RESUMEN
Resting-state functional connectivity (FC) is widely used in multivariate pattern analysis of functional magnetic resonance imaging (fMRI), including identifying the locations of putative brain functional borders, predicting individual phenotypes, and diagnosing clinical mental diseases. However, limited attention has been paid to the analysis of functional interactions from a frequency perspective. In this study, by contrasting coherence-based and correlation-based FC with two machine learning tasks, we observed that measuring FC in the frequency domain helped to identify finer functional subregions and achieve better pattern discrimination capability relative to the temporal correlation. This study has proven the feasibility of coherence in the analysis of fMRI, and the results indicate that modeling functional interactions in the frequency domain may provide richer information than that in the time domain, which may provide a new perspective on the analysis of functional neuroimaging.
Asunto(s)
Conectoma , Imagen por Resonancia Magnética , Humanos , Imagen por Resonancia Magnética/métodos , Conectoma/métodos , Adulto , Masculino , Femenino , Aprendizaje Automático , Adulto Joven , Encéfalo/fisiología , Encéfalo/diagnóstico por imagen , Red Nerviosa/diagnóstico por imagen , Red Nerviosa/fisiologíaRESUMEN
Edge enhancement, as an important part of image processing, has played an essential role in amplitude-contrast and phase-contrast object imaging. The edge enhancement of three-dimensional (3D) vortex imaging has been successfully implemented by Fresnel incoherent correlation holography (FINCH), but the background noise and image contrast effects are still not satisfactory. To solve these issues, the edge enhancement of FINCH by employing Bessel-like spiral phase modulation is proposed and demonstrated. Compared with the conventional spiral phase modulated FINCH, the proposed technique can achieve high-quality edge enhancement 3D vortex imaging with lower background noise, higher contrast and resolution. The significantly improved imaging quality is mainly attributed to the effective sidelobes' suppression in the generated optical vortices with the Bessel-like modulation technique. Experimental results of the small circular aperture, resolution target, and the Drosophila melanogaster verify its excellent imaging performance. Moreover, we also proposed a new method for selective edge enhancement of 3D vortex imaging by breaking the symmetry of the spiral phase in the algorithmic model of isotropic edge enhancement. The reconstructed images of the circular aperture show that the proposed method is able to enhance the edges of the given objects selectively in any desired direction.
RESUMEN
We proposed a three-dimensional (3D) ranging system based on Fresnel incoherent correlation holography (FINCH). Distinct from the displacement measurement based on coherent digital holography (DH), our system simultaneously achieves a 3D range measurement using incoherent illumination. The observation range is obtained by the holographic reconstruction, while the in-plane range is determined using the two-dimensional digital imaging correlation (2D-DIC) technique. Experimental results on the resolution target demonstrate precise 3D ranging determination and improved measurement accuracy.
RESUMEN
Limited sample size hinders the application of deep learning in brain image analysis, and transfer learning is a possible solution. However, most pretrained models are 2D based and cannot be applied directly to 3D brain images. In this study, we propose a novel framework to apply 2D pretrained models to 3D brain images by projecting surface-based cortical morphometry into planar images using computational geometry mapping. Firstly, 3D cortical meshes are reconstructed from magnetic resonance imaging (MRI) using FreeSurfer and projected into 2D planar meshes with topological preservation based on area-preserving geometry mapping. Then, 2D deep models pretrained on ImageNet are adopted and fine-tuned for cortical image classification on morphometric shape metrics. We apply the framework to sex classification on the Human Connectome Project dataset and autism spectrum disorder (ASD) classification on the Autism Brain Imaging Data Exchange dataset. Moreover, a 2-stage transfer learning strategy is suggested to boost the ASD classification performance by using the sex classification as an intermediate task. Our framework brings significant improvement in sex classification and ASD classification with transfer learning. In summary, the proposed framework builds a bridge between 3D cortical data and 2D models, making 2D pretrained models available for brain image analysis in cognitive and psychiatric neuroscience.
Asunto(s)
Trastorno del Espectro Autista , Trastorno del Espectro Autista/diagnóstico por imagen , Trastorno del Espectro Autista/patología , Encéfalo/patología , Mapeo Encefálico/métodos , Corteza Cerebral/diagnóstico por imagen , Humanos , Aprendizaje Automático , Imagen por Resonancia MagnéticaRESUMEN
OBJECTIVE: Cortical tremor/myoclonus is the hallmark feature of benign adult familial myoclonic epilepsy (BAFME), the mechanism of which remains elusive. A hypothesis is that a defective control in the preexisting cerebellar-motor loop drives cortical tremor. Meanwhile, the basal ganglia system might also participate in BAFME. This study aimed to discover the structural basis of cortical tremor/myoclonus in BAFME. METHODS: Nineteen patients with BAFME type 1 (BAFME1) and 30 matched healthy controls underwent T1-weighted and diffusion tensor imaging scans. FreeSurfer and spatially unbiased infratentorial template (SUIT) toolboxes were utilized to assess the motor cortex and the cerebellum. Probabilistic tractography was generated for two fibers to test the hypothesis: the dentato-thalamo-(M1) (primary motor cortex) and globus pallidus internus (GPi)-thalamic projections. Average fractional anisotropy (FA), axial diffusivity (AD), mean diffusivity (MD), and radial diffusivity (RD) of each tract were extracted. RESULTS: Cerebellar atrophy and dentate nucleus alteration were observed in the patients. In addition, patients with BAFME1 exhibited reduced AD and FA in the left and right dentato-thalamo-M1 nondecussating fibers, respectively false discovery rate (FDR) correction q < .05. Cerebellar projections showed negative correlations with somatosensory-evoked potential P25-N33 amplitude and were independent of disease duration and medication. BAFME1 patients also had increased FA and decreased MD in the left GPi-thalamic projection. Higher FA and lower RD in the right GPi-thalamic projection were also observed (FDR q < .05). SIGNIFICANCE: The present findings support the hypothesis that the cerebello-thalamo-M1 loop might be the structural basis of cortical tremor in BAFME1. The basal ganglia system also participates in BAFME1 and probably serves a regulatory role.
Asunto(s)
Imagen de Difusión Tensora , Epilepsias Mioclónicas , Humanos , Adulto , Epilepsias Mioclónicas/diagnóstico por imagenRESUMEN
Until now, dynamic functional connectivity (dFC) based on functional magnetic resonance imaging is typically estimated on a set of predefined regions of interest (ROIs) derived from an anatomical or static functional atlas which follows an implicit assumption of functional homogeneity within ROIs underlying temporal fluctuation of functional coupling, potentially leading to biases or underestimation of brain network dynamics. Here, we presented a novel computational method based on dynamic functional connectivity degree (dFCD) to derive meaningful brain parcellations that can capture functional homogeneous regions in temporal variance of functional connectivity. Several spatially distributed but functionally meaningful areas that are well consistent with known intrinsic connectivity networks were identified through independent component analysis (ICA) of time-varying dFCD maps. Furthermore, a systematical comparison with commonly used brain atlases, including the Anatomical Automatic Labeling template, static ICA-driven parcellation and random parcellation, demonstrated that the ROI-definition strategy based on the proposed dFC-driven parcellation could better capture the interindividual variability in dFC and predict observed individual cognitive performance (e.g., fluid intelligence, cognitive flexibility, and sustained attention) based on chronnectome. Together, our findings shed new light on the functional organization of resting brains at the timescale of seconds and emphasized the significance of a dFC-driven and voxel-wise functional homogeneous parcellation for network dynamics analyses in neuroscience.
Asunto(s)
Cerebelo , Corteza Cerebral , Conectoma/métodos , Red en Modo Predeterminado , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Red Nerviosa , Adulto , Atlas como Asunto , Cerebelo/diagnóstico por imagen , Cerebelo/fisiología , Corteza Cerebral/diagnóstico por imagen , Corteza Cerebral/fisiología , Conectoma/normas , Red en Modo Predeterminado/diagnóstico por imagen , Red en Modo Predeterminado/fisiología , Humanos , Procesamiento de Imagen Asistido por Computador/normas , Imagen por Resonancia Magnética/normas , Red Nerviosa/diagnóstico por imagen , Red Nerviosa/fisiología , Máquina de Vectores de Soporte , Factores de TiempoRESUMEN
Fresnel incoherent correlation holography (FINCH) shows great advantages of coherent-light-source-free, high lateral resolution, no scanning, and easy integration, and has exhibited great potential in recording three-dimensional information of objects. Despite the rapid advances in the resolution of the FINCH system, little attention has been paid to the influence of the effective aperture of the system. Here, the effective aperture of the point spread function (PSF) has been investigated both theoretically and experimentally. It is found that the effective aperture is mainly restricted by the aperture of the charge-coupled device (CCD), the pixel size of the CCD, and the actual aperture of the PSF at different recording distances. It is also found that the optimal spatial resolution exists only for a small range of recording distance, while this range would become smaller as the imaging wavelength gets longer, leading to the result that the optimal spatial resolution is solely determined by the actual aperture of the PSF. By further combining the FINCH system with a microscopy system and optimizing the recording distance, a spatial resolution as high as 0.78 µm at the wavelength of 633â nm has been obtained, enabling a much higher quality imaging of unstained living biological cells compared to the commercial optical microscope. The results of this work may provide some helpful insights into the design of high-resolution FINCH systems and pave the way for their application in biomedical imaging.
RESUMEN
OBJECTIVES: To develop and validate a machine learning model for the prediction of adverse outcomes in hospitalized patients with COVID-19. METHODS: We included 424 patients with non-severe COVID-19 on admission from January 17, 2020, to February 17, 2020, in the primary cohort of this retrospective multicenter study. The extent of lung involvement was quantified on chest CT images by a deep learning-based framework. The composite endpoint was the occurrence of severe or critical COVID-19 or death during hospitalization. The optimal machine learning classifier and feature subset were selected for model construction. The performance was further tested in an external validation cohort consisting of 98 patients. RESULTS: There was no significant difference in the prevalence of adverse outcomes (8.7% vs. 8.2%, p = 0.858) between the primary and validation cohorts. The machine learning method extreme gradient boosting (XGBoost) and optimal feature subset including lactic dehydrogenase (LDH), presence of comorbidity, CT lesion ratio (lesion%), and hypersensitive cardiac troponin I (hs-cTnI) were selected for model construction. The XGBoost classifier based on the optimal feature subset performed well for the prediction of developing adverse outcomes in the primary and validation cohorts, with AUCs of 0.959 (95% confidence interval [CI]: 0.936-0.976) and 0.953 (95% CI: 0.891-0.986), respectively. Furthermore, the XGBoost classifier also showed clinical usefulness. CONCLUSIONS: We presented a machine learning model that could be effectively used as a predictor of adverse outcomes in hospitalized patients with COVID-19, opening up the possibility for patient stratification and treatment allocation. KEY POINTS: ⢠Developing an individually prognostic model for COVID-19 has the potential to allow efficient allocation of medical resources. ⢠We proposed a deep learning-based framework for accurate lung involvement quantification on chest CT images. ⢠Machine learning based on clinical and CT variables can facilitate the prediction of adverse outcomes of COVID-19.
Asunto(s)
COVID-19 , Humanos , Aprendizaje Automático , Estudios Retrospectivos , SARS-CoV-2 , Tomografía Computarizada por Rayos XRESUMEN
This project aims to explore if stronger functional connectivity (FC) exists in the maximal BOLD response of EEG/fMRI analysis when it is concordant with seizure-onset-zone (SOZ). Twenty-six patients with drug-resistant focal epilepsy who had an EEG/fMRI and later underwent stereo-EEG implantation were included. Different types of IEDs were labeled in scalp EEG and IED-related maximal BOLD responses were evaluated separately, each constituting one study. After evaluating concordance between maximal BOLD and SOZ, twenty-seven studies were placed in the concordant group and eight in the discordant group. We evaluated the local connectivity and ipsilaterally distant connectivity difference between the maximal BOLD and the contralateral homotopic region. Significantly stronger local FC was found for the maximal BOLD in the concordant group (p < 0.05, Bonferroni corrected). 52% of the studies in the concordant group and 13% in the discordant group had a significant difference compared to healthy subjects (p < 0.05, uncorrected). The finding suggests that, when concordant with the SOZ, the maximal BOLD is more likely to have stronger local FC compared to its contralateral counterpart. This asymmetry in functional connectivity may help to noninvasively improve the specificity of EEG/fMRI analysis.
Asunto(s)
Encéfalo , Epilepsias Parciales , Imagen por Resonancia Magnética , Encéfalo/diagnóstico por imagen , Electroencefalografía , Epilepsias Parciales/diagnóstico por imagen , Humanos , Convulsiones/diagnóstico por imagenRESUMEN
Recently, resting-state functional magnetic resonance imaging (fMRI) studies have been extended to explore fluctuations in correlations over shorter timescales, referred to as dynamic functional connectivity (dFC). However, the impact of global signal regression (GSR) on dFC is not well established, despite the intensive investigations of the influence of GSR on static functional connectivity (sFC). This study aimed to examine the effect of GSR on the performance of the sliding-window correlation, a commonly used method for capturing functional connectivity (FC) dynamics based on resting-state fMRI and simultaneous electroencephalograph (EEG)-fMRI data. The results revealed that the impact of GSR on dFC was spatially heterogeneous, with some susceptible regions including the occipital cortex, sensorimotor area, precuneus, posterior insula and superior temporal gyrus, and that the impact was temporally modulated by the mean global signal (GS) magnitude across windows. Furthermore, GSR substantially changed the connectivity structures of the FC states responding to a high GS magnitude, as well as their temporal features, and even led to the emergence of new FC states. Conversely, those FC states marked by obvious anti-correlation structures associated with the default model network (DMN) were largely unaffected by GSR. Finally, we reported an association between the fluctuations in the windowed magnitude of GS and the time-varying EEG power within subjects, which implied changes in mental states underlying GS dynamics. Overall, this study suggested a potential neuropsychological basis, in addition to nuisance sources, for GS dynamics and highlighted the need for caution in applying GSR to sliding-window correlation analyses. At a minimum, the mental fluctuations of an individual subject, possibly related to ongoing vigilance, should be evaluated during the entire scan when the dynamics of FC is estimated.
Asunto(s)
Mapeo Encefálico/métodos , Encéfalo/fisiología , Modelos Neurológicos , Red Nerviosa/fisiología , Electroencefalografía/métodos , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Procesamiento de Señales Asistido por ComputadorRESUMEN
The cognitive and behavioral functions of the human brain are supported by its frequency multiplexing mechanism. However, there is limited understanding of the dynamics of the functional network topology. This study aims to investigate the frequency-specific topology of the functional human brain using 7T rs-fMRI data. Frequency-specific parcellations were first performed, revealing frequency-dependent dynamics within the frontoparietal control, parietal memory, and visual networks. An intrinsic functional atlas containing 456 parcels was proposed and validated using stereo-EEG. Graph theory analysis suggested that, in addition to the task-positive vs. task-negative organization observed in static networks, there was a cognitive control system additionally from a frequency perspective. The reproducibility and plausibility of the identified hub sets were confirmed through 3T fMRI analysis, and their artificial removal had distinct effects on network topology. These results indicate a more intricate and subtle dynamics of the functional human brain and emphasize the significance of accurate topography.
RESUMEN
Major depressive disorder is often characterized by changes in the structure and function of the brain, which are influenced by modifications in gene expression profiles. How the depression-related genes work together within the scope of time and space to cause pathological changes remains unclear. By integrating the brain-wide gene expression data and imaging data in major depressive disorder, we identified gene signatures of major depressive disorder and explored their temporal-spatial expression specificity, network properties, function annotations and sex differences systematically. Based on correlation analysis with permutation testing, we found 345 depression-related genes significantly correlated with functional and structural alteration of brain images in major depressive disorder and separated them by directional effects. The genes with negative effect for grey matter density and positive effect for functional indices are enriched in downregulated genes in the post-mortem brain samples of patients with depression and risk genes identified by genome-wide association studies than genes with positive effect for grey matter density and negative effect for functional indices and control genes, confirming their potential association with major depressive disorder. By introducing a parameter of dispersion measure on the gene expression data of developing human brains, we revealed higher spatial specificity and lower temporal specificity of depression-related genes than control genes. Meanwhile, we found depression-related genes tend to be more highly expressed in females than males, which may contribute to the difference in incidence rate between male and female patients. In general, we found the genes with negative effect have lower network degree, more specialized function, higher spatial specificity, lower temporal specificity and more sex differences than genes with positive effect, indicating they may play different roles in the occurrence and development of major depressive disorder. These findings can enhance the understanding of molecular mechanisms underlying major depressive disorder and help develop tailored diagnostic and treatment strategies for patients of depression of different sex.
RESUMEN
Dividing a pre-defined brain region into several heterogenous subregions is crucial for understanding its functional segregation and integration. Due to the high dimensionality of brain functional features, clustering is often postponed until dimensionality reduction in traditional parcellation frameworks occurs. However, under such stepwise parcellation, it is very easy to fall into the dilemma of local optimum since dimensionality reduction could not take into account the requirement of clustering. In this study, we developed a new parcellation framework based on the discriminative embedded clustering (DEC), combining subspace learning and clustering in a common procedure with alternative minimization adopted to approach global optimum. We tested the proposed framework in functional connectivity-based parcellation of the hippocampus. The hippocampus was parcellated into three spatial coherent subregions along the anteroventral-posterodorsal axis; the three subregions exhibited distinct functional connectivity changes in taxi drivers relative to non-driver controls. Moreover, compared with traditional stepwise methods, the proposed DEC-based framework demonstrated higher parcellation consistency across different scans within individuals. The study proposed a new brain parcellation framework with joint dimensionality reduction and clustering; the findings might shed new light on the functional plasticity of hippocampal subregions related to long-term navigation experience.
RESUMEN
A rapid, sensitive, and practical CE with C(4) D detection was developed for the analysis of three polyphenols (rutin, scopoletin, and chlorogenic acid) in tobacco samples. The constructed mini detection cell (12 mm × 10 mm × 10 mm) of C(4) D featured with small inner cell volume (â¼2 nL), smaller noise (<0.9 mV), repeatability, high strength and durableness. Three polyphenols were ultrasonically extracted with methanol-water (70:30, v/v) solution following SPE cleanup. The CE method was optimized with the running buffer of 150 mmol L(-1) 2-amino-2-methyl-1-propanol (pH 11.2), and the applied separation voltage of +20 kV over a capillary of 50 µm id × 375 µm od × 50 cm (38 cm to the C(4) D window, 41.5 cm to the UV detector window), which gave a baseline separation of three polyphenols within ca. 6 min. The method provided the limits of quantification (S/N = 10) at about 0.08-0.15 µg g(-1) for three polyphenols, whereas the overall recoveries ranged from 82% to 88%. The proposed method has been successfully applied to measure three polyphenols in the actual tobacco samples, and their contents were calculated and evaluated.
Asunto(s)
Ácido Clorogénico/análisis , Electroforesis Capilar/métodos , Nicotiana/química , Rutina/análisis , Escopoletina/análisis , Ácido Clorogénico/química , Electroforesis Capilar/instrumentación , Modelos Lineales , Extractos Vegetales/química , Hojas de la Planta/química , Rutina/química , Escopoletina/química , Sensibilidad y Especificidad , Extracción en Fase SólidaRESUMEN
Thin metal films are good candidates of terahertz detectors, reflectors, waveguides and terahertz quantum-cascade lasers (THz-QCLs). The optical parameter is the basis not only for designing the THz components but also for developing novel optoelectronic materials. In the present paper, the complex refractive indices of the ultra-thin metal (Cr, Ni and Ti) films in the THz band were obtained by the THz differential time-domain spectroscopy. The reflection spectra of the GaAs/metals interface were calculated according to the Fresnel formula. The mean reflectance of 25 nm Cr, Ni and Ti are over 80% from 0.3 to 1.5 THz. The results show that ultra-thin metal films can be used for reflectors as well as the electrodes in the THz band.
RESUMEN
Federated learning has shown its unique advantages in many different tasks, including brain image analysis. It provides a new way to train deep learning models while protecting the privacy of medical image data from multiple sites. However, previous studies suggest that domain shift across different sites may influence the performance of federated models. As a solution, we propose a gradient matching federated domain adaptation (GM-FedDA) method for brain image classification, aiming to reduce domain discrepancy with the assistance of a public image dataset and train robust local federated models for target sites. It mainly includes two stages: 1) pretraining stage; we propose a one-common-source adversarial domain adaptation (OCS-ADA) strategy, i.e., adopting ADA with gradient matching loss to pretrain encoders for reducing domain shift at each target site (private data) with the assistance of a common source domain (public data) and 2) fine-tuning stage; we develop a gradient matching federated (GM-Fed) fine-tuning method for updating local federated models pretrained with the OCS-ADA strategy, i.e., pushing the optimization direction of a local federated model toward its specific local minimum by minimizing gradient matching loss between sites. Using fully connected networks as local models, we validate our method with the diagnostic classification tasks of schizophrenia and major depressive disorder based on multisite resting-state functional MRI (fMRI), respectively. Results show that the proposed GM-FedDA method outperforms other commonly used methods, suggesting the potential of our method in brain imaging analysis and other fields, which need to utilize multisite data while preserving data privacy.
RESUMEN
OBJECTIVE: Dim target detection in remote sensing images is a significant and challenging problem. In this work, we seek to explore event-related brain responses of dim target detection tasks and extend the brain-computer interface (BCI) systems to this task for efficiency enhancement. METHODS: We develop a BCI paradigm named Asynchronous Visual Evoked Paradigm (AVEP), in which subjects are required to search the dim targets within satellite images when their scalp electroencephalography (EEG) signals are simultaneously recorded. In the paradigm, stimulus onset time and target onset time are asynchronous because subjects need enough time to confirm whether there are targets of interest in the presented serial images. We further propose a Domain adaptive and Channel-wise attention-based Time-domain Convolutional Neural Network (DC-tCNN) to solve the single-trial EEG classification problem for the AVEP task. In this model, we design a multi-scale CNN module combined with a channel-wise attention module to effectively extract event-related brain responses underlying EEG signals. Meanwhile, domain adaptation is proposed to mitigate cross-subject distribution discrepancy. RESULTS: The results demonstrate the superior performance and better generalizability of this model in classifying the single-trial EEG data of AVEP task in contrast to typical EEG deep learning networks. Visualization analyses of spatiotemporal features also illustrate the effectiveness and interpretability of our proposed paradigm and learning model. CONCLUSION: The proposed paradigm and model can effectively explore ambiguous event-related brain responses on EEG-based dim target detection tasks. SIGNIFICANCE: Our work can provide a valuable reference for BCI-based image detection of dim targets.
Asunto(s)
Interfaces Cerebro-Computador , Electroencefalografía , Algoritmos , Encéfalo/fisiología , Electroencefalografía/métodos , Humanos , Redes Neurales de la Computación , Cuero CabelludoRESUMEN
In epidemiological studies, type 2 diabetes mellitus (T2DM) has been associated with cognitive impairment and dementia, but studies about functional network connectivity in T2DM without cognitive impairment are limited. This study aimed to explore network connectivity alterations that may help enhance our understanding of damage-associated processes in T2DM. MRI data were analyzed from 82 patients with T2DM and 66 normal controls. Clinical, biochemical, and neuropsychological assessments were conducted in parallel with resting-state functional magnetic resonance imaging, and the cognitive status of the patients was assessed using the Montreal Cognitive Assessment-B (MoCA-B) score. Independent component analysis revealed a positive correlation between the salience network and the visual network and a negative connection between the left executive control network and the default mode network in patients with T2DM. The differences in dynamic brain network connectivity were observed in the precuneus, visual, and executive control networks. Internal network connectivity was primarily affected in the thalamus, inferior parietal lobe, and left precuneus. Hemoglobin A1c level, body mass index, MoCA-B score, and grooved pegboard (R) assessments indicated significant differences between the two groups (p < 0.05). Our findings show that key changes in functional connectivity in diabetes occur in the precuneus and executive control networks that evolve before patients develop cognitive deficits. In addition, the current study provides useful information about the role of the thalamus, inferior parietal lobe, and precuneus, which might be potential biomarkers for predicting the clinical progression, assessing the cognitive function, and further understanding the neuropathology of T2DM.
RESUMEN
Early screening is essential for effective intervention and treatment of individuals with mental disorders. Functional magnetic resonance imaging (fMRI) is a noninvasive tool for depicting neural activity and has demonstrated strong potential as a technique for identifying mental disorders. Due to the difficulty in data collection and diagnosis, imaging data from patients are rare at a single site, whereas abundant healthy control data are available from public datasets. However, joint use of these data from multiple sites for classification model training is hindered by cross-domain distribution discrepancy and diverse label spaces. Herein, we propose few-shot domain-adaptive anomaly detection (FAAD) to achieve cross-site anomaly detection of brain images based on only a few labeled samples. We introduce domain adaptation to mitigate cross-domain distribution discrepancy and jointly align the general and conditional feature distributions of imaging data across multiple sites. We utilize fMRI data of healthy subjects in the Human Connectome Project (HCP) as the source domain and fMRI images from six independent sites, including patients with mental disorders and demographically matched healthy controls, as target domains. Experiments showed the superiority of the proposed method compared with binary classification, traditional anomaly detection methods, and several recognized domain adaptation methods.
RESUMEN
Mild traumatic brain injury (mTBI) is usually caused by a bump, blow, or jolt to the head or penetrating head injury, and carries the risk of inducing cognitive disorders. However, identifying the biomarkers for the diagnosis of mTBI is challenging as evident abnormalities in brain anatomy are rarely found in patients with mTBI. In this study, we tested whether the alteration of functional network dynamics could be used as potential biomarkers to better diagnose mTBI. We propose a sparse dictionary learning framework to delineate spontaneous fluctuation of functional connectivity into the subject-specific time-varying evolution of a set of overlapping group-level sparse connectivity components (SCCs) based on the resting-state functional magnetic resonance imaging (fMRI) data from 31 mTBI patients in the early acute phase (<3 days postinjury) and 31 healthy controls (HCs). The identified SCCs were consistently distributed in the cohort of subjects without significant inter-group differences in connectivity patterns. Nevertheless, subject-specific temporal expression of these SCCs could be used to discriminate patients with mTBI from HCs with a classification accuracy of 74.2% (specificity 64.5% and sensitivity 83.9%) using leave-one-out cross-validation. Taken together, our findings indicate neuroimaging biomarkers for mTBI individual diagnosis based on the temporal expression of SCCs underlying time-resolved functional connectivity.