi-shot echo planar imaging; DW-SPLICE = Diffusion-weighted split acquisition of fast spin echo signals for diffusion imaging; DW-TSE = Diffusion-weighted Turbo Spin Echo; ICC = Intraclass Correlation Coefficient; ROC = Receiver Operating Characteristic; SCC = Squamous cell carcinoma; T1WIc = T1 weighted imaging with gadolinium contrast.

Whole-brain mapping in adult zebrafish and identification of a novel tank test functional connectome.

Identifying general principles of brain function requires the study of structure-function relationships in a variety of species. Zebrafish have recently gained prominence as a model organism in neuroscience, yielding important insights into vertebrate brain function. Although methods have been developed for mapping neural activity in larval animals, we lack similar techniques for adult zebrafish that have the advantage of a fully developed neuroanatomy and larger behavioral repertoire. Here, we describe a pipeline built around open-source tools for whole-brain activity mapping in freely swimming adult zebrafish. Our pipeline combines recent advances in histology, microscopy, and machine learning to capture cfos activity across the entirety of the adult brain. Images captured using light-sheet microscopy are registered to the recently created adult zebrafish brain atlas (AZBA) for automated segmentation using advanced normalization tools (ANTs). We used our pipeline to measure brain activity after zebrafish were subject to the novel tank test. We found that cfos levels peaked 15 minutes following behavior and that several regions containing serotoninergic, dopaminergic, noradrenergic, and cholinergic neurons were active during exploration. Finally, we generated a novel tank test functional connectome. Functional network analysis revealed that several regions of the medial ventral telencephalon form a cohesive sub-network during exploration. We also found that the anterior portion of the parvocellular preoptic nucleus (PPa) serves as a key connection between the ventral telencephalon and many other parts of the brain. Taken together, our work enables whole-brain activity mapping in adult zebrafish for the first time while providing insight into neural basis for the novel tank test.

Morphological simulation tests the limits on phenotype discovery in 3D image analysis.

In the past few decades, advances in 3D imaging have created new opportunities for reverse genetic screens. Rapidly growing datasets of 3D images of genetic knockouts require high-throughput, automated computational approaches for identifying and characterizing new phenotypes. However, exploratory, discovery-oriented image analysis pipelines used to discover these phenotypes can be difficult to validate because, by their nature, the expected outcome is not known a priori . Introducing known morphological variation through simulation can help distinguish between real phenotypic differences and random variation; elucidate the effects of sample size; and test the sensitivity and reproducibility of morphometric analyses. Here we present a novel approach for 3D morphological simulation that uses open-source, open-access tools available in 3D Slicer, SlicerMorph, and Advanced Normalization Tools in R (ANTsR). While we focus on diffusible-iodine contrast-enhanced micro-CT (diceCT) images, this approach can be used on any volumetric image. We then use our simulated datasets to test whether tensor-based morphometry (TBM) can recover our introduced differences; to test how effect size and sample size affect detectability; and to determine the reproducibility of our results. In our approach to morphological simulation, we first generate a simulated deformation based on a reference image and then propagate this deformation to subjects using inverse transforms obtained from the registration of subjects to the reference. This produces a new dataset with a shifted population mean while retaining individual variability because each sample deforms more or less based on how different or similar it is from the reference. TBM is a widely-used technique that statistically compares local volume differences associated with local deformations. Our results showed that TBM recovered our introduced morphological differences, but that detectability was dependent on the effect size, the sample size, and the region of interest (ROI) included in the analysis. Detectability of subtle phenotypes can be improved both by increasing the sample size and by limiting analyses to specific body regions. However, it is not always feasible to increase sample sizes in screens of essential genes. Therefore, methodical use of ROIs is a promising way to increase the power of TBM to detect subtle phenotypes. Generating known morphological variation through simulation has broad applicability in developmental, evolutionary, and biomedical morphometrics and is a useful way to distinguish between a failure to detect morphological difference and a true lack of morphological difference. Morphological simulation can also be applied to AI-based supervised learning to augment datasets and overcome dataset limitations.

ANTsX neuroimaging-derived structural phenotypes of UK Biobank

UK Biobank is a large-scale epidemiological resource for investigating prospective correlations between various lifestyle, environmental, and genetic factors with health and disease progression. In addition to individual subject information obtained through surveys and physical examinations, a comprehensive neuroimaging battery consisting of multiple modalities provides imaging-derived phenotypes (IDPs) that can serve as biomarkers in neuroscience research. In this study, we augment the existing set of UK Biobank neuroimaging structural IDPs, obtained from well-established software libraries such as FSL and FreeSurfer, with related measurements acquired through the Advanced Normalization Tools Ecosystem. This includes previously established cortical and subcortical measurements defined, in part, based on the Desikan-Killiany-Tourville atlas. Also included are morphological measurements from two recent developments: medial temporal lobe parcellation of hippocampal and extra-hippocampal regions in addition to cerebellum parcellation and thickness based on the Schmahmann anatomical labeling. Through predictive modeling, we assess the clinical utility of these IDP measurements, individually and in combination, using commonly studied phenotypic correlates including age, fluid intelligence, numeric memory, and several other sociodemographic variables. The predictive accuracy of these IDP-based models, in terms of root-mean-squared-error or area-under-the-curve for continuous and categorical variables, respectively, provides comparative insights between software libraries as well as potential clinical interpretability. Results demonstrate varied performance between package-based IDP sets and their combination, emphasizing the need for careful consideration in their selection and utilization.

Association between cortical thickness and cognitive ability in very preterm school-age children

Very preterm children, born before 32 weeks of gestation, are at risk for impaired cognitive function, mediated by several risk factors. Cognitive impairment can be measured by various neurodevelopmental assessments and is closely associated with structural alterations of brain morphometry, such as cortical thickness. However, the association between structural alterations and high-order cognitive function remains unclear. This study aimed to investigate the neurodevelopmental associations between brain structural changes and cognitive abilities in very preterm and full-term children. Cortical thickness was assessed in 37 very preterm and 24 full-term children aged 6 years. Cortical thickness analysis of structural T1-weighted images was performed using Advanced Normalization Tools. Associations between cortical thickness and the Wechsler Intelligence Scale for Children were evaluated by regression analysis based on ordinary least square estimation. Compared with full-term children, very preterm children showed significant differences in cortical thickness, variously associated with cognitive abilities in several brain regions. Perceptual reasoning indices were broadly correlated with cortical thickness in very preterm and full-term children. These findings provide important insights into neurodevelopment and its association with cortical thickness, which may serve as a biomarker in predictive models for neurodevelopmental diagnosis of high-order cognitive function.

Specific-CT brain template construction and retrospective dosimetric comparison study in brain for nasopharyngeal carcinoma patients treated with IMRT or VMAT.

The current Radiotherapy (RT) technology still inevitably irradiated normal brain tissue, causing implicit radiation-induced injury. This study investigates the precise localization and the corresponding radiation dosage of brain regions susceptible to damage in nasopharyngeal carcinoma (NPC) patients following RT. Utilizing the Advanced Normalization Tools (ANTs) package, a computed tomography (CT) brain template was created in the standard Montreal Neurological Institute (MNI) space, based on 803 Chinese NPC patients (T0~T4) who underwent RT. With this template, all patients' CT and RTdose data were registered to the MNI space, and the RTdose distribution characteristics in normal brain tissues were compared for NPC patients treated with Intensity-modulated radiotherapy (IMRT) or Volumetric Modulated Arc Therapy (VMAT), with patients' age and gender as covariates. Analysis of the average dosages indicated that certain areas within the Limbic, Temporal, and Posterior Lobes, the Brainstem, and the Cerebellum Posterior Lobe were exposed to doses exceeding 50 Gy. Inter-group analysis revealed that IMRT delivered higher doses than VMAT to brain regions anterior to the nasopharyngeal tumor, whereas VMAT affected the posterior regions more. Interestingly, VMAT showed a drawback in preserving the normal brain tissues for T4-stage patients. This revealed that the two treatment modalities have unique characteristics in preserving normal brain tissue, each with advantages. With better localization precision, the created CT brain template in MNI space may be beneficial for NPC patients' toxicity and dosimetric analyses.

The Pattern of Hippocampus and Entorhinal Cortex Subregion Atrophy in Early Alzheimer’s Disease

AbstractBackgroundAtrophy of the hippocampus and entorhinal cortex (EC) develops early in Alzheimer’s disease (AD). The nature of atrophy along the anterior‐posterior longitudinal axis of the hippocampus and EC in individuals with amnestic mild cognitive impairment (aMCI) with positive AD biomarkers (AD aMCI) has been less researched. We aimed to reveal a possible different pattern of atrophy in longitudinal axis of the hippocampus and EC between AD aMCI individuals and those with AD biomarker negative aMCI (non‐AD aMCI).MethodIn total, 100 older adults with AD aMCI (n = 26), non‐AD aMCI (n = 23), mild AD dementia (n = 22) and cognitively normal (CN; n = 29) from the Czech Brain Aging Study (CBAS) underwent clinical and cognitive testing, and brain MRI with the 3‐dimensional T1‐weighted high‐resolution magnetization‐prepared rapid gradient echo sequences. An automated processing pipeline using the Advanced Normalization Tools based on the CBAS population template and a manual segmentation protocol were used to measure left and right subregional hippocampus and EC volumes including hippocampus head (HH), body (HB) and tail (HT), and anterolateral (alEC) and posteromedial (pmEC) entorhinal cortex volumes, respectively. Volumes were normalized to estimated total intracranial volume.ResultCompared to the CN group, the AD aMCI group had lower subregional hippocampus and EC volumes (p&lt;0.05) except for right and left HH volumes. Compared to the non‐AD aMCI group, the AD aMCI group had lower right HB (p&lt;0.05), right and left HT (p&lt;0.01), right alEC (p&lt;0.05), and right (p&lt;0.01) and left (p&lt;0.05) pmEC volumes. The mild AD dementia group had lower all subregional hippocampus and EC volumes compared to the CN group (p&lt;0.05).ConclusionThese results are in line with previous research that demonstrated atrophy of the hippocampus and EC in early AD and indicate that atrophy of the posterior hippocampus and EC subregions may reflect AD pathology in aMCI individuals. Volumetric differences along the anterior‐posterior axis of the hippocampus and EC could serve as a potential biomarker to identify the underlying pathology in different neurodegenerative diseases.

NIMG-01. AI-BASED ASSESSMENT OF BRAIN VOLUME DECREASE AFTER SRS AND WBRT

Abstract BACKGROUND Stereotactic radiosurgery (SRS) for 4-10 brain metastases has been shown to be associated with prolonged survival as compared to whole brain radiotherapy (WBRT). Brain volume decrease after WBRT is a marker for poor survival. We aimed at comparing brain volume decrease in patients treated with either SRS or WBRT. METHODS Patients treated with SRS were drawn from the prospective dataset of the STEREOBRAIN study (DRKS00014694) that recruited from 2017 to 2020. Patients that received WBRT for 4-10 brain metastases were included retrospectively from 2012 - 2017. Images were registered to the MNI305 space utilizing the Advanced Normalization Tools (ANTs) Toolkit. Brain extraction was performed using the deep-learning based HD-BET UNet. Anatomical brain structures were labelled by employing the current state-of-the-art pretrained transformer based UNesT network using the MONAI deep-learning framework. Labels were bundled and analysed. Last pre-radiotherapy scans were compared with the last post-radiotherapy scans. The proportion of the ventricular system to the total intracranial volume was implemented as a measure of brain volume decrease. RESULTS Overall, 65 patients were included. 29 patients (45%) received SRS and 36 patients (55%) were treated with WBRT. Patients treated with SRS showed no significant increase in the volume of the ventricular system compared to the total intracranial volume (p= 0.13), whereas patients in the WBRT cohort did (p&amp;lt; 0.01). The mean relative volume increase of the ventricular system was 33% in the SRS cohort. In the WBRT cohort, the mean increase was 54%. The median time between the two scans was 414 days in the SRS cohort and 244 days in the WBRT cohort. CONCLUSION Brain volume decrease is less extensive in patients treated with SRS than WBRT. The clinical implication of this finding, e.g., prolonged survival and better clinical status, is yet to be determined and quantified.

Exploring the performance of implicit neural representations for brain image registration

Pairwise image registration is a necessary prerequisite for brain image comparison and data integration in neuroscience and radiology. In this work, we explore the efficacy of implicit neural representations (INRs) in improving the performance of brain image registration in magnetic resonance imaging. In this setting, INRs serve as a continuous and coordinate based approximation of the deformation field obtained through a multi-layer perceptron. Previous research has demonstrated that sinusoidal representation networks (SIRENs) surpass ReLU models in performance. In this study, we first broaden the range of activation functions to further investigate the registration performance of implicit networks equipped with activation functions that exhibit diverse oscillatory properties. Specifically, in addition to the SIRENs and ReLU, we evaluate activation functions based on snake, sine+, chirp and Morlet wavelet functions. Second, we conduct experiments to relate the hyper-parameters of the models to registration performance. Third, we propose and assess various techniques, including cycle consistency loss, ensembles and cascades of implicit networks, as well as a combined image fusion and registration objective, to enhance the performance of implicit registration networks beyond the standard approach. The investigated implicit methods are compared to the VoxelMorph convolutional neural network and to the symmetric image normalization (SyN) registration algorithm from the Advanced Normalization Tools (ANTs). Our findings not only highlight the remarkable capabilities of implicit networks in addressing pairwise image registration challenges, but also showcase their potential as a powerful and versatile off-the-shelf tool in the fields of neuroscience and radiology.

Comparative analysis of alignment algorithms for macular optical coherence tomography imaging

BackgroundOptical coherence tomography (OCT) is the most important and commonly utilized imaging modality in ophthalmology and is especially crucial for the diagnosis and management of macular diseases. Each OCT volume is typically only available as a series of cross-sectional images (B-scans) that are accessible through proprietary software programs which accompany the OCT machines. To maximize the potential of OCT imaging for machine learning purposes, each OCT image should be analyzed en bloc as a 3D volume, which requires aligning all the cross-sectional images within a particular volume.MethodsA dataset of OCT B-scans obtained from 48 age-related macular degeneration (AMD) patients and 50 normal controls was used to evaluate five registration algorithms. After alignment of B-scans from each patient, an en face surface map was created to measure the registration quality, based on an automatically generated Laplace difference of the surface map–the smoother the surface map, the smaller the average Laplace difference. To demonstrate the usefulness of B-scan alignment, we trained a 3D convolutional neural network (CNN) to detect age-related macular degeneration (AMD) on OCT images and compared the performance of the model with and without B-scan alignment.ResultsThe mean Laplace difference of the surface map before registration was 27 ± 4.2 pixels for the AMD group and 26.6 ± 4 pixels for the control group. After alignment, the smoothness of the surface map was improved, with a mean Laplace difference of 5.5 ± 2.7 pixels for Advanced Normalization Tools Symmetric image Normalization (ANTs-SyN) registration algorithm in the AMD group and a mean Laplace difference of 4.3 ± 1.4.2 pixels for ANTs in the control group. Our 3D CNN achieved superior performance in detecting AMD, when aligned OCT B-scans were used (AUC 0.95 aligned vs. 0.89 unaligned).ConclusionsWe introduced a novel metric to quantify OCT B-scan alignment and compared the effectiveness of five alignment algorithms. We confirmed that alignment could be improved in a statistically significant manner with readily available alignment algorithms that are available to the public, and the ANTs algorithm provided the most robust performance overall. We further demonstrated that alignment of OCT B-scans will likely be useful for training 3D CNN models.

The effect of processing pipelines, input images and age on automatic cortical morphology estimates

Background and ObjectiveMagnetic resonance imaging of the brain allows to enrich the study of the relationship between cortical morphology, healthy ageing, diseases and cognition. Since manual segmentation of the cerebral cortex is time consuming and subjective, many software packages have been developed. FreeSurfer (FS) and Advanced Normalization Tools (ANTs) are the most used and allow as inputs a T1-weighted (T1w) image or its combination with a T2-weighted (T2w) image. In this study we evaluated the impact of different software and input images on cortical estimates. Additionally, we investigated whether the variation of the results depending on software and inputs is also influenced by age. MethodsFor 240 healthy subjects, cortical thickness was computed with ANTs and FreeSurfer. Estimates were derived using both the T1w image and adding the T2w image. Significant effects due to software, input images and age range were investigated with ANOVA statistical analysis. Moreover, the accuracy of the cortical thickness estimates was assessed based on their age-prediction precision. ResultsUsing FreeSurfer and ANTs with T1w or T1w-T2w images resulted in significant differences in the cortical thickness estimates. These differences change with the age range of the subjects. Regardless of the images used, the more recent FS version tested exhibited the best performances in terms of age prediction. ConclusionsOur study points out the importance of i) consistently processing data using the same tool; ii) considering the software, input images and the age range of the subjects when comparing multiple studies.

Direct Occipital Remodeling in Sagittal Synostosis Improves 2-Year Posterior Morphology after Modified Pi Procedure.

Modifications of the pi craniectomy technique are meant to address the occipital bullet deformity of sagittal synostosis, but it is not clear whether they result in persistent improvement. The authors' purpose was to use morphometric analysis to determine whether a low occipital osteotomy with verticalization results in improved occipital shape after a modified pi procedure 2 years after surgery. The authors performed a retrospective cohort study comparing modified pi technique with and without a low occipital osteotomy with verticalization immediately and 2 years after surgery relative to age-matched normal controls. The authors used anthropometric measures and population-level anatomical templates using the multivariate template construction script from advanced normalization tools for comparison between groups. A subgroup analysis was performed for severe occipital bullet deformity at presentation. The authors observed stable improvement in the angle of the inferior occiput with the occipital remodeling modification that persisted 2 years after surgery. This improvement was seen in the entire cohort and was greater in the severe subgroup analysis. Complications and blood transfusion volumes were not different between the 2 techniques. The low occipital osteotomy group demonstrated improved posterior vertical height and cephalic index immediately after surgery, but these did not persist 2 years later. Occipital remodeling improves the bullet deformity but does not affect posterior vertical height 2 years after surgery. The authors recommend direct inferior occipital remodeling when using the pi technique for young patients with acute occipital incline angles and occipital constriction. Therapeutic, III.

An Anatomical Template for the Normalization of Medical Images of Adult Human Hands.

During medical image analysis, it is often useful to align (or 'normalize') a given image of a given body part to a representative standard (or 'template') of that body part. The impact that brain templates have had on the analysis of brain images highlights the importance of templates in general. However, templates for human hands do not exist. Image normalization is especially important for hand images because hands, by design, readily change shape during various tasks. Here we report the construction of an anatomical template for healthy adult human hands. To do this, we used 27 anatomically representative T1-weighted magnetic resonance (MR) images of either hand from 21 demographically representative healthy adult subjects (13 females and 8 males). We used the open-source, cross-platform ANTs (Advanced Normalization Tools) medical image analysis software framework, to preprocess the MR images. The template was constructed using the ANTs standard multivariate template construction workflow. The resulting template image preserved all the essential anatomical features of the hand, including all the individual bones, muscles, tendons, ligaments, as well as the main branches of the median nerve and radial, ulnar, and palmar metacarpal arteries. Furthermore, the image quality of the template was significantly higher than that of the underlying individual hand images as measured by two independent canonical metrics of image quality.

Remote effects of temporal lobe epilepsy surgery: Long-term morphological changes after surgical resection.

Epilepsy surgery is an effective treatment for drug-resistant patients. However, how different surgical approaches affect long-term brain structure remains poorly characterized. Here, we present a semiautomated method for quantifying structural changes after epilepsy surgery and compare the remote structural effects of two approaches, anterior temporal lobectomy (ATL), and selective amygdalohippocampectomy (SAH). We studied 36 temporal lobe epilepsy patients who underwent resective surgery (ATL = 22, SAH = 14). All patients received same-scanner MR imaging preoperatively and postoperatively (mean 2 years). To analyze postoperative structural changes, we segmented the resection zone and modified the Advanced Normalization Tools (ANTs) longitudinal cortical pipeline to account for resections. We compared global and regional annualized cortical thinning between surgical treatments. Across procedures, there was significant cortical thinning in the ipsilateral insula, fusiform, pericalcarine, and several temporal lobe regions outside the resection zone as well as the contralateral hippocampus. Additionally, increased postoperative cortical thickness was seen in the supramarginal gyrus. Patients treated with ATL exhibited greater annualized cortical thinning compared with SAH cases (ATL: -0.08 ± 0.11 mm per year, SAH: -0.01 ± 0.02 mm per year, t = 2.99, P = 0.006). There were focal postoperative differences between the two treatment groups in the ipsilateral insula (P = 0.039, corrected). Annualized cortical thinning rates correlated with preoperative cortical thickness (r = 0.60, P < 0.001) and had weaker associations with age at surgery (r = -0.33, P = 0.051) and disease duration (r = -0.42, P = 0.058). Our evidence suggests that selective procedures are associated with less cortical thinning and that earlier surgical intervention may reduce long-term impacts on brain structure.

Craniofacial Soft-Tissue Anthropomorphic Database with Magnetic Resonance Imaging and Unbiased Diffeomorphic Registration.

Objective assessment of craniofacial surgery outcomes in a pediatric population is challenging because of the complexity of patient presentations, diversity of procedures performed, and rapid craniofacial growth. There is a paucity of robust methods to quantify anatomical measurements by age and objectively compare craniofacial dysmorphology and postoperative outcomes. Here, the authors present data in developing a racially and ethnically sensitive anthropomorphic database, providing plastic and craniofacial surgeons with "normal" three-dimensional anatomical parameters with which to appraise and optimize aesthetic and reconstructive outcomes. Patients with normal craniofacial anatomy undergoing head magnetic resonance imaging (MRI) scans from 2008 to 2021 were included in this retrospective study. Images were used to construct composite (template) images with diffeomorphic image registration method using the Advanced Normalization Tools package. Composites were thresholded to generate binary three-dimensional segmentations used for anatomical measurements in Materalise Mimics. High-resolution MRI scans from 130 patients generated 12 composites from an average of 10 MRI sequences each: four 3-year-olds, four 4-year-olds, and four 5-year-olds (two male, two female, two Black, and two White). The average head circumference of 3-, 4-, and 5-year-old composites was 50.3, 51.5, and 51.7 cm, respectively, comparable to normative data published by the World Health Organization. Application of diffeomorphic registration-based image template algorithm to MRI is effective in creating composite templates to represent "normal" three-dimensional craniofacial and soft-tissue anatomy. Future research will focus on development of automated computational tools to characterize anatomical normality, generation of indices to grade preoperative severity, and quantification of postoperative results to reduce subjectivity bias.

Deep learning based registration for head motion correction in positron emission tomography as a strategy for improved image quantification

Objectives: Positron emission tomography (PET) is affected by various kinds of patient movement during a scan. Frame-by-frame image registration is one of the most practiced motion correction techniques. In recent years, deep learning has shown a remarkable ability to quickly and accurately register images once trained. This paper studies the feasibility of using a deep learning framework to correct 3D positron emission tomography image volumes for head motion in routine positron emission tomography imaging to improve quantification in motion impacted data.Materials and Methods: A neural network was trained with 3D positron emission tomography image volumes in an unsupervised manner to predict transformation parameters required to perform image registration. A multi-step convolutional neural network (CNN) was combined with a spatial transform layer. Pairs of target and source images were used as input to the network. To prepare the training dataset, a previously published TOF-PEPT algorithm was applied to automatically detect static frames where the patient remained in a relatively steady position and transitional frames where they underwent abrupt motion. A single image volume was reconstructed for each static frame. The image reconstructed from the first static frame served as the target image with images from subsequent static frames being used as source images. The trained neural network predicted transformation parameters that could be used to perform frame-by-frame image-based motion correction but also enabled raw listmode positron emission tomography data correction where individual line-of-responses were repositioned. Line profiles and ROIs were drawn across the reconstructed image volumes to compare performance and quantitative results between standard registration tools and the deep learning technique. Corrected volumes were further compared to motion free images quantitatively using Dice indices.Results: In total, one hundred 3D positron emission tomography image volumes were used to train the network. Cross-validation was carried out using a 4:1 ratio for the training and test data. A conventional algorithm for affine registration from the Advanced Normalization Tools (ANTs) software package served as a baseline. To evaluate the correction performance, the mean Dice index and standardized uptake value (SUV) were used. Application of the algorithm to clinical data showed good performance with respect to registration accuracy as well as processing time. The neural network yielded a mean Dice index of ∼0.87 which was similar to the advanced Normalization Tools algorithm and did so ∼3x faster using a multi-core CPU and ∼20x faster with a GPU. Standardized uptake value analysis showed that quantitative results were 30%–60% higher in the motion-corrected images, and the neural network performed better than or close to the advanced Normalization Tools.Conclusion: The aim of this work was to study the quantitative impact of using a data-driven deep learning motion correction technique for positron emission tomography data and assess its performance. The results showed the technique is capable of producing high quality registrations that compensate for patient motion that occurs during a scan and improve quantitative accuracy.

Developing an automated skeletal phenotyping pipeline to leverage biobank-level medical imaging databases.

Collecting skeletal measurements from medical imaging databases remains a tedious task, limiting the research utility of biobank-level data. Here we present an automated phenotyping pipeline for obtaining skeletal measurements from DXA scans and compare its performance to manually collected measurements. A pipeline that extends the Advanced Normalization Tools (ANTs) framework was developed on 341 whole-body DXA scans of UK Biobank South Asian participants. A set of 10 measurements throughout the skeleton was automatically obtained via this process, and the performance of the method was tested on 20 additional DXA images by calculating percent error and concordance correlation coefficients (CCC) for manual and automated measurements. Stature was then regressed on the automated femoral and tibia lengths and compared to published stature regressions to further assess the reliability of the automated measurements. Based on percent error and CCC, the performance of the automated measurements falls into three categories: poor (sacral and acetabular breadths), variable (trunk length, upper thoracic breadth, and innominate height), and high (maximum pelvic aperture breadth, bi-iliac breadth, femoral maximum length, and tibia length). Stature regression plots indicate that the automated measurements reflect realistic body proportions and appear consistent with published data reflecting these relationships in South Asian populations. Based on the performance of this pipeline, a subset of measurements can be reliably extracted from DXA scans, greatly expanding the utility of biobank-level data for biological anthropologists and medical researchers.

Comparison of Anatomical Pathway Models with Tractography Estimates of the Pallidothalamic, Cerebellothalamic, and Corticospinal Tracts.

Introduction: Models of structural connectivity in the human brain are typically simulated using tractographic approaches. However, the nonlinear fitting of anatomical pathway atlases to de novo subject brains represents a simpler alternative that is hypothesized to provide more anatomically realistic results. Therefore, the goal of this study was to perform a side-by-side comparison of the streamline estimates generated by either pathway atlas fits or tractographic reconstructions in the same subjects. Methods: Our analyses focused on reconstruction of the corticospinal tract (CST), cerebellothalamic (CBT), and pallidothalamic (PT) pathways using example datasets from the Human Connectome Project (HCP). We used MRtrix3 to explore whole brain, as well as manual seed-to-target, tractography approaches. In parallel, we performed nonlinear fits of an axonal pathway atlas to each HCP dataset using Advanced Normalization Tools (ANTs). Results: The different methods produced notably different estimates for each pathway in each subject. The fitted atlas pathways were highly stereotyped and exhibited low variability in their streamline trajectories. Manual tractography resulted in pathway estimates that generally corresponded with the fitted atlas pathways, but with a higher degree of variability in the individual streamlines. Pathway reconstructions derived from whole-brain tractography exhibited the highest degree of variability and struggled to create anatomically realistic representations for either the CBT or PT pathways. Conclusion: The speed, simplicity, reproducibility, and realism of anatomical pathway model fits makes them an appealing option for some forms of structural connectivity modeling in the human brain. Impact statement Axonal pathway modeling is an important component of deep brain stimulation (DBS) research studies that seek to identify the brain connections that are directly activated by stimulation. The corticospinal tract, cerebellothalamic (CBT), and pallidothalamic (PT) pathways are specifically relevant to the study of subthalamic DBS for the treatment of Parkinson's disease. Our results suggest that anatomical pathway model fits of the CBT and PT pathways to de novo subject brains represent a more anatomically realistic option than tractographic approaches when studying subthalamic DBS.

Contrast-agnostic deep learning–based registration pipeline: Validation in spinal cord multimodal MRI data

Medical image registration can be challenging, in that optimal solutions depend on the application domain (unimodal, multimodal, intra-subject and inter-subject), anatomical sites (e.g., brain, spinal cord (SC) and lungs), dimensionality of the data (2D, 3D and 4D), deformation constraints (rigid, affine and nonlinear) and computational time. Solutions that could accommodate a large variety of applications while producing satisfactory results are needed. SynthMorph was recently introduced as an unsupervised deep learning–based registration method. A particularly interesting feature is that training is performed on synthetic data so that registration becomes agnostic to image contrast and anatomy. However, SynthMorph is particularly sensitive to the initial closeness of the images. In this work, we extend the SynthMorph method by developing a cascaded pipeline of two models that can accommodate large and fine deformations, respectively. We also validate this pipeline for the registration of intra-subject multimodal and inter-subject uni/multimodal MRI data of the SC. This task is known to be particularly difficult due to the vicinity of multiple tissue types whose morphometrics can vary substantially across subjects and contrasts. Evaluation of the method was conducted on a publicly available dataset (spine-generic, 267 subjects) and was compared with a state-of-the-art benchmark: Spinal Cord Toolbox and Advanced Normalization Tools. Results demonstrate better registration accuracy compared with the benchmark and about 24–30 times faster on CPUs depending on the image size. This proposed pipeline provides an easy-to-use, accurate and fast solution for multimodal 3D registration. The code and trained models are freely available at https://github.com/ivadomed/multimodal-registration.

Comprehensive personalized ankle joint shape analysis of children with cerebral palsy from pediatric MRI.

Cerebral palsy, a common physical disability in childhood, often causes abnormal patterns of movement and posture. To better understand the pathology and improve rehabilitation of patients, a comprehensive bone shape analysis approach is proposed in this article. First, a group analysis is performed on a clinical MRI dataset using two state-of-the-art shape analysis methods: ShapeWorks and a voxel-based method relying on Advanced Normalization Tools (ANTs) registration. Second, an analysis of three bones of the ankle is done to provide a complete view of the ankle joint. Third, a bone shape analysis is carried out at subject level to highlight variability patterns for personnalized understanding of deformities.