Microstructural abnormalities of white matter in the cingulum bundle of adolescents with major depression and non-suicidal self-injury.

BACKGROUND: Non-suicidal self-injury (NSSI) is prevalent in major depressive disorder (MDD) during adolescence, but the underlying neural mechanisms are unclear. This study aimed to investigate microstructural abnormalities in the cingulum bundle associated with NSSI and its clinical characteristics. METHODS: 130 individuals completed the study, including 35 healthy controls, 47 MDD patients with NSSI, and 48 MDD patients without NSSI. We used tract-based spatial statistics (TBSS) with a region of interest (ROI) analysis to compare the fractional anisotropy (FA) of the cingulum bundle across the three groups. receiver-operating characteristics (ROC) analysis was employed to evaluate the ability of the difficulties with emotion regulation (DERS) score and mean FA of the cingulum to differentiate between the groups. RESULTS: MDD patients with NSSI showed reduced cingulum integrity in the left dorsal cingulum compared to MDD patients without NSSI and healthy controls. The severity of NSSI was negatively associated with cingulum integrity (r = -0.344, p = 0.005). Combining cingulum integrity and DERS scores allowed for successful differentiation between MDD patients with and without NSSI, achieving a sensitivity of 70% and specificity of 83%. CONCLUSIONS: Our study highlights the role of the cingulum bundle in the development of NSSI in adolescents with MDD. The findings support a frontolimbic theory of emotion regulation and suggest that cingulum integrity and DERS scores may serve as potential early diagnostic tools for identifying MDD patients with NSSI.

Prediction of Early Antidepressant Efficacy in Patients with Major Depressive Disorder Based on Multidimensional Features of rs-fMRI and P11 Gene DNA Methylation: Prédiction de l'efficacité précoce d'un antidépresseur chez des patients souffrant du trouble dépressif majeur d'après les caractéristiques multidimensionnelles de la méthylation de l'ADN du gène P11 et de la IRMf-rs.

OBJECTIVE: This study established a machine learning model based on the multidimensional data of resting-state functional activity of the brain and P11 gene DNA methylation to predict the early efficacy of antidepressant treatment in patients with major depressive disorder (MDD). METHODS: A total of 98 Han Chinese MDD were analysed in this study. Patients were divided into 51 responders and 47 nonresponders according to whether the Hamilton Depression Rating Scale-17 items (HAMD-17) reduction rate was ≥50% after 2 weeks of antidepressant treatment. At baseline, the Illumina HiSeq Platform was used to detect the methylation of 74 CpG sites of the P11 gene in peripheral blood samples. Resting-state functional magnetic resonance imaging (rs-fMRI) scan detected the amplitude of low-frequency fluctuations (ALFF), regional homogeneity (ReHo), and functional connectivity (FC) in 116 brain regions. The least absolute shrinkage and selection operator analysis method was used to perform feature reduction and feature selection. Four typical machine learning methods were used to establish support vector machine (SVM), random forest (RF), Naïve Bayes (NB), and logistic regression (LR) prediction models based on different combinations of functional activity of the brain, P11 gene DNA methylation and clinical/demographic features after screening. RESULTS: The SVM model based on ALFF, ReHo, FC, P11 methylation, and clinical/demographic features showed the best performance, with 95.92% predictive accuracy and 0.9967 area under the receiver operating characteristic curve, which was better than RF, NB, and LR models. CONCLUSION: The multidimensional data features combining rs-fMRI, DNA methylation, and clinical/demographic features can predict the early antidepressant efficacy in MDD.

Transcriptome Regulation by Oncogenic ALK Pathway in Mammalian Cortical Development Revealed by Single-Cell RNA Sequencing.

Precise regulation of embryonic neurodevelopment is crucial for proper structural organization and functioning of the adult brain. The key molecular machinery orchestrating this process remains unclear. Anaplastic lymphoma kinase (ALK) is an oncogenic receptor-type protein tyrosine kinase that is specifically and transiently expressed in developing nervous system. However, its role in the mammalian brain development is unknown. We found that transient embryonic ALK inactivation caused long-lasting abnormalities in the adult mouse brain, including impaired neuronal connectivity and cognition, along with delayed neuronal migration and decreased neuronal proliferation during neurodevelopment. scRNA-seq on human cerebral organoids revealed a delayed transition of cell-type composition. Molecular characterization identified a group of differentially expressed genes (DEGs) that were temporally regulated by ALK at distinct developmental stages. In addition to oncogenes, many DEGs found by scRNA-seq are associated with neurological or neuropsychiatric disorders. Our study demonstrates a pivotal role of oncogenic ALK pathway in neurodevelopment and characterized cell-type-specific transcriptome regulated by ALK for better understanding mammalian cortical development.

Spatio-temporal graph convolutional network for diagnosis and treatment response prediction of major depressive disorder from functional connectivity.

The pathophysiology of major depressive disorder (MDD) has been explored to be highly associated with the dysfunctional integration of brain networks. It is therefore imperative to explore neuroimaging biomarkers to aid diagnosis and treatment. In this study, we developed a spatiotemporal graph convolutional network (STGCN) framework to learn discriminative features from functional connectivity for automatic diagnosis and treatment response prediction of MDD. Briefly, dynamic functional networks were first obtained from the resting-state fMRI with the sliding temporal window method. Secondly, a novel STGCN approach was proposed by introducing the modules of spatial graph attention convolution (SGAC) and temporal fusion. A novel SGAC was proposed to improve the feature learning ability and special anatomy prior guided pooling was developed to enable the feature dimension reduction. A temporal fusion module was proposed to capture the dynamic features of functional connectivity between adjacent sliding windows. Finally, the STGCN proposed approach was utilized to the tasks of diagnosis and antidepressant treatment response prediction for MDD. Performances of the framework were comprehensively examined with large cohorts of clinical data, which demonstrated its effectiveness in classifying MDD patients and predicting the treatment response. The sound performance suggests the potential of the STGCN for the clinical use in diagnosis and treatment prediction.

Desynchronized Functional Activities Between Brain White and Gray Matter in Major Depression Disorder.

BACKGROUND: Alterations in gray matter (GM) have been recognized as playing an important role in the neurobiological mechanism underlying major depressive disorder (MDD) and antidepressant responses. However, little is known about white matter (WM) connectivity in MDD, leaving an incomplete understanding of the pathophysiology of the disorder. PURPOSE: To examine the functional connectivity (FC) of WM, GM, and WM-GM in MDD patients and explore the relationship between FC and antidepressant response. STUDY TYPE: Longitudinal study. SUBJECTS: In all, 129 MDD patients and 89 healthy controls (HC). FIELD STRENGTH/SEQUENCE: Whole-brain blood oxygen level-dependent (BOLD) single-shot echo planar imaging was acquired at 3.0T. ASSESSMENT: At baseline, all participants received Hamilton depression rating scale (HAMD) assessment and an fMRI scan. After 2- and 8-week antidepressant treatment, patients completed the HAMD again. The HAMD reductive rate of 2- and 8-weeks were calculated. STATISTICAL TESTS: The comparisons of age, education, HAMD scores, and FC values (false discovery rate correction) between patients and controls were calculated with a two-sample t-test. The chi-square test was employed to compare the differences of gender between these two groups. Correlations between FC and HAMD, as well as the reductive rate of HAMD, were analyzed with Pearson or Spearman correlation. Receiver operator curve analysis was performed to predict the antidepressant response. RESULTS: Compared to HC, MDD patients exhibited widespread decreases in FC of WM-GM. Furthermore, 28 GM regions and 11 WM bundles had lower connectivity in MDD patients. At baseline, four FC of WM-GM showed negative correlations with the HAMD scores. Six FC of WM-GM correlated with the 2-week reductive rate of HAMD. Moreover, FC in GM, WM, and WM-GM also exhibited significantly positive correlations with an 8-week reductive rate of HAMD. DATA CONCLUSION: The FC of WM-GM was decreased in MDD and may play a role in its pathophysiology and antidepressant responses. LEVEL OF EVIDENCE: 2. TECHNICAL EFFICACY STAGE: 2.

Automatic brain tissue segmentation based on graph filter.

BACKGROUND: Accurate segmentation of brain tissues from magnetic resonance imaging (MRI) is of significant importance in clinical applications and neuroscience research. Accurate segmentation is challenging due to the tissue heterogeneity, which is caused by noise, bias filed and partial volume effects. METHODS: To overcome this limitation, this paper presents a novel algorithm for brain tissue segmentation based on supervoxel and graph filter. Firstly, an effective supervoxel method is employed to generate effective supervoxels for the 3D MRI image. Secondly, the supervoxels are classified into different types of tissues based on filtering of graph signals. RESULTS: The performance is evaluated on the BrainWeb 18 dataset and the Internet Brain Segmentation Repository (IBSR) 18 dataset. The proposed method achieves mean dice similarity coefficient (DSC) of 0.94, 0.92 and 0.90 for the segmentation of white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) for BrainWeb 18 dataset, and mean DSC of 0.85, 0.87 and 0.57 for the segmentation of WM, GM and CSF for IBSR18 dataset. CONCLUSIONS: The proposed approach can well discriminate different types of brain tissues from the brain MRI image, which has high potential to be applied for clinical applications.

[Research on effective connectivity of intracerebral electroencephalogram based on Wiener-Granger Causality Index modified by generalized Akaike's Information Criterion].

The objective is to deal with brain effective connectivity among epilepsy electroencephalogram (EEG) signals recorded by use of depth electrodes in the cerebral cortex of patients suffering from refractory epilepsy during their epileptic seizures. The Wiener-Granger Causality Index (WGCI) is a well-known effective measure that can be useful to detect causal relations of interdependence in these kinds of EEG signals. It is based on the linear autoregressive model, and the issue of the estimation of the model parameters plays an important role in the calculation accuracy and robustness of WGCI to do research on brain effective connectivity. Focusing on this issue, a modified Akaike's information criterion algorithm is introduced in the computation of the WGCI to estimate the orders involved in the underlying models and in order to advance the performance of WGCI to detect brain effective connectivity. Experimental results support the interesting performance of the proposed algorithm to characterize the information flow both in a linear stochastic system and a physiology-based model.

Noise reduction of diffusion tensor images by sparse representation and dictionary learning.

BACKGROUND: The low quality of diffusion tensor image (DTI) could affect the accuracy of oncology diagnosis. METHODS: We present a novel sparse representation based denoising method for three dimensional DTI by learning adaptive dictionary with the context redundancy between neighbor slices. In this study, the context redundancy among the adjacent slices of the diffusion weighted imaging volumes is utilized to train sparsifying dictionaries. Therefore, higher redundancy could be achieved for better description of image with lower computation complexity. The optimization problem is solved efficiently using an iterative block-coordinate relaxation method. RESULTS: The effectiveness of our proposed method has been assessed on both simulated and real experimental DTI datasets. Qualitative and quantitative evaluations demonstrate the performance of the proposed method on the simulated data. The experiments on real datasets with different b-values also show the effectiveness of the proposed method for noise reduction of DTI. CONCLUSIONS: The proposed approach well removes the noise in the DTI, which has high potential to be applied for clinical oncology applications.

STANet: Spatio-Temporal Adaptive Network and Clinical Prior Embedding Learning for 3D+T CMR Segmentation.

The segmentation of cardiac structure in magnetic resonance images (CMR) is paramount in diagnosing and managing cardiovascular illnesses, given its 3D+Time (3D+T) sequence. The existing deep learning methods are constrained in their ability to 3D+T CMR segmentation, due to: (1) Limited motion perception. The complexity of heart beating renders the motion perception in 3D+T CMR, including the long-range and cross-slice motions. The existing methods' local perception and slice-fixed perception directly limit the performance of 3D+T CMR perception. (2) Lack of labels. Due to the expensive labeling cost of the 3D+T CMR sequence, the labels of 3D+T CMR only contain the end-diastolic and end-systolic frames. The incomplete labeling scheme causes inefficient supervision. Hence, we propose a novel spatio-temporal adaptation network with clinical prior embedding learning (STANet) to ensure efficient spatio-temporal perception and optimization on 3D+T CMR segmentation. (1) A spatio-temporal adaptive convolution (STAC) treats the 3D+T CMR sequence as a whole for perception. The long-distance motion correlation is embedded into the structural perception by learnable weight regularization to balance long-range motion perception. The structural similarity is measured by cross-attention to adaptively correlate the cross-slice motion. (2) A clinical prior embedding learning strategy (CPE) is proposed to optimize the partially labeled 3D+T CMR segmentation dynamically by embedding clinical priors into optimization. STANet achieves outstanding performance with Dice of 0.917 and 0.94 on two public datasets (ACDC and STACOM), which indicates STANet has the potential to be incorporated into computer-aided diagnosis tools for clinical application.

Multi-Scale Spatial-Temporal Attention Networks for Functional Connectome Classification.

Many neuropsychiatric disorders are considered to be associated with abnormalities in the functional connectivity networks of the brain. The research on the classification of functional connectivity can therefore provide new perspectives for understanding the pathology of disorders and contribute to early diagnosis and treatment. Functional connectivity exhibits a nature of dynamically changing over time, however, the majority of existing methods are unable to collectively reveal the spatial topology and time-varying characteristics. Furthermore, despite the efforts of limited spatial-temporal studies to capture rich information across different spatial scales, they have not delved into the temporal characteristics among different scales. To address above issues, we propose a novel Multi-Scale Spatial-Temporal Attention Networks (MSSTAN) to exploit the multi-scale spatial-temporal information provided by functional connectome for classification. To fully extract spatial features of brain regions, we propose a Topology Enhanced Graph Transformer module to guide the attention calculations in the learning of spatial features by incorporating topology priors. A Multi-Scale Pooling Strategy is introduced to obtain representations of brain connectome at various scales. Considering the temporal dynamic characteristics between dynamic functional connectome, we employ Locality Sensitive Hashing attention to further capture long-term dependencies in time dynamics across multiple scales and reduce the computational complexity of the original attention mechanism. Experiments on three brain fMRI datasets of MDD and ASD demonstrate the superiority of our proposed approach. In addition, benefiting from the attention mechanism in Transformer, our results are interpretable, which can contribute to the discovery of biomarkers. The code is available at https://github.com/LIST-KONG/MSSTAN.

A deep learning model for translating CT to ventilation imaging: analysis of accuracy and impact on functional avoidance radiotherapy planning.

PURPOSE: Radiotherapy planning incorporating functional lung images has the potential to reduce pulmonary toxicity. Free-breathing 4DCT-derived ventilation image (CTVI) may help quantify lung function. This study introduces a novel deep-learning model directly translating planning CT images into CTVI. We investigated the accuracy of generated images and the impact on functional avoidance planning. MATERIALS AND METHODS: Paired planning CT and 4DCT scans from 48 patients with NSCLC were randomized to training (n = 41) and testing (n = 7) data sets. The ventilation maps were generated from 4DCT using a Jacobian-based algorithm to provide ground truth labels (CTVI4DCT). A 3D U-Net-based model was trained to map CT to synthetic CTVI (CTVISyn) and validated using fivefold cross-validation. The highest-performing model was applied to the testing set. Spearman's correlation (rs) and Dice similarity coefficient (DSC) determined voxel-wise and functional-wise concordance between CTVI4DCT and CTVISyn. Three plans were designed per patient in the testing set: one clinical plan without CTVI and two functional avoidance plans combined with CTVI4DCT or CTVISyn, aimed at sparing high-functional lungs defined as the top 50% of the percentile ventilation ranges. Dose-volume (DVH) parameters regarding the planning target volume (PTV) and organs at risk (OARs) were recorded. Radiation pneumonitis (RP) risk was estimated using a dose-function (DFH)-based normal tissue complication probability (NTCP) model. RESULTS: CTVISyn showed a mean rs value of 0.65 ± 0.04 compared to CTVI4DCT. Mean DSC values over the top 50% and 60% of ventilation ranges were 0.41 ± 0.07 and 0.52 ± 0.10, respectively. In the test set (n = 7), all patients' RP-risk benefited from CTVI4DCT-guided plans (Riskmean_4DCT_vs_Clinical: 29.24% vs. 49.12%, P = 0.016), and six patients benefited from CTVISyn-guided plans (Riskmean_Syn_vs_Clinical: 31.13% vs. 49.12%, P = 0.022). There were no significant differences in DVH and DFH metrics between CTVISyn and CTVI4DCT-guided plan (P > 0.05). CONCLUSION: Using deep-learning techniques, CTVISyn generated from planning CT exhibited a moderate-to-high correlation with CTVI4DCT. The CTVISyn-guided plans were comparable to the CTVI4DCT-guided plans, effectively reducing pulmonary toxicity in patients while maintaining acceptable plan quality. Further prospective trials are needed to validate these findings.

Dual circuits originating from the ventral hippocampus independently facilitate affective empathy.

Affective empathy enables social mammals to learn and transfer emotion to conspecifics, but an understanding of the neural circuitry and genetics underlying affective empathy is still very limited. Here, using the naive observational fear between cagemates as a paradigm similar to human affective empathy and chemo/optogenetic neuroactivity manipulation in mouse brain, we investigate the roles of multiple brain regions in mouse affective empathy. Remarkably, two neural circuits originating from the ventral hippocampus, previously unknown to function in empathy, are revealed to regulate naive observational fear. One is from ventral hippocampal pyramidal neurons to lateral septum GABAergic neurons, and the other is from ventral hippocampus pyramidal neurons to nucleus accumbens dopamine-receptor-expressing neurons. Furthermore, we identify the naive observational-fear-encoding neurons in the ventral hippocampus. Our findings highlight the potentially diverse regulatory pathways of empathy in social animals, shedding light on the mechanisms underlying empathy circuity and its disorders.

Multi-Connectivity Representation Learning Network for Major Depressive Disorder Diagnosis.

The pathophysiology of major depressive disorder (MDD) has been demonstrated to be highly associated with the dysfunctional integration of brain activity. Existing studies only fuse multi-connectivity information in a one-shot approach and ignore the temporal property of functional connectivity. A desired model should utilize the rich information in multiple connectivities to help improve the performance. In this study, we develop a multi-connectivity representation learning framework to integrate multi-connectivity topological representation from structural connectivity, functional connectivity and dynamic functional connectivities for automatic diagnosis of MDD. Briefly, structural graph, static functional graph and dynamic functional graphs are first computed from the diffusion magnetic resonance imaging (dMRI) and resting state functional magnetic resonance imaging (rsfMRI). Secondly, a novel Multi-Connectivity Representation Learning Network (MCRLN) approach is developed to integrate the multiple graphs with modules of structural-functional fusion and static-dynamic fusion. We innovatively design a Structural-Functional Fusion (SFF) module, which decouples graph convolution to capture modality-specific features and modality-shared features separately for an accurate brain region representation. To further integrate the static graphs and dynamic functional graphs, a novel Static-Dynamic Fusion (SDF) module is developed to pass the important connections from static graphs to dynamic graphs via attention values. Finally, the performance of the proposed approach is comprehensively examined with large cohorts of clinical data, which demonstrates its effectiveness in classifying MDD patients. The sound performance suggests the potential of the MCRLN approach for the clinical use in diagnosis. The code is available at https://github.com/LIST-KONG/MultiConnectivity-master.

Predicting treatment response in adolescents and young adults with major depressive episodes from fMRI using graph isomorphism network.

BACKGROUND: Major depressive episode (MDE) is the main clinical feature of mood disorders (major depressive disorder and bipolar disorder) in adolescents and young adults and accounts for most of the disease course. However, 30%-40% of MDE patients not responding to clinical first-line interventions. It is crucial to predict treatment response in the early stages and identify biomarkers associated with treatment response. Graph Isomorphism Network (GIN), a deep learning method, is promising for predicting treatment response for individual MDE patients with more powerful representation ability to capture the features of brain functional connectivity. METHODS: In this study, GIN was used to predict individual treatment response in 198 adolescents and young adults with MDE. The most discriminating regions were also identified for the treatment response prediction. RESULTS: Using GIN approach, the baseline functional connectivity could predict 79.8% responders and 67.4% non-responders to treatment (accuracy 74.24%). Furthermore, the most discriminating brain regions were mainly involved in paralimbic and subcortical areas. CONCLUSIONS: GIN has shown potential in predicting treatment response for individual patients, which may enable personalized treatment decisions. Furthermore, targeted interventions focused on modulating the activity and connectivity within paralimbic and subcortical regions could potentially improve treatment outcomes and enable personalized interventions for adolescents and young adults with MDE.

Linking individual variability in functional brain connectivity to polygenic risk in major depressive disorder.

BACKGROUND: Major depressive disorder (MDD) is a highly heterogeneous disease, which brings great difficulties to clinical diagnosis and therapy. Its mechanism is still unknown. Prior neuroimaging studies mainly focused on mean differences between patients and healthy controls (HC), largely ignoring individual differences between patients. METHODS: This study included 112 MDD patients and 93 HC subjects. Resting-state functional MRI data were obtained to examine the patterns of individual variability of brain functional connectivity (IVFC). The genetic risk of pathways including dopamine, 5-hydroxytryptamine (5-HT), norepinephrine (NE), hypothalamic-pituitary-adrenal (HPA) axis, and synaptic plasticity was assessed by multilocus genetic profile scores (MGPS), respectively. RESULTS: The IVFC pattern of the MDD group was similar but higher than that in HCs. The inter-network functional connectivity in the default mode network contributed to altered IVFC in MDD. 5-HT, NE, and HPA pathway genes affected IVFC in MDD patients. The age of onset, duration, severity, and treatment response, were correlated with IVFC. IVFC in the left ventromedial prefrontal cortex had a mediating effect between MGPS of the 5-HT pathway and baseline depression severity. LIMITATIONS: Environmental factors and differences in locations of functional areas across individuals were not taken into account. CONCLUSIONS: This study found MDD patients had significantly different inter-individual functional connectivity variations than healthy people, and genetic risk might affect clinical manifestations through brain function heterogeneity.

CMF-Net: craniomaxillofacial landmark localization on CBCT images using geometric constraint and transformer.

Accurate and robust anatomical landmark localization is a mandatory and crucial step in deformation diagnosis and treatment planning for patients with craniomaxillofacial (CMF) malformations. In this paper, we propose a trainable end-to-end cephalometric landmark localization framework on Cone-beam computed tomography (CBCT) scans, referred to as CMF-Net, which combines the appearance with transformers, geometric constraint, and adaptive wing (AWing) loss. More precisely: (1) we decompose the localization task into two branches: the appearance branch integrates transformers for identifying the exact positions of candidates, while the geometric constraint branch at low resolution allows the implicit spatial relationships to be effectively learned on the reduced training data. (2) We use the AWing loss to leverage the difference between the pixel values of the target heatmaps and the automatic prediction heatmaps. We verify our CMF-Net by identifying the 24 most relevant clinical landmarks on 150 dental CBCT scans with complicated scenarios collected from real-world clinics. Comprehensive experiments show that it performs better than the state-of-the-art deep learning methods, with an average localization error of 1.108 mm (the clinically acceptable precision range being 1.5 mm) and a correct landmark detection rate equal to 79.28%. Our CMF-Net is time-efficient and able to locate skull landmarks with high accuracy and significant robustness. This approach could be applied in 3D cephalometric measurement, analysis, and surgical planning.

Auto-segmentation of important centers of growth in the pediatric skeleton to consider during radiation therapy based on deep learning.

BACKGROUND: Routinely delineating of important skeletal growth centers is imperative to mitigate radiation-induced growth abnormalities for pediatric cancer patients treated with radiotherapy. However, it is hindered by several practical problems, including difficult identification, time consumption, and inter-practitioner variability. PURPOSE: The goal of this study was to construct and evaluate a novel Triplet-Attention U-Net (TAU-Net)-based auto-segmentation model for important skeletal growth centers in childhood cancer radiotherapy, concentrating on the accuracy and time efficiency. METHODS: A total of 107 childhood cancer patients fulfilled the eligibility criteria were enrolled in the training cohort (N = 80) and test cohort (N = 27). The craniofacial growth plates, shoulder growth centers, and pelvic ossification centers, with a total of 19 structures in the three groups, were manually delineated by two experienced radiation oncologists on axial, coronal, and sagittal computed tomography images. Modified from U-Net, the proposed TAU-Net has one main branch and two bypass branches, receiving semantic information of three adjacent slices to predict the target structure. With supervised deep learning, the skeletal growth centers contouring of each group was generated by three different auto-segmentation models: U-Net, V-Net, and the proposed TAU-Net. Dice similarity coefficient (DSC) and Hausdorff distance 95% (HD95) were used to evaluate the accuracy of three auto-segmentation models. The time spent on performing manual tasks and manually correcting auto-contouring generated by TAU-Net was recorded. The paired t-test was used to compare the statistical differences in delineation quality and time efficiency. RESULTS: Among the three groups, including craniofacial growth plates, shoulder growth centers, and pelvic ossification centers groups, TAU-Net had demonstrated highly acceptable performance (the average DSC = 0.77, 0.87, and 0.83 for each group; the average HD95 = 2.28, 2.07, and 2.86 mm for each group). In the overall evaluation of 19 regions of interest (ROIs) in the test cohort, TAU-Net had an overwhelming advantage over U-Net (63.2% ROIs in DSC and 31.6% ROIs in HD95, p = 0.001-0.042) and V-Net (94.7% ROIs in DSC and 36.8% ROIs in HD95, p = 0.001-0.040). With an average time of 52.2 min for manual delineation, the average time saved to adjust TAU-Net-generated contours was 37.6 min (p < 0.001), a 72% reduction. CONCLUSIONS: Deep learning-based models have presented enormous potential for the auto-segmentation of important growth centers in pediatric skeleton, where the proposed TAU-Net outperformed the U-Net and V-Net in geometrical precision for the majority status.

Landmark Localization for Cephalometric Analysis Using Multiscale Image Patch-Based Graph Convolutional Networks.

Accurate and robust cephalometric image analysis plays an essential role in orthodontic diagnosis, treatment assessment and surgical planning. This paper proposes a novel landmark localization method for cephalometric analysis using multiscale image patch-based graph convolutional networks. In detail, image patches with the same size are hierarchically sampled from the Gaussian pyramid to well preserve multiscale context information. We combine local appearance and shape information into spatialized features with an attention module to enrich node representations in graph. The spatial relationships of landmarks are built with the incorporation of three-layer graph convolutional networks, and multiple landmarks are simultaneously updated and moved toward the targets in a cascaded coarse-to-fine process. Quantitative results obtained on publicly available cephalometric X-ray images have exhibited superior performance compared with other state-of-the-art methods in terms of mean radial error and successful detection rate within various precision ranges. Our approach performs significantly better especially in the clinically accepted range of 2 mm and this makes it suitable in cephalometric analysis and orthognathic surgery.

Few-Shot Learning for Deformable Medical Image Registration With Perception-Correspondence Decoupling and Reverse Teaching.

Deformable medical image registration estimates corresponding deformation to align the regions of interest (ROIs) of two images to a same spatial coordinate system. However, recent unsupervised registration models only have correspondence ability without perception, making misalignment on blurred anatomies and distortion on task-unconcerned backgrounds. Label-constrained (LC) registration models embed the perception ability via labels, but the lack of texture constraints in labels and the expensive labeling costs causes distortion internal ROIs and overfitted perception. We propose the first few-shot deformable medical image registration framework, Perception-Correspondence Registration (PC-Reg), which embeds perception ability to registration models only with few labels, thus greatly improving registration accuracy and reducing distortion. 1) We propose the Perception-Correspondence Decoupling which decouples the perception and correspondence actions of registration to two CNNs. Therefore, independent optimizations and feature representations are available avoiding interference of the correspondence due to the lack of texture constraints. 2) For few-shot learning, we propose Reverse Teaching which aligns labeled and unlabeled images to each other to provide supervision information to the structure and style knowledge in unlabeled images, thus generating additional training data. Therefore, these data will reversely teach our perception CNN more style and structure knowledge, improving its generalization ability. Our experiments on three datasets with only five labels demonstrate that our PC-Reg has competitive registration accuracy and effective distortion-reducing ability. Compared with LC-VoxelMorph( λ = 1), we achieve the 12.5%, 6.3% and 1.0% Reg-DSC improvements on three datasets, revealing our framework with great potential in clinical application.

Identification of first-episode unmedicated major depressive disorder using pretreatment features of dominant coactivation patterns.

Identifying neuroimaging features to diagnose major depressive disorder (MDD) and predict treatment response remains challenging. Using the pretreatment dominant coactivation pattern (dCAP) analysis approach, we aimed to identify patients with MDD and predict antidepressant efficacy. Seventy-seven first-episode unmedicated MDD patients and forty-two age- and sex-matched healthy controls (HCs) were recruited in the study. The dCAP analysis was performed for the reward and default mode network (DMN) to identify the MDD patients from the HCs. The dCAP1 of the left posterior DMN and bilateral anterior DMN were significantly higher in the MDD group than in the HC group (P < .001), and the dCAP1 in the left posterior DMN was positively correlated with the baseline severity of depression (rho = 0.248, P = .030). Besides, the MDD group exhibited significantly higher dCAP1 in the right reward network than the HC group. Further correlation analyses revealed that the transfer probability in the right reward network was positively correlated with the treatment responsivity (r = 0.247, P = .030). Importantly, integrating the dCAPs of the above four subnetworks can effectively identify the patients with MDD (AUC = 0.920, P < .001). The distinct pretreatment features of the dCAP in the subnetwork of the DMN and reward network may serve as potential indicators for individual diagnosis and prediction of antidepressant response in the early stage.