RESUMO
Accurate tissue segmentation is critical to characterize early cerebellar development in the first two postnatal years. However, challenges in tissue segmentation arising from tightly-folded cortex, low and dynamic tissue contrast, and large inter-site data heterogeneity have limited our understanding of early cerebellar development. In this paper, we propose an accurate self-supervised learning framework for infant cerebellum segmentation. We validate its accuracy using 358 subjects from three datasets. Our results suggest the first six months exhibit the most rapid and dynamic changes, with gray matter (GM) playing a dominant role in cerebellar growth over white matter (WM). We also find both GM and WM volumes are larger in males than females, and GM and WM volumes are larger in autistic males than neurotypical males. Application of our method to a larger population will fuel more cerebellar studies, ultimately advancing our comprehension of its structure and function in neurotypical and disordered development.
Assuntos
Imageamento por Ressonância Magnética , Substância Branca , Masculino , Feminino , Humanos , Lactente , Imageamento por Ressonância Magnética/métodos , Substância Cinzenta/diagnóstico por imagem , Cerebelo/diagnóstico por imagem , Substância Branca/diagnóstico por imagem , Aprendizado de Máquina Supervisionado , EncéfaloRESUMO
In the prediction of time series, the echo state network (ESN) exhibits exclusive strengths and a unique training structure. Based on ESN model, a pooling activation algorithm consisting noise value and adjusted pooling algorithm is proposed to enrich the update strategy of the reservoir layer in ESN. The algorithm optimizes the distribution of reservoir layer nodes. And the nodes set will be more matched to the characteristics of the data. In addition, we introduce a more efficient and accurate compressed sensing technique based on the existing research. The novel compressed sensing technique reduces the amount of spatial computation of methods. The ESN model based on the above two techniques overcomes the limitations in traditional prediction. In the experimental part, the model is validated with different chaotic time series as well as multiple stocks, and the method shows its efficiency and accuracy in prediction.
Assuntos
Algoritmos , Redes Neurais de Computação , Fatores de Tempo , RuídoRESUMO
BACKGROUND: Microvascular dysfunction (MVD) may contribute to cognitive impairment and Alzheimer's disease, but evidence is limited. OBJECTIVE: To investigate the association of composite and organ-specific MVD burden with mild cognitive impairment (MCI) and cognition among rural-dwelling Chinese older adults. METHODS: In this population-based cross-sectional study, we assessed MVD makers using optical coherence tomographic angiography for retinal microvasculature features, brain magnetic resonance imaging scans for cerebral small vessel disease (CSVD), and serum biomarkers for MVD. A composite MVD score was generated from the aforementioned organ-specific parameters. We used a neuropsychological test battery to assess memory, verbal fluency, attention, executive function, and global cognitive function. MCI, amnestic MCI (aMCI), and non-amnestic MCI (naMCI) were diagnosed following the Petersen's criteria. Data was analyzed with the linear and logistic regression models. RESULTS: Of the 274 dementia-free participants (age≥65 years), 56 were diagnosed with MCI, including 47 with aMCI and 9 with naMCI. A composite MVD score was statistically significantly associated with an odds ratio (OR) of 2.70 (95% confidence interval 1.12-6.53) for MCI and ß-coefficient of -0.29 (-0.48, -0.10) for global cognitive score after adjustment for socio-demographics, lifestyle factors, APOE genotype, the Geriatric Depression Scale score, serum inflammatory biomarkers, and cardiovascular comorbidity. A composite score of retinal microvascular morphology was associated with a multivariable-adjusted OR of 1.72 (1.09-2.73) for MCI and multivariable-adjusted ß-coefficient of -0.11 (-0.22, -0.01) for global cognitive score. A composite CSVD score was associated with a lower global cognitive score (ß=â-0.10; -0.17, -0.02). CONCLUSION: Microvascular dysfunction, especially in the brain and retina, is associated with MCI and poor cognitive function among rural-dwelling older adults.
Assuntos
Doença de Alzheimer , Disfunção Cognitiva , Humanos , Idoso , Estudos Transversais , Cognição , Disfunção Cognitiva/diagnóstico por imagem , Disfunção Cognitiva/epidemiologia , Doença de Alzheimer/psicologia , Testes Neuropsicológicos , BiomarcadoresRESUMO
Objective: To explore the associations of macular microvascular parameters with cerebral small vessel disease (CSVD) in rural-dwelling older adults in China. Methods: This population-based cross-sectional study included 195 participants (age ≥ 60 years; 57.4% women) in the optical coherence tomographic angiography (OCTA) sub-study within the Multimodal Interventions to delay Dementia and disability in rural China (MIND-China). Macular microvascular parameters were measured using the OCTA. We automatically estimated volumes of gray matter, white matter, and white matter hyperintensity (WMH), and manually assessed numbers of enlarged perivascular spaces (EPVS) and lacunes on brain magnetic resonance imaging. Data were analyzed with the general linear models. Results: Adjusting for multiple confounders, lower vessel skeleton density (VSD) and higher vessel diameter index (VDI) were significantly associated with larger WMH volume (P < 0.05). Lower VSD and foveal density-300 (FD-300) of left eye were significantly associated with lower brain parenchymal volume (P < 0.05). In addition, lower areas of foveal avascular zone (FAZ) and FD-300 of left eye were significantly associated with more EPVS (P < 0.05). The associations of abnormal macular microvascular parameters with WMH volume were evident mainly among females. Macular microvascular parameters were not associated with lacunes. Conclusion: Macular microvascular signs are associated with WMH, brain parenchymal volume, and EPVS in older adults. The OCTA-assessed macular microvascular parameters can be valuable markers for microvascular lesions in the brain.
RESUMO
Accurate measurements of the size, shape and volume of macular edema can provide important biomarkers to jointly assess disease progression and treatment outcome. Although many deep learning-based segmentation algorithms have achieved remarkable success in semantic segmentation, these methods have difficulty obtaining satisfactory segmentation results in retinal optical coherence tomography (OCT) fluid segmentation tasks due to low contrast, blurred boundaries, and varied distribution. Moreover, directly applying a well-trained model on one device to test the images from other devices may cause the performance degradation in the joint analysis of multi-domain OCT images. In this paper, we propose a self-training adversarial learning framework for unsupervised domain adaptation in retinal OCT fluid segmentation tasks. Specifically, we develop an image style transfer module and a fine-grained feature transfer module to reduce discrepancies in the appearance and high-level features of images from different devices. Importantly, we transfer the target images to the appearance of source images to ensure that no image information of the source domain for supervised training is lost. To capture specific features of the target domain, we design a self-training module based on a discrepancy and similarity strategy to select the images with better segmentation results from the target domain and then introduce them into the source domain for the iterative training segmentation model. Extensive experiments on two challenging datasets demonstrate the effectiveness of our proposed method. In Particular, our proposed method achieves comparable results on cross-domain retinal OCT fluid segmentation compared with the state-of-the-art methods.
Assuntos
Edema Macular , Tomografia de Coerência Óptica , Humanos , Retina , Algoritmos , Progressão da Doença , Processamento de Imagem Assistida por ComputadorRESUMO
Structured pruning has received ever-increasing attention as a method for compressing convolutional neural networks. However, most existing methods directly prune the network structure according to the statistical information of the parameters. Besides, these methods differentiate the pruning rates only in each pruning stage or even use the same pruning rate across all layers, rather than using learnable parameters. In this article, we propose a network redundancy elimination approach guided by the pruned model. Our proposed method can easily tackle multiple architectures and is scalable to the deeper neural networks because of the use of joint optimization during the pruning procedure. More specifically, we first construct a sparse self-representation for the filters or neurons of the well-trained model, which is useful for analyzing the relationship among filters. Then, we employ particle swarm optimization to learn pruning rates in a layerwise manner according to the performance of the pruned model, which can determine optimal pruning rates with the best performance of the pruned model. Under this criterion, the proposed pruning approach can remove more parameters without undermining the performance of the model. Experimental results demonstrate the effectiveness of our proposed method on different datasets and different architectures. For example, it can reduce 58.1% FLOPs for ResNet50 on ImageNet with only a 1.6% top-five error increase and 44.1% FLOPs for FCN_ResNet50 on COCO2017 with a 3% error increase, outperforming most state-of-the-art methods.
RESUMO
Anomaly detection refers to leveraging only normal data to train a model for identifying unseen abnormal cases, which is extensively studied in various fields. Most previous methods are based on reconstruction models, and use anomaly score calculated by the reconstruction error as the metric to tackle anomaly detection. However, these methods just employ single constraint on latent space to construct reconstruction model, resulting in limited performance in anomaly detection. To address this problem, we propose a Spatial-Contextual Variational Autoencoder with Attention Correction for anomaly detection in retinal OCT images. Specifically, we first propose a self-supervised segmentation network to extract retinal regions, which can effectively eliminate interference of background regions. Next, by introducing both multi-dimensional and one-dimensional latent space, our proposed framework can then learn the spatial and contextual manifolds of normal images, which is conducive to enlarging the difference between reconstruction errors of normal images and those of abnormal ones. Furthermore, an ablation-based method is proposed to localize anomalous regions by computing the importance of feature maps, which is used to correct anomaly score calculated by reconstruction error. Finally, a novel anomaly score is constructed to separate the abnormal images from the normal ones. Extensive experiments on two retinal OCT datasets are conducted to evaluate our proposed method, and the experimental results demonstrate the effectiveness of our approach.
Assuntos
Algoritmos , Tomografia de Coerência Óptica , Tomografia de Coerência Óptica/métodos , Retina/diagnóstico por imagemRESUMO
This paper investigates the fixed-time synchronization and the predefined-time synchronization of memristive complex-valued bidirectional associative memory neural networks (MCVBAMNNs) with leakage time-varying delay. First, the proposed neural networks are regarded as two dynamic real-valued systems. By designing a suitable feedback controller, combined with the Lyapunov method and inequality technology, a more accurate upper bound of stability time estimation is given. Then, a predefined-time stability theorem is proposed, which can easily establish a direct relationship between tuning gain and system stability time. Any predefined time can be set as controller parameters to ensure that the synchronization error converges within the predefined time. Finally, the developed chaotic MCVBAMNNs and predefined-time synchronization technology are applied to image encryption and decryption. The correctness of the theory and the security of the cryptographic system are verified by numerical simulation.
RESUMO
With the rapid advances in digital imaging and communication technologies, recently image set classification has attracted significant attention and has been widely used in many real-world scenarios. As an effective technology, the class-specific representation theory-based methods have demonstrated their superior performances. However, this type of methods either only uses one gallery set to measure the gallery-to-probe set distance or ignores the inner connection between different metrics, leading to the learned distance metric lacking robustness, and is sensitive to the size of image sets. In this article, we propose a novel joint metric learning-based class-specific representation framework (JMLC), which can jointly learn the related and unrelated metrics. By iteratively modeling probe set and related or unrelated gallery sets as affine hull, we reconstruct this hull sparsely or collaboratively over another image set. With the obtained representation coefficients, the combined metric between the query set and the gallery set can then be calculated. In addition, we also derive the kernel extension of JMLC and propose two new unrelated set constituting strategies. Specifically, kernelized JMLC (KJMLC) embeds the gallery sets and probe sets into the high-dimensional Hilbert space, and in the kernel space, the data become approximately linear separable. Extensive experiments on seven benchmark databases show the superiority of the proposed methods to the state-of-the-art image set classifiers.
RESUMO
In this paper, two novel and general predefined-time stability lemmas are given and applied to the predefined-time synchronization problem of memristive complex-valued bidirectional associative memory neural networks (MCVBAMNNs). Firstly, different from the generally fixed-time stability lemma, the setting of an adjustable time parameter in the derived predefined-time stability lemma causes it to be more flexible and more general. Secondly, the model studied in the complex-valued BAM neural networks model, which is different from the previous discussion of the real part and imaginary part respectively. It is more practical to study the complex-valued nonseparation. Thirdly, two effective controllers are designed to realize the synchronization performance of BAM neural networks based on the predefined-time stability, and the analysis is given based on general predefined-time synchronization. Finally, the correctness of the theoretical derivation is verified by numerical simulation. A secure communication scheme based on predefined-time synchronization of MCVBAMNNs is proposed, and the effectiveness and superiority of the results are proved.
Assuntos
Redes Neurais de Computação , Fatores de TempoRESUMO
The aims of this article were to study the effect of Fenton pretreatment and bacterial inoculation on cellulose-degrading genes and fungal communities during rice straw composting. The rice straw was pretreated by Fenton reactions and functional bacterial agents were then inoculated during the cooling phase of composting. Three treatment groups were carried out, the control (CK), Fenton pretreatment (FeW) and Fenton pretreatment and bacterial inoculation (FeWI). The results indicated that Fenton pretreatment and bacterial inoculation changed the fungal communities composition and increased fungal diversity, leading to changes in the cellulose-degrading genes. In addition, a network analysis showed that in the FeWI treatment, the fungi from modules 1, 5 and 8 were core hosts of the cellulose-degrading genes driving the cellulosic degradation. Moreover, Fenton pretreatment and bacterial inoculation changed the core module fungal communities and strengthened the correlation between the core fungi and the cellulose-degrading genes, thereby promoting cellulosic degradation. Based on redundancy and structural equation model analyses, the NH4+-N, TOC, pH and Shannon index were important factors influencing the variations in the cellulose-degrading genes. This study provides a foundation for cellulosic degradation during cellulosic waste composting.
Assuntos
Compostagem , Micobioma , Oryza , Celulose , SoloRESUMO
Autism, or autism spectrum disorder (ASD), is a developmental disability that is diagnosed at about 2 years of age based on abnormal behaviors. Existing neuroimaging-based methods for the prediction of ASD typically focus on functional magnetic resonance imaging (fMRI); however, most of these fMRI-based studies include subjects older than 5 years of age. Due to challenges in the application of fMRI for infants, structural magnetic resonance imaging (sMRI) has increasingly received attention in the field for early status prediction of ASD. In this study, we propose an automated prediction framework based on infant sMRI at about 24 months of age. Specifically, by leveraging an infant-dedicated pipeline, iBEAT V2.0 Cloud, we derived segmentation and parcellation maps from infant sMRI. We employed a convolutional neural network to extract features from pairwise maps and a Siamese network to distinguish whether paired subjects were from the same or different classes. As compared to T1w imaging without segmentation and parcellation maps, our proposed approach with segmentation and parcellation maps yielded greater sensitivity, specificity, and accuracy of ASD prediction, which was validated using two datasets with different imaging protocols/scanners and was confirmed by receiver operating characteristic analysis. Furthermore, comparison with state-of-the-art methods demonstrated the superior effectiveness and robustness of the proposed method. Finally, attention maps were generated to identify subject-specific autism effects, supporting the reasonability of the predictive results. Collectively, these findings demonstrate the utility of our unified framework for the early-stage status prediction of ASD by sMRI. LAY SUMMARY: The status prediction of autism spectrum disorder (ASD) at an early age is highly desirable, as early intervention may significantly reduce autism symptoms. However, current methods for diagnosing young children are limited to behavioral assays. In this study, we propose an automated method for ASD status prediction at the age of 24 months that uses infant structural magnetic resonance imaging to identify neural features.
Assuntos
Transtorno do Espectro Autista , Transtorno Autístico , Transtorno do Espectro Autista/diagnóstico por imagem , Encéfalo/diagnóstico por imagem , Pré-Escolar , Humanos , Lactente , Imageamento por Ressonância Magnética , NeuroimagemRESUMO
Non-invasive whole-brain scans aid the diagnosis of neuropsychiatric disorder diseases such as autism, dementia, and brain cancer. The assessable analysis for autism spectrum disorders (ASD) is rationally challenging due to the limitations of publicly available datasets. For diagnostic or prognostic tools, functional Magnetic Resonance Imaging (fMRI) exposed affirmation to the biomarkers in neuroimaging research because of fMRI pickup inherent connectivity between the brain and regions. There are profound studies in ASD with introducing machine learning or deep learning methods that have manifested advanced steps for ASD predictions based on fMRI data. However, utmost antecedent models have an inadequacy in their capacity to manipulate performance metrics such as accuracy, precision, recall, and F1-score. To overcome these problems, we proposed an avant-garde DarkASDNet, which has the competence to extract features from a lower level to a higher level and bring out promising results. In this work, we considered 3D fMRI data to predict binary classification between ASD and typical control (TC). Firstly, we pre-processed the 3D fMRI data by adopting proper slice time correction and normalization. Then, we introduced a novel DarkASDNet which surpassed the benchmark accuracy for the classification of ASD. Our model's outcomes unveil that our proposed method established state-of-the-art accuracy of 94.70% to classify ASD vs. TC in ABIDE-I, NYU dataset. Finally, we contemplated our model by performing evaluation metrics including precision, recall, F1-score, ROC curve, and AUC score, and legitimize by distinguishing with recent literature descriptions to vindicate our outcomes. The proposed DarkASDNet architecture provides a novel benchmark approach for ASD classification using fMRI processed data.
RESUMO
Automated lesion segmentation is one of the important tasks for the quantitative assessment of retinal diseases in SD-OCT images. Recently, deep convolutional neural networks (CNN) have shown promising advancements in the field of automated image segmentation, whereas they always benefit from large-scale datasets with high-quality pixel-wise annotations. Unfortunately, obtaining accurate annotations is expensive in both human effort and finance. In this paper, we propose a weakly supervised two-stage learning architecture to detect and further segment central serous chorioretinopathy (CSC) retinal detachment with only image-level annotations. Specifically, in the first stage, a Located-CNN is designed to detect the location of lesion regions in the whole SD-OCT retinal images, and highlight the distinguishing regions. To generate available a pseudo pixel-level label, the conventional level set method is employed to refine the distinguishing regions. In the second stage, we customize the active-contour loss function in deep networks to achieve the effective segmentation of the lesion area. A challenging dataset is used to evaluate our proposed method, and the results demonstrate that the proposed method consistently outperforms some current models trained with a different level of supervision, and is even as competitive as those relying on stronger supervision. To our best knowledge, we are the first to achieve CSC segmentation in SD-OCT images using weakly supervised learning, which can greatly reduce the labeling efforts.
RESUMO
To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.
Assuntos
Algoritmos , Imageamento por Ressonância Magnética , Encéfalo/diagnóstico por imagem , Mapeamento Encefálico , Substância Cinzenta , Humanos , LactenteRESUMO
This paper explores the realization of a predefined-time synchronization problem for coupled memristive neural networks with multi-links (MCMNN) via nonlinear control. Several effective conditions are obtained to achieve the predefined-time synchronization of MCMNN based on the controller and Lyapunov function. Moreover, the settling time can be tunable based on a parameter designed by the controller, which is more flexible than fixed-time synchronization. Then based on the predefined-time stability criterion and the tunable settling time, we propose a secure communication scheme. This scheme can determine security of communication in the aspect of encrypting the plaintext signal with the participation of multi-links topology and coupled form. Meanwhile, the plaintext signals can be recovered well according to the given new predefined-time stability theorem. Finally, numerical simulations are given to verify the effectiveness of the obtained theoretical results and the feasibility of the secure communication scheme.
RESUMO
Accurate tissue segmentation of large-scale pediatric brain MR images from multiple sites is essential to characterize early brain development. Due to imaging motion/Gibbs artifacts and multi-site issue (or domain shift issue), it remains a challenge to accurately segment brain tissues from multi-site pediatric MR images. In this paper, we present a multi-scale self-supervised learning (M-SSL) framework to accurately segment tissues for multi-site pediatric brain MR images with artifacts. Specifically, we first work on the downsampled images to estimate coarse tissue probabilities and build a global anatomic guidance. We then train another segmentation model based on the original images to estimate fine tissue probabilities, which are further integrated with the global anatomic guidance to refine the segmentation results. In the testing stage, to alleviate the multi-site issue, we propose an iterative self-supervised learning strategy to train a site-specific segmentation model based on a set of reliable training samples automatically generated for a to-be-segmented site. The experimental results on pediatric brain MR images with real artifacts and multi-site subjects from the iSeg2019 challenge demonstrate that our M-SSL method achieves better performance compared with several state-of-the-art methods.
RESUMO
The automated prediction of geographic atrophy (GA) lesion growth can help ophthalmologists understand how the GA progresses, and assess the efficiency of current treatment and the prognosis of the disease. We developed an integrated time adaptive prediction model for identifying the location of future GA growth. The proposed model was comprised of bi-directional long short-term memory (BiLSTM) network-based prediction module and convolutional neural network (CNN)-based refinement module. Considering the discontinuity of time intervals among sequential follow-up visits, we integrated time factors into BiLSTM-based prediction module to control the time attribute expediently. Then, the results from prediction module were refined by a CNN-based strategy to obtain the final locations of future GA growth. The 10 scenarios were designed to evaluate the prediction accuracy of our proposed model. The 1-6th scenarios demonstrated the importance of the prior information similarity, the 7-8th scenarios verified the effect of time factors and refinement methods respectively and the 9th scenario compared the prediction results between those using a single follow-up visit for training and using 2 sequential follow-up visits for training. The 10th scenario showed the model generalization performance across regions. The average dice indexes (DI) of the predicted GA regions in the 1-6th scenarios are 0.86, 0.89, 0.89, 0.92 and 0.88, 0.90, respectively. By integrating time factors to the BiLSTM models, the prediction accuracy was improved by almost 10%. The CNN-based refinement strategy can remove the wrong GA regions effectively to preserve the actual GA regions and improve the prediction accuracy further. The prediction results based on 2 sequential follow-up visits showed higher correlations than that based on single follow-up visit. The proposed model presented a good generalization performance while training patients and testing patients were from different regions. Experimental results demonstrated the importance of prior information to the prediction accuracy. We demonstrate the feasibility of creating a model for disease prediction.
Assuntos
Atrofia Geográfica , Humanos , Redes Neurais de Computação , Prognóstico , Tomografia de Coerência ÓpticaRESUMO
As one of the most critical characteristics in advanced stage of non-exudative Age-related Macular Degeneration (AMD), Geographic Atrophy (GA) is one of the significant causes of sustained visual acuity loss. Automatic localization of retinal regions affected by GA is a fundamental step for clinical diagnosis. In this paper, we present a novel weakly supervised model for GA segmentation in Spectral-Domain Optical Coherence Tomography (SD-OCT) images. A novel Multi-Scale Class Activation Map (MS-CAM) is proposed to highlight the discriminatory significance regions in localization and detail descriptions. To extract available multi-scale features, we design a Scaling and UpSampling (SUS) module to balance the information content between features of different scales. To capture more discriminative features, an Attentional Fully Connected (AFC) module is proposed by introducing the attention mechanism into the fully connected operations to enhance the significant informative features and suppress less useful ones. Based on the location cues, the final GA region prediction is obtained by the projection segmentation of MS-CAM. The experimental results on two independent datasets demonstrate that the proposed weakly supervised model outperforms the conventional GA segmentation methods and can produce similar or superior accuracy comparing with fully supervised approaches. The source code has been released and is available on GitHub: https://github.com/ jizexuan/Multi-Scale-Class-Activation-Map-Tensorflow.