MR-Class: A Python Tool for Brain MR Image Classification Utilizing One-vs-All DCNNs to Deal with the Open-Set Recognition Problem.

BACKGROUND: MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences. METHODS: Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes: T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20,101 MRI images) was used for training, while C2 (197, 11,333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics model performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I). RESULTS: Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95% Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. A total of 620 images were misclassified; manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased the PFS model C-I by 14.6% on average, compared to a model trained without MR-Class. CONCLUSIONS: We provide a DCNN-based method for the sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.

MR Intensity Normalization Methods Impact Sequence Specific Radiomics Prognostic Model Performance in Primary and Recurrent High-Grade Glioma.

PURPOSE: This study investigates the impact of different intensity normalization (IN) methods on the overall survival (OS) radiomics models' performance of MR sequences in primary (pHGG) and recurrent high-grade glioma (rHGG). METHODS: MR scans acquired before radiotherapy were retrieved from two independent cohorts (rHGG C1: 197, pHGG C2: 141) from multiple scanners (15, 14). The sequences are T1 weighted (w), contrast-enhanced T1w (T1wce), T2w, and T2w-FLAIR. Sequence-specific significant features (SF) associated with OS, extracted from the tumour volume, were derived after applying 15 different IN methods. Survival analyses were conducted using Cox proportional hazard (CPH) and Poisson regression (POI) models. A ranking score was assigned based on the 10-fold cross-validated (CV) concordance index (C-I), mean square error (MSE), and the Akaike information criterion (AICs), to evaluate the methods' performance. RESULTS: Scatter plots of the 10-CV C-I and MSE against the AIC showed an impact on the survival predictions between the IN methods and MR sequences (C1/C2 C-I range: 0.62-0.71/0.61-0.72, MSE range: 0.20-0.42/0.13-0.22). White stripe showed stable results for T1wce (C1/C2 C-I: 0.71/0.65, MSE: 0.21/0.14). Combat (0.68/0.62, 0.22/0.15) and histogram matching (HM, 0.67/0.64, 0.22/0.15) showed consistent prediction results for T2w models. They were also the top-performing methods for T1w in C2 (Combat: 0.67, 0.13; HM: 0.67, 0.13); however, only HM achieved high predictions in C1 (0.66, 0.22). After eliminating IN impacted SF using Spearman's rank-order correlation coefficient, a mean decrease in the C-I and MSE of 0.05 and 0.03 was observed in all four sequences. CONCLUSION: The IN method impacted the predictive power of survival models; thus, performance is sequence-dependent.

Deep Learning-based Automatic Lung Segmentation on Multiresolution CT Scans from Healthy and Fibrotic Lungs in Mice.

Purpose: To develop a model to accurately segment mouse lungs with varying levels of fibrosis and investigate its applicability to mouse images with different resolutions. Materials and Methods: In this experimental retrospective study, a U-Net was trained to automatically segment lungs on mouse CT images. The model was trained (n = 1200), validated (n = 300), and tested (n = 154) on longitudinally acquired and semiautomatically segmented CT images, which included both healthy and irradiated mice (group A). A second independent group of 237 mice (group B) was used for external testing. The Dice score coefficient (DSC) and Hausdorff distance (HD) were used as metrics to quantify segmentation accuracy. Transfer learning was applied to adapt the model to high-spatial-resolution mouse micro-CT segmentation (n = 20; group C [n = 16 for training and n = 4 for testing]). Results: The trained model yielded a high median DSC in both test datasets: 0.984 (interquartile range [IQR], 0.977-0.988) in group A and 0.966 (IQR, 0.955-0.972) in group B. The median HD in both test datasets was 0.47 mm (IQR, 0-0.51 mm [group A]) and 0.31 mm (IQR, 0.30-0.32 mm [group B]). Spatially resolved quantification of differences toward reference masks revealed two hot spots close to the air-tissue interfaces, which are particularly prone to deviation. Finally, for the higher-resolution mouse CT images, the median DSC was 0.905 (IQR, 0.902-0.929) and the median 95th percentile of the HD was 0.33 mm (IQR, 2.61-2.78 mm). Conclusion: The developed deep learning-based method for mouse lung segmentation performed well independently of disease state (healthy, fibrotic, emphysematous lungs) and CT resolution.Keywords: Deep Learning, Lung Fibrosis, Radiation Therapy, Segmentation, Animal Studies, CT, Thorax, Lung Supplemental material is available for this article. Published under a CC BY 4.0 license.

MR-PET head motion correction based on co-registration of multicontrast MR images.

Head motion is a major source of image artefacts in neuroimaging studies and can lead to degradation of the quantitative accuracy of reconstructed PET images. Simultaneous magnetic resonance-positron emission tomography (MR-PET) makes it possible to estimate head motion information from high-resolution MR images and then correct motion artefacts in PET images. In this article, we introduce a fully automated PET motion correction method, MR-guided MAF, based on the co-registration of multicontrast MR images. The performance of the MR-guided MAF method was evaluated using MR-PET data acquired from a cohort of ten healthy participants who received a slow infusion of fluorodeoxyglucose ([18-F]FDG). Compared with conventional methods, MR-guided PET image reconstruction can reduce head motion introduced artefacts and improve the image sharpness and quantitative accuracy of PET images acquired using simultaneous MR-PET scanners. The fully automated motion estimation method has been implemented as a publicly available web-service.

Individual differences in haemoglobin concentration influence bold fMRI functional connectivity and its correlation with cognition.

Resting-state connectivity measures the temporal coherence of the spontaneous neural activity of spatially distinct regions, and is commonly measured using BOLD-fMRI. The BOLD response follows neuronal activity, when changes in the relative concentration of oxygenated and deoxygenated haemoglobin cause fluctuations in the MRI T2* signal. Since the BOLD signal detects changes in relative concentrations of oxy/deoxy-haemoglobin, individual differences in haemoglobin levels may influence the BOLD signal-to-noise ratio in a manner independent of the degree of neural activity. In this study, we examined whether group differences in haemoglobin may confound measures of functional connectivity. We investigated whether relationships between measures of functional connectivity and cognitive performance could be influenced by individual variability in haemoglobin. Finally, we mapped the neuroanatomical distribution of the influence of haemoglobin on functional connectivity to determine where group differences in functional connectivity are manifest. In a cohort of 518 healthy elderly subjects (259 men), each sex group was median-split into two groups with high and low haemoglobin concentration. Significant differences were obtained in functional connectivity between the high and low haemoglobin groups for both men and women (Cohen's d 0.17 and 0.03 for men and women respectively). The haemoglobin connectome in males showed a widespread systematic increase in functional connectivity correlation values, whilst the female connectome showed predominantly parietal and subcortical increases and temporo-parietal decreases. Despite the haemoglobin groups having no differences in cognitive measures, significant differences in the linear relationships between cognitive performance and functional connectivity were obtained for all 5 cognitive tests in males, and 4 out of 5 tests in females. Our findings confirm that individual variability in haemoglobin levels that give rise to group differences are an important confounding variable in BOLD-fMRI-based studies of functional connectivity. Controlling for haemoglobin variability as a potentially confounding variable is crucial to ensure the reproducibility of human brain connectome studies, especially in studies that compare groups of individuals, compare sexes, or examine connectivity-cognition relationships.

Relationship between parenthood and cortical thickness in late adulthood.

Pregnancy and the early postpartum period alter the structure of the brain; particularly in regions related to parental care. However, the enduring effects of this period on human brain structure and cognition in late life is unknown. Here we use magnetic resonance imaging to examine differences in cortical thickness related to parenthood in late life, for both sexes. In 235 healthy older women, we find a positive relationship between parity (number of children parented) and memory performance in mothers. Parity was also associated with differences in cortical thickness in women in the parahippocampus, precuneus, cuneus and pericalcarine sulcus. We also compared non-parents to parents of one child, in a sub-sample of older women (N = 45) and men (N = 35). For females, six regions differed in cortical thickness between parents and non-parents; these regions were consistent with those seen earlier in life in previous studies. For males, five regions differed in cortical thickness between parents and non-parents. We are first to reveal parenthood-related brain differences in late-life; our results are consistent with previously identified areas that are altered during pregnancy and the postpartum period. This study provides preliminary evidence to suggest that neural changes associated with early stages of parenthood persist into older age, and for women, may be related to marginally better cognitive outcomes.

A Comprehensive Framework to Capture the Arcana of Neuroimaging Analysis.

Mastering the "arcana of neuroimaging analysis", the obscure knowledge required to apply an appropriate combination of software tools and parameters to analyse a given neuroimaging dataset, is a time consuming process. Therefore, it is not typically feasible to invest the additional effort required generalise workflow implementations to accommodate for the various acquisition parameters, data storage conventions and computing environments in use at different research sites, limiting the reusability of published workflows. We present a novel software framework, Abstraction of Repository-Centric ANAlysis (Arcana), which enables the development of complex, "end-to-end" workflows that are adaptable to new analyses and portable to a wide range of computing infrastructures. Analysis templates for specific image types (e.g. MRI contrast) are implemented as Python classes, which define a range of potential derivatives and analysis methods. Arcana retrieves data from imaging repositories, which can be BIDS datasets, XNAT instances or plain directories, and stores selected derivatives and associated provenance back into a repository for reuse by subsequent analyses. Workflows are constructed using Nipype and can be executed on local workstations or in high performance computing environments. Generic analysis methods can be consolidated within common base classes to facilitate code-reuse and collaborative development, which can be specialised for study-specific requirements via class inheritance. Arcana provides a framework in which to develop unified neuroimaging workflows that can be reused across a wide range of research studies and sites.

Functional Connectivity of Corticostriatal Circuitry and Psychosis-like Experiences in the General Community.

BACKGROUND: Psychotic symptoms are proposed to lie on a continuum, ranging from isolated psychosis-like experiences (PLEs) in nonclinical populations to frank disorder. Here, we investigated the neurobiological correlates of this continuum by examining whether functional connectivity of dorsal corticostriatal circuitry, which is disrupted in psychosis patients and individuals at high risk for psychosis, is associated with the severity of subclinical PLEs. METHODS: A community sample of 672 adults with no history of psychiatric or neurological illnesses completed a battery of seven questionnaires spanning various PLE domains. Principal component analysis of 12 subscales taken from seven questionnaires was used to estimate major dimensions of PLEs. Dimension scores from principal component analysis were then correlated with whole-brain voxelwise functional connectivity maps of the dorsal striatum in a subset of 353 participants who completed a resting-state neuroimaging protocol. RESULTS: Principal component analysis identified two dimensions of PLEs that accounted for 62.57% of variance in the measures, corresponding to positive (i.e., subthreshold delusions and hallucinations) and negative (i.e., subthreshold social and physical anhedonia) symptom-like PLEs. Reduced functional connectivity between the dorsal striatum and prefrontal and motor cortices correlated with more severe positive PLEs. Increased functional connectivity between the dorsal striatum and motor cortex was associated with more severe negative PLEs. CONCLUSIONS: Consistent with past findings in patients and individuals at high risk for psychosis, subthreshold positive symptomatology is associated with reduced functional connectivity of the dorsal circuit. This finding suggests that the connectivity of this circuit tracks the expression of psychotic phenomena across a broad spectrum of severity, extending from the subclinical domain to clinical diagnosis.

Simultaneous task-based BOLD-fMRI and [18-F] FDG functional PET for measurement of neuronal metabolism in the human visual cortex.

Studies of task-evoked brain activity are the cornerstone of cognitive neuroscience, and unravel the spatial and temporal brain dynamics of cognition in health and disease. Blood oxygenation level dependent functional magnetic resonance imaging (BOLD-fMRI) is one of the most common methods of studying brain function in humans. BOLD-fMRI indirectly infers neuronal activity from regional changes in blood oxygenation and is not a quantitative metric of brain function. Regional variation in glucose metabolism, measured using [18-F] fluorodeoxyglucose positron emission tomography (FDG-PET), provides a more direct and interpretable measure of neuronal activity. However, while the temporal resolution of BOLD-fMRI is in the order of seconds, standard FDG-PET protocols provide a static snapshot of glucose metabolism. Here, we develop a novel experimental design for measurement of task-evoked changes in regional blood oxygenation and glucose metabolism with high temporal resolution. Over a 90-min simultaneous BOLD-fMRI/FDG-PET scan, [18F] FDG was constantly infused to 10 healthy volunteers, who viewed a flickering checkerboard presented in a hierarchical block design. Dynamic task-related changes in blood oxygenation and glucose metabolism were examined with temporal resolution of 2.5sec and 1-min, respectively. Task-related, temporally coherent brain networks of haemodynamic and metabolic connectivity were jointly coupled in the visual cortex, as expected. Results demonstrate that the hierarchical block design, together with the infusion FDG-PET technique, enabled both modalities to track task-related neural responses with high temporal resolution. The simultaneous MR-PET approach has the potential to provide unique insights into the dynamic haemodynamic and metabolic interactions that underlie cognition in health and disease.

Sexual Dimorphism of Resting-State Network Connectivity in Healthy Ageing.

OBJECTIVES: The onset of many illnesses is confounded with age and sex. Increasing age is a risk factor for the development of many illnesses, and sexual dimorphism influences brain anatomy, function, and cognition. Here, we examine frequency-specific connectivity in resting-state networks in a large sample (n = 406) of healthy aged adults. METHOD: We quantify frequency-specific connectivity in three resting-state networks known to be implicated in age-related decline: the default mode, dorsal attention, and salience networks, using multiband functional magnetic resonance imaging. Frequency-specific connectivity was quantified in four bands: low (0.015-0.027 Hz), moderately low (0.027-0.073 Hz), moderately high (0.073-0.198 Hz), and high (0.198-0.5 Hz) frequency bands, using mean intensity and spatial extent. Differences in connectivity between the sexes in each of the three networks were examined. RESULTS: Each network showed the largest intensity and spatial extent at low frequencies and smallest extent at high frequencies. Males showed greater connectivity than females in the salience network. Females showed greater connectivity than males in the default mode network. DISCUSSION: Results in this healthy aged cohort are compatible with those obtained in young samples, suggesting that frequency-specific connectivity, and differences between the sexes, are maintained into older age. Our results indicate that sex should be considered as an influencing factor in studies of resting-state connectivity.

Accurate hybrid template-based and MR-based attenuation correction using UTE images for simultaneous PET/MR brain imaging applications.

BACKGROUND: Attenuation correction is one of the most crucial correction factors for accurate PET data quantitation in hybrid PET/MR scanners, and computing accurate attenuation coefficient maps from MR brain acquisitions is challenging. Here, we develop a method for accurate bone and air segmentation using MR ultrashort echo time (UTE) images. METHODS: MR UTE images from simultaneous MR and PET imaging of five healthy volunteers was used to generate a whole head, bone and air template image for inclusion into an improved MR derived attenuation correction map, and applied to PET image data for quantitative analysis. Bone, air and soft tissue were segmented based on Gaussian Mixture Models with probabilistic tissue maps as a priori information. We present results for two approaches for bone attenuation coefficient assignments: one using a constant attenuation correction value; and another using an estimated continuous attenuation value based on a calibration fit. Quantitative comparisons were performed to evaluate the accuracy of the reconstructed PET images, with respect to a reference image reconstructed with manually segmented attenuation maps. RESULTS: The DICE coefficient analysis for the air and bone regions in the images demonstrated improvements compared to the UTE approach, and other state-of-the-art techniques. The most accurate whole brain and regional brain analyses were obtained using constant bone attenuation coefficient values. CONCLUSIONS: A novel attenuation correction method for PET data reconstruction is proposed. Analyses show improvements in the quantitative accuracy of the reconstructed PET images compared to other state-of-the-art AC methods for simultaneous PET/MR scanners. Further evaluation is needed with radiopharmaceuticals other than FDG, and in larger cohorts of participants.

From simultaneous to synergistic MR-PET brain imaging: A review of hybrid MR-PET imaging methodologies.

Simultaneous Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) scanning is a recent major development in biomedical imaging. The full integration of the PET detector ring and electronics within the MR system has been a technologically challenging design to develop but provides capacity for simultaneous imaging and the potential for new diagnostic and research capability. This article reviews state-of-the-art MR-PET hardware and software, and discusses future developments focusing on neuroimaging methodologies for MR-PET scanning. We particularly focus on the methodologies that lead to an improved synergy between MRI and PET, including optimal data acquisition, PET attenuation and motion correction, and joint image reconstruction and processing methods based on the underlying complementary and mutual information. We further review the current and potential future applications of simultaneous MR-PET in both systems neuroscience and clinical neuroimaging research. We demonstrate a simultaneous data acquisition protocol to highlight new applications of MR-PET neuroimaging research studies.

Functional subdivisions within the human intraparietal sulcus are involved in visuospatial transformation in a non-context-dependent manner.

Object-based visuospatial transformation is important for the ability to interact with the world and the people and objects within it. In this preliminary investigation, we hypothesized that object-based visuospatial transformation is a unitary process invoked regardless of current context and is localized to the intraparietal sulcus. Participants (n = 14) performed both antisaccade and mental rotation tasks while scanned using fMRI. A statistical conjunction confirmed that both tasks activated the intraparietal sulcus. Statistical parametric anatomical mapping determined that the statistical conjunction was localized to intraparietal sulcus subregions hIP2 and hIP3. A Gaussian naïve Bayes classifier confirmed that the conjunction in region hIP3 was indistinguishable between tasks. The results provide evidence that object-based visuospatial transformation is a domain-general process that is invoked regardless of current context. Our results are consistent with the modular model of the posterior parietal cortex and the distinct cytoarchitectonic, structural, and functional connectivity profiles of the subregions in the intraparietal sulcus. Hum Brain Mapp 39:354-368, 2018. © 2017 Wiley Periodicals, Inc.

Altered functional connectivity networks in acallosal and socially impaired BTBR mice.

Agenesis of the corpus callosum (AgCC) is a congenital condition associated with wide-ranging emotional and social impairments often overlapping with the diagnostic criteria for autism. Mapping functional connectivity in the acallosal brain can help identify neural correlates of the deficits associated with this condition, and elucidate how congenital white matter alterations shape the topology of large-scale functional networks. By using resting-state BOLD functional magnetic resonance imaging (rsfMRI), here we show that acallosal BTBR T+tpr3tf/J (BTBR) mice, an idiopathic model of autism, exhibit impaired intra-hemispheric connectivity in fronto-cortical, but not in posterior sensory cortical areas. We also document profoundly altered subcortical and intra-hemispheric connectivity networks, with evidence of marked fronto-thalamic and striatal disconnectivity, along with aberrant spatial extension and strength of ipsilateral and local connectivity. Importantly, inter-hemispheric tracing of monosynaptic connections in the primary visual cortex using recombinant rabies virus confirmed the absence of direct homotopic pathways between posterior cortical areas of BTBR mice, suggesting a polysynaptic origin for the synchronous rsfMRI signal observed in these regions. Collectively, the observed long-range connectivity impairments recapitulate hallmark neuroimaging findings in autism, and are consistent with the behavioral phenotype of BTBR mice. In contrast to recent rsfMRI studies in high functioning AgCC individuals, the profound fronto-cortical and subcortical disconnectivity mapped suggest that compensatory mechanism may not necessarily restore the full connectional topology of the brain, resulting in residual connectivity alterations that serve as plausible substrates for the cognitive and emotional deficits often associated with AgCC.

Deficient neuron-microglia signaling results in impaired functional brain connectivity and social behavior.

Microglia are phagocytic cells that infiltrate the brain during development and have a role in the elimination of synapses during brain maturation. Changes in microglial morphology and gene expression have been associated with neurodevelopmental disorders. However, it remains unknown whether these changes are a primary cause or a secondary consequence of neuronal deficits. Here we tested whether a primary deficit in microglia was sufficient to induce some autism-related behavioral and functional connectivity deficits. Mice lacking the chemokine receptor Cx3cr1 exhibit a transient reduction of microglia during the early postnatal period and a consequent deficit in synaptic pruning. We show that deficient synaptic pruning is associated with weak synaptic transmission, decreased functional brain connectivity, deficits in social interaction and increased repetitive-behavior phenotypes that have been previously associated with autism and other neurodevelopmental and neuropsychiatric disorders. These findings open the possibility that disruptions in microglia-mediated synaptic pruning could contribute to neurodevelopmental and neuropsychiatric disorders.

Distributed BOLD and CBV-weighted resting-state networks in the mouse brain.

Laboratory mouse models represent a powerful tool to elucidate the biological foundations of disease, but translation to and from human studies rely upon valid cross-species measures. Resting-state functional connectivity (rsFC) represents a promising translational probe of brain function; however, no convincing demonstration of the presence of distributed, bilateral rsFC networks in the mouse brain has yet been reported. Here we used blood oxygen level dependent (BOLD) and cerebral blood volume (CBV) weighted fMRI to demonstrate the presence of robust and reproducible resting-state networks in the mouse brain. Independent-component analysis (ICA) revealed inter-hemispheric homotopic rsFC networks encompassing several established neuro-anatomical systems of the mouse brain, including limbic, motor and parietal cortex, striatum, thalamus and hippocampus. BOLD and CBV contrast produced consistent networks, with the latter exhibiting a superior anatomical preservation of brain regions close to air-tissue interfaces (e.g. ventral hippocampus). Seed-based analysis confirmed the inter-hemispheric specificity of the correlations observed with ICA and highlighted the presence of distributed antero-posterior networks anatomically homologous to the human salience network (SN) and default-mode network (DMN). Consistent with rsFC investigations in humans, BOLD and CBV-weighted fMRI signals in the DMN-like network exhibited spontaneous anti-correlation with neighbouring fronto-parietal areas. These findings demonstrate the presence of robust distributed intrinsic functional connectivity networks in the mouse brain, and pave the way for the application of rsFC readouts in transgenic models to investigate the biological underpinnings of spontaneous BOLD fMRI fluctuations and their derangement in pathological states.