Neural deformation fields for template-based reconstruction of cortical surfaces from MRI.

The reconstruction of cortical surfaces is a prerequisite for quantitative analyses of the cerebral cortex in magnetic resonance imaging (MRI). Existing segmentation-based methods separate the surface registration from the surface extraction, which is computationally inefficient and prone to distortions. We introduce Vox2Cortex-Flow (V2C-Flow), a deep mesh-deformation technique that learns a deformation field from a brain template to the cortical surfaces of an MRI scan. To this end, we present a geometric neural network that models the deformation-describing ordinary differential equation in a continuous manner. The network architecture comprises convolutional and graph-convolutional layers, which allows it to work with images and meshes at the same time. V2C-Flow is not only very fast, requiring less than two seconds to infer all four cortical surfaces, but also establishes vertex-wise correspondences to the template during reconstruction. In addition, V2C-Flow is the first approach for cortex reconstruction that models white matter and pial surfaces jointly, therefore avoiding intersections between them. Our comprehensive experiments on internal and external test data demonstrate that V2C-Flow results in cortical surfaces that are state-of-the-art in terms of accuracy. Moreover, we show that the established correspondences are more consistent than in FreeSurfer and that they can directly be utilized for cortex parcellation and group analyses of cortical thickness.

Emotion regulation training for adolescents with major depression: Results from a randomized controlled trial.

Difficulties in emotion regulation (ER) are thought to contribute to the development and maintenance of major depression (MD) in adolescents. In healthy adults, a task-based training of ER has previously proven effective to reduce stress, but no such studies are available for MD. It is also unclear whether findings can be generalized onto adolescent populations. The final sample consisted of n = 70 adolescents with MD, who were randomized to a task-based ER training (n = 36) or a control training (n = 34). Across four sessions, the ER group was trained to downregulate negative affect to negative images via reappraisal, while the control group was instructed to attend the images. Rumination, stress-, and affect-related measures were assessed as primary outcomes, behavioral and neurophysiological responses (late positive potential, LPP), as secondary outcomes. The trial was preregistered at clinicaltrials.gov (NCT03957850). While there was no significant differential effect of the ER training on primary outcomes, we found small to moderate effects on rumination in the ER group, but not the control group. During reappraisal (compared to attend), the ER group showed an unexpected increase of the LPP during the first, but not during later training sessions. Although replication in large, multicenter trials is needed, our findings on effect sizes suggest that ER training might be promising to decrease rumination in adolescent MD. The LPP increase at the first session may represent cognitive effort, which was successfully reduced over the sessions. Future studies should research whether training effects transfer to daily life and are durable over a longer time period. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Can we diagnose mental disorders in children? A large-scale assessment of machine learning on structural neuroimaging of 6916 children in the adolescent brain cognitive development study.

Background: Prediction of mental disorders based on neuroimaging is an emerging area of research with promising first results in adults. However, research on the unique demographic of children is underrepresented and it is doubtful whether findings obtained on adults can be transferred to children. Methods: Using data from 6916 children aged 9-10 in the multicenter Adolescent Brain Cognitive Development study, we extracted 136 regional volume and thickness measures from structural magnetic resonance images to rigorously evaluate the capabilities of machine learning to predict 10 different psychiatric disorders: major depressive disorder, bipolar disorder (BD), psychotic symptoms, attention deficit hyperactivity disorder (ADHD), oppositional defiant disorder, conduct disorder, post-traumatic stress disorder, obsessive-compulsive disorder, generalized anxiety disorder, and social anxiety disorder. For each disorder, we performed cross-validation and assessed whether models discovered a true pattern in the data via permutation testing. Results: Two of 10 disorders can be detected with statistical significance when using advanced models that (i) allow for non-linear relationships between neuroanatomy and disorder, (ii) model interdependencies between disorders, and (iii) avoid confounding due to sociodemographic factors: ADHD (AUROC = 0.567, p = 0.002) and BD (AUROC = 0.551, p = 0.002). In contrast, traditional models perform consistently worse and predict only ADHD with statistical significance (AUROC = 0.529, p = 0.002). Conclusion: While the modest absolute classification performance does not warrant application in the clinic, our results provide empirical evidence that embracing and explicitly accounting for the complexities of mental disorders via advanced machine learning models can discover patterns that would remain hidden with traditional models.

Deep learning for the prediction of type 2 diabetes mellitus from neck-to-knee Dixon MRI in the UK biobank.

Rationale and objectives: We evaluate the automatic identification of type 2 diabetes from neck-to-knee, two-point Dixon MRI scans with 3D convolutional neural networks on a large, population-based dataset. To this end, we assess the best combination of MRI contrasts and stations for diabetes prediction, and the benefit of integrating risk factors. Materials and methods: Subjects with type 2 diabetes mellitus have been identified in the prospective UK Biobank Imaging study, and a matched control sample has been created to avoid confounding bias. Five-fold cross-validation is used for the evaluation. All scans from the two-point Dixon neck-to-knee sequence have been standardized. A neural network that considers multi-channel MRI input was developed and integrates clinical information in tabular format. An ensemble strategy is used to combine multi-station MRI predictions. A subset with quantitative fat measurements is identified for comparison to prior approaches. Results: MRI scans from 3406 subjects (mean age, 66.2 years ± 7.1 [standard deviation]; 1128 women) were analyzed with 1703 diabetics. A balanced accuracy of 78.7 %, AUC ROC of 0.872, and an average precision of 0.878 was obtained for the classification of diabetes. The ensemble over multiple Dixon MRI stations yields better performance than selecting the individually best station. Moreover, combining fat and water scans as multi-channel inputs to the networks improves upon just using single contrasts as input. Integrating clinical information about known risk factors of diabetes in the network boosts the performance across all stations and the ensemble. The neural network achieved superior results compared to the prediction based on quantitative MRI measurements. Conclusions: The developed deep learning model accurately predicted type 2 diabetes from neck-to-knee two-point Dixon MRI scans.

Abdominal organ segmentation via deep diffeomorphic mesh deformations.

Abdominal organ segmentation from CT and MRI is an essential prerequisite for surgical planning and computer-aided navigation systems. It is challenging due to the high variability in the shape, size, and position of abdominal organs. Three-dimensional numeric representations of abdominal shapes with point-wise correspondence to a template are further important for quantitative and statistical analyses thereof. Recently, template-based surface extraction methods have shown promising advances for direct mesh reconstruction from volumetric scans. However, the generalization of these deep learning-based approaches to different organs and datasets, a crucial property for deployment in clinical environments, has not yet been assessed. We close this gap and employ template-based mesh reconstruction methods for joint liver, kidney, pancreas, and spleen segmentation. Our experiments on manually annotated CT and MRI data reveal limited generalization capabilities of previous methods to organs of different geometry and weak performance on small datasets. We alleviate these issues with a novel deep diffeomorphic mesh-deformation architecture and an improved training scheme. The resulting method, UNetFlow, generalizes well to all four organs and can be easily fine-tuned on new data. Moreover, we propose a simple registration-based post-processing that aligns voxel and mesh outputs to boost segmentation accuracy.

Emotion regulation in adolescents with major depression - Evidence from a combined EEG and eye-tracking study.

BACKGROUND: Adolescent major depression (MD) is characterized by deficits in emotion regulation (ER). Little is known about the neurophysiological correlates that are associated with these deficits. Moreover, the additional examination of visual attention during ER would allow a more in-depth understanding of ER deficits but has not yet been applied simultaneously. METHODS: N = 33 adolescents with MD and n = 35 healthy controls (HCs) aged 12-18 years performed an ER task during which they either a) down-regulated their negative affective response to negative images via cognitive reappraisal or b) attended the images without changing their affective response. During the task, the Late Positive Potential (LPP), gaze fixations on emotional image aspects, and self-reported affective responses were collected simultaneously. RESULTS: Compared to HCs, adolescents with MD demonstrated reduced ER success based on self-report but did not differ in LPP amplitudes. Participants in both groups showed increased amplitudes in the middle LPP window when they reappraised negative pictures compared to when they attended them. Only in the HC group, increased LPP amplitudes during reappraisal were paralleled by more positive affective responses. LIMITATION: The applied stimuli were part of picture databases and might therefore have limited self-relevance. CONCLUSIONS: Increased LPP amplitude during ER in both groups might be specific to adolescence and might suggest that ER at this age is challenging and requires a high amount of cognitive resources. These findings provide an important starting point for future interventional studies in youth MD.

Aberrant allometric scaling of cortical folding in preterm-born adults.

A universal allometric scaling law has been proposed to describe cortical folding of the mammalian brain as a function of the product of cortical surface area and the square root of cortical thickness across different mammalian species, including humans. Since these cortical properties are vulnerable to developmental disturbances caused by preterm birth in humans and since these alterations are related to cognitive impairments, we tested (i) whether cortical folding in preterm-born adults follows this cortical scaling law and (ii) the functional relevance of potential scaling aberrances. We analysed the cortical scaling relationship in a large and prospectively collected cohort of 91 very premature-born adults (<32 weeks of gestation and/or birthweight <1500 g, very preterm and/or very low birth weight) and 105 full-term controls at 26 years of age based on the total surface area, exposed surface area and average cortical thickness measured with structural magnetic resonance imaging and surface-based morphometry. We found that the slope of the log-transformed cortical scaling relationship was significantly altered in adults (very preterm and/or very low birth weight: 1.24, full-term: 1.14, P = 0.018). More specifically, the slope was significantly altered in male adults (very preterm and/or very low birth weight: 1.24, full-term: 1.00, P = 0.031), while there was no significant difference in the slope of female adults (very preterm and/or very low birth weight: 1.27, full-term: 1.12, P = 0.225). Furthermore, offset was significantly lower compared with full-term controls in both male (very preterm and/or very low birth weight: -0.546, full-term: -0.538, P = 0.001) and female adults (very preterm and/or very low birth weight: -0.545, full-term: -0.538, P = 0.023), indicating a systematic shift of the regression line after preterm birth. Gestational age had a significant effect on the slope in very preterm and/or very low birth weight adults and more specifically in male very preterm and/or very low birth weight adults, indicating that the difference in slope is specifically related to preterm birth. The shape or tension term of the scaling law had no significant effect on cognitive performance, while the size of the cortex did. Results demonstrate altered scaling of cortical surface and cortical thickness in very premature-born adults. Data suggest altered mechanical forces acting on the cortex after preterm birth.

Identification of causal effects of neuroanatomy on cognitive decline requires modeling unobserved confounders.

INTRODUCTION: Carrying out a randomized controlled trial to estimate the causal effects of regional brain atrophy due to Alzheimer's disease (AD) is impossible. Instead, we must estimate causal effects from observational data. However, this generally requires knowing and having recorded all confounders, which is often unrealistic. METHODS: We provide an approach that leverages the dependencies among multiple neuroanatomical measures to estimate causal effects from observational neuroimaging data without the need to know and record all confounders. RESULTS: Our analyses of N = 732 $N=732$ subjects from the Alzheimer's Disease Neuroimaging Initiative demonstrate that using our approach results in biologically meaningful conclusions, whereas ignoring unobserved confounding yields results that conflict with established knowledge on cognitive decline due to AD. DISCUSSION: The findings provide evidence that the impact of unobserved confounding can be substantial. To ensure trustworthy scientific insights, future AD research can account for unobserved confounding via the proposed approach.

AbdomenNet: deep neural network for abdominal organ segmentation in epidemiologic imaging studies.

BACKGROUND: Whole-body imaging has recently been added to large-scale epidemiological studies providing novel opportunities for investigating abdominal organs. However, the segmentation of these organs is required beforehand, which is time consuming, particularly on such a large scale. METHODS: We introduce AbdomentNet, a deep neural network for the automated segmentation of abdominal organs on two-point Dixon MRI scans. A pre-processing pipeline enables to process MRI scans from different imaging studies, namely the German National Cohort, UK Biobank, and Kohorte im Raum Augsburg. We chose a total of 61 MRI scans across the three studies for training an ensemble of segmentation networks, which segment eight abdominal organs. Our network presents a novel combination of octave convolutions and squeeze and excitation layers, as well as training with stochastic weight averaging. RESULTS: Our experiments demonstrate that it is beneficial to combine data from different imaging studies to train deep neural networks in contrast to training separate networks. Combining the water and opposed-phase contrasts of the Dixon sequence as input channels, yields the highest segmentation accuracy, compared to single contrast inputs. The mean Dice similarity coefficient is above 0.9 for larger organs liver, spleen, and kidneys, and 0.71 and 0.74 for gallbladder and pancreas, respectively. CONCLUSIONS: Our fully automated pipeline provides high-quality segmentations of abdominal organs across population studies. In contrast, a network that is only trained on a single dataset does not generalize well to other datasets.

The Medical Segmentation Decathlon.

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

DAFT: A universal module to interweave tabular data and 3D images in CNNs.

Prior work on Alzheimer's Disease (AD) has demonstrated that convolutional neural networks (CNNs) can leverage the high-dimensional image information for diagnosing patients. Beside such data-driven approaches, many established biomarkers exist and are typically represented as tabular data, such as demographics, genetic alterations, or laboratory measurements from cerebrospinal fluid. However, little research has focused on the effective integration of tabular data into existing CNN architectures to improve patient diagnosis. We introduce the Dynamic Affine Feature Map Transform (DAFT), a general-purpose module for CNNs that incites or represses high-level concepts learned from a 3D image by conditioning feature maps of a convolutional layer on both a patient's image and tabular clinical information. This is achieved by using an auxiliary neural network that outputs a scaling factor and offset to dynamically apply an affine transformation to the feature maps of a convolutional layer. In our experiments on AD diagnosis and time-to-dementia prediction, we show that the DAFT is highly effective in combining 3D image and tabular information by achieving a mean balanced accuracy of 0.622 for diagnosis, and mean c-index of 0.748 for time-to-dementia prediction, thus outperforming all baseline methods. Finally, our extensive ablation study and empirical experiments reveal that the performance improvement due to the DAFT is robust with respect to many design choices.

Hippocampal representations for deep learning on Alzheimer's disease.

Deep learning offers a powerful approach for analyzing hippocampal changes in Alzheimer's disease (AD) without relying on handcrafted features. Nevertheless, an input format needs to be selected to pass the image information to the neural network, which has wide ramifications for the analysis, but has not been evaluated yet. We compare five hippocampal representations (and their respective tailored network architectures) that span from raw images to geometric representations like meshes and point clouds. We performed a thorough evaluation for the prediction of AD diagnosis and time-to-dementia prediction with experiments on an independent test dataset. In addition, we evaluated the ease of interpretability for each representation-network pair. Our results show that choosing an appropriate representation of the hippocampus for predicting Alzheimer's disease with deep learning is crucial, since it impacts performance and ease of interpretation.

Visual attention during cognitive reappraisal in adolescent major depression: Evidence from two eye-tracking studies.

Adolescent major depression (MD) is associated with impaired emotion regulation. However, results on cognitive reappraisal (CR) are mixed. Investigation of gaze behavior during CR allows a more thorough understanding of intact and deviant CR processes in MD. These studies examined for the first time the role of visual attention during CR in MD. We applied an established CR paradigm in two separate studies, with each study focusing on a different CR strategy. In Study 1, we investigated "distancing" in 39 adolescents with MD and 44 healthy controls (HCs). In Study 2, we applied "reinterpretation" in an independent sample of 37 HCs and 19 adolescents with MD. In both studies, adolescents either down-regulated negative affect to negative pictures via CR or attended them, while eye-movements were continuously recorded. Results of both studies showed that adolescents with MD and HCs did not differ in self-reported ER success. The groups showed comparable gaze behaviour patterns for emotional interest areas and entire pictures. Findings suggest that adolescents with MD are capable of applying CR when instructed and show intact visual attention processes. Future studies should examine whether repeatedly instructing adolescents with MD to apply CR might lead to improved emotion regulation in daily life.

Effect of MRI acquisition acceleration via compressed sensing and parallel imaging on brain volumetry.

OBJECTIVES: To investigate the effect of compressed SENSE (CS), an acceleration technique combining parallel imaging and compressed sensing, on potential bias and precision of brain volumetry and evaluate it in the context of normative brain volumetry. MATERIALS AND METHODS: In total, 171 scans from scan-rescan experiments on three healthy subjects were analyzed. Each subject received 3D-T1-weighted brain MRI scans at increasing degrees of acceleration (CS-factor = 1/4/8/12/16/20/32). Single-scan acquisition times ranged from 00:41 min (CS-factor = 32) to 21:52 min (CS-factor = 1). Brain segmentation and volumetry was performed using two different software tools: md.brain, a proprietary software based on voxel-based morphometry, and FreeSurfer, an open-source software based on surface-based morphometry. Four sub-volumes were analyzed: brain parenchyma (BP), total gray matter, total white matter, and cerebrospinal fluid (CSF). Coefficient of variation (CoV) of the repeated measurements as a measure of intra-subject reliability was calculated. Intraclass correlation coefficient (ICC) with regard to increasing CS-factor was calculated as another measure of reliability. Noise-to-contrast ratio as a measure of image quality was calculated for each dataset to analyze the association between acceleration factor, noise and volumetric brain measurements. RESULTS: For all sub-volumes, there is a systematic bias proportional to the CS-factor which is dependent on the utilized software and subvolume. Measured volumes deviated significantly from the reference standard (CS-factor = 1), e.g. ranging from 1 to 13% for BP. The CS-induced systematic bias is driven by increased image noise. Except for CSF, reliability of brain volumetry remains high, demonstrated by low CoV (< 1% for CS-factor up to 20) and good to excellent ICC for CS-factor up to 12. CONCLUSION: CS-acceleration has a systematic biasing effect on volumetric brain measurements.

MRI-Derived Radiomics Features of Hepatic Fat Predict Metabolic States in Individuals without Cardiovascular Disease.

RATIONALE AND OBJECTIVES: To investigate radiomics features of hepatic fat as potential biomarkers of type 2 diabetes mellitus (T2DM) and metabolic syndrome (MetS) in individuals without overt cardiovascular disease, and benchmarking against hepatic proton density fat fraction (PDFF) and the body mass index (BMI). MATERIALS AND METHODS: This study collected liver radiomics features of 310 individuals that were part of a case-controlled imaging substudy embedded in a prospective cohort. Individuals had known T2DM (n = 39; 12.6 %) and MetS (n = 107; 34.5 %) status, and were divided into stratified training (n = 232; 75 %) and validation (n = 78; 25 %) sets. Six hundred eighty-four MRI radiomics features were extracted for each liver volume of interest (VOI) on T1-weighted dual-echo Dixon relative fat water content (rfwc) maps. Test-retest and inter-rater variance was simulated by additionally extracting radiomics features using noise augmented rfwc maps and deformed volume of interests. One hundred and seventy-one features with test-retest reliability (ICC(1,1)) and inter-rater agreement (ICC(3,k)) of ≥0.85 on the training set were considered stable. To construct predictive random forest (RF) models, stable features were filtered using univariate RF analysis followed by sequential forward aggregation. The predictive performance was evaluated on the independent validation set with area under the curve of the receiver operating characteristic (AUROC) and balanced accuracy (AccuracyB). RESULTS: On the validation set, the radiomics RF models predicted T2DM with AUROC of 0.835 and AccuracyB of 0.822 and MetS with AUROC of 0.838 and AccuracyB of 0.787, outperforming the RF models trained on the benchmark parameters PDFF and BMI. CONCLUSION: Hepatic radiomics features may serve as potential imaging biomarkers for T2DM and MetS.

Discriminative and generative models for anatomical shape analysis on point clouds with deep neural networks.

We introduce deep neural networks for the analysis of anatomical shapes that learn a low-dimensional shape representation from the given task, instead of relying on hand-engineered representations. Our framework is modular and consists of several computing blocks that perform fundamental shape processing tasks. The networks operate on unordered point clouds and provide invariance to similarity transformations, avoiding the need to identify point correspondences between shapes. Based on the framework, we assemble a discriminative model for disease classification and age regression, as well as a generative model for the accruate reconstruction of shapes. In particular, we propose a conditional generative model, where the condition vector provides a mechanism to control the generative process. For instance, it enables to assess shape variations specific to a particular diagnosis, when passing it as side information. Next to working on single shapes, we introduce an extension for the joint analysis of multiple anatomical structures, where the simultaneous modeling of multiple structures can lead to a more compact encoding and a better understanding of disorders. We demonstrate the advantages of our framework in comprehensive experiments on real and synthetic data. The key insights are that (i) learning a shape representation specific to the given task yields higher performance than alternative shape descriptors, (ii) multi-structure analysis is both more efficient and more accurate than single-structure analysis, and (iii) point clouds generated by our model capture morphological differences associated to Alzheimer's disease, to the point that they can be used to train a discriminative model for disease classification. Our framework naturally scales to the analysis of large datasets, giving it the potential to learn characteristic variations in large populations.

Detect and correct bias in multi-site neuroimaging datasets.

The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence for the presence of bias by showing that scans can be correctly assigned to their respective dataset with 71.5% accuracy. Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies. In practice, we neither know all potential confounders nor do we have data on them. Hence, we model confounders as unknown, latent variables. Kolmogorov complexity is then used to decide whether the confounded or the causal model provides the simplest factorization of the graphical model. Finally, we present methods for dataset harmonization and study their ability to remove bias in imaging features. In particular, we propose an extension of the recently introduced ComBat algorithm to control for global variation across image features, inspired by adjusting for unknown population stratification in genetics. Our results demonstrate that harmonization can reduce dataset-specific information in image features. Further, confounding bias can be reduced and even turned into a causal relationship. However, harmonization also requires caution as it can easily remove relevant subject-specific information. Code is available at https://github.com/ai-med/Dataset-Bias.

Increased hippocampal shape asymmetry and volumetric ventricular asymmetry in autism spectrum disorder.

Autism spectrum disorder (ASD) is a prevalent and fast-growing pervasive neurodevelopmental disorder worldwide. Despite the increasing prevalence of ASD and the breadth of research conducted on the disorder, a conclusive etiology has yet to be established and controversy still exists surrounding the anatomical abnormalities in ASD. In particular, structural asymmetries have seldom been investigated in ASD, especially in subcortical regions. Additionally, the majority of studies for identifying structural biomarkers associated with ASD have focused on small sample sizes. Therefore, the present study utilizes a large-scale, multi-site database to investigate asymmetries in the amygdala, hippocampus, and lateral ventricles, given the potential involvement of these regions in ASD. Contrary to prior work, we are not only computing volumetric asymmetries, but also shape asymmetries, using a new measure of asymmetry based on spectral shape descriptors. This measure represents the magnitude of the asymmetry and therefore captures both directional and undirectional asymmetry. The asymmetry analysis is conducted on 437 individuals with ASD and 511 healthy controls using T1-weighted MRI scans from the Autism Brain Imaging Data Exchange (ABIDE) database. Results reveal significant asymmetries in the hippocampus and the ventricles, but not in the amygdala, in individuals with ASD. We observe a significant increase in shape asymmetry in the hippocampus, as well as increased volumetric asymmetry in the lateral ventricles in individuals with ASD. Asymmetries in these regions have not previously been reported, likely due to the different characterization of neuroanatomical asymmetry and smaller sample sizes used in previous studies. Given that these results were demonstrated in a large cohort, such asymmetries may be worthy of consideration in the development of neurodiagnostic classification tools for ASD.

Recalibrating 3D ConvNets with Project & Excite.

Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for segmentation tasks in computer vision and medical imaging. Recently, computational blocks termed squeeze and excitation (SE) have been introduced to recalibrate F-CNN feature maps both channel- and spatial-wise, boosting segmentation performance while only minimally increasing the model complexity. So far, the development of SE blocks has focused on 2D architectures. For volumetric medical images, however, 3D F-CNNs are a natural choice. In this article, we extend existing 2D recalibration methods to 3D and propose a generic compress-process-recalibrate pipeline for easy comparison of such blocks. We further introduce Project & Excite (PE) modules, customized for 3D networks. In contrast to existing modules, Project & Excite does not perform global average pooling but compresses feature maps along different spatial dimensions of the tensor separately to retain more spatial information that is subsequently used in the excitation step. We evaluate the modules on two challenging tasks, whole-brain segmentation of MRI scans and whole-body segmentation of CT scans. We demonstrate that PE modules can be easily integrated into 3D F-CNNs, boosting performance up to 0.3 in Dice Score and outperforming 3D extensions of other recalibration blocks, while only marginally increasing the model complexity. Our code is publicly available on https://github.com/ai-med/squeezeandexcitation.

Neuroimage signature from salient keypoints is highly specific to individuals and shared by close relatives.

Neuroimaging studies typically adopt a common feature space for all data, which may obscure aspects of neuroanatomy only observable in subsets of a population, e.g. cortical folding patterns unique to individuals or shared by close relatives. Here, we propose to model individual variability using a distinctive keypoint signature: a set of unique, localized patterns, detected automatically in each image by a generic saliency operator. The similarity of an image pair is then quantified by the proportion of keypoints they share using a novel Jaccard-like measure of set overlap. Experiments demonstrate the keypoint method to be highly efficient and accurate, using a set of 7536 T1-weighted MRIs pooled from four public neuroimaging repositories, including twins, non-twin siblings, and 3334 unique subjects. All same-subject image pairs are identified by a similarity threshold despite confounds including aging and neurodegenerative disease progression. Outliers reveal previously unknown data labeling inconsistencies, demonstrating the usefulness of the keypoint signature as a computational tool for curating large neuroimage datasets.