RESUMEN
Objective: Using functional magnetic resonance imaging (fMRI) and deep learning to discover the spatial pattern of brain function, or functional brain networks (FBNs) has been attracted many reseachers. Most existing works focus on static FBNs or dynamic functional connectivity among fixed spatial network nodes, but ignore the potential dynamic/time-varying characteristics of the spatial networks themselves. And most of works based on the assumption of linearity and independence, that oversimplify the relationship between blood-oxygen level dependence signal changes and the heterogeneity of neuronal activity within voxels.Approach: To overcome these problems, we proposed a novel spatial-wise attention (SA) based method called Spatial and Channel-wise Attention Autoencoder (SCAAE) to discover the dynamic FBNs without the assumptions of linearity or independence. The core idea of SCAAE is to apply the SA to generate FBNs directly, relying solely on the spatial information present in fMRI volumes. Specifically, we trained the SCAAE in a self-supervised manner, using the autoencoder to guide the SA to focus on the activation regions. Experimental results show that the SA can generate multiple meaningful FBNs at each fMRI time point, which spatial similarity are close to the FBNs derived by known classical methods, such as independent component analysis.Main results: To validate the generalization of the method, we evaluate the approach on HCP-rest, HCP-task and ADHD-200 dataset. The results demonstrate that SA mechanism can be used to discover time-varying FBNs, and the identified dynamic FBNs over time clearly show the process of time-varying spatial patterns fading in and out.Significance: Thus we provide a novel method to understand human brain better. Code is available athttps://github.com/WhatAboutMyStar/SCAAE.
Asunto(s)
Mapeo Encefálico , Fenómenos Fisiológicos del Sistema Nervioso , Humanos , Mapeo Encefálico/métodos , Encéfalo/fisiología , Imagen por Resonancia Magnética/métodos , AtenciónRESUMEN
Functional brain networks (FBNs) are spatial patterns of brain function that play a critical role in understanding human brain function. There are many proposed methods for mapping the spatial patterns of brain function, however they oversimplify the underlying assumptions of brain function and have various limitations such as linearity and independence. Additionally, current methods fail to account for the dynamic nature of FBNs, which limits their effectiveness in accurately characterizing these networks. To address these limitations, we present a novel deep learning and spatial-wise attention based model called Spatial-Temporal Convolutional Attention (STCA) to accurately model dynamic FBNs. Specifically, we train STCA in a self-supervised manner by utilizing a Convolutional Autoencoder to guide the STCA module in assigning higher attention weights to regions of functional activity. To validate the reliability of the results, we evaluate our approach on the HCP-task motor behavior dataset, the experimental results demonstrate that the STCA derived FBNs have higher spatial similarity with the templates and that the spatial similarity between the templates and the FBNs derived by STCA fluctuates with the task design over time, suggesting that STCA can reflect the dynamic changes of brain function, providing a powerful tool to better understand human brain function. Code is available at https://github.com/SNNUBIAI/STCAE.
Asunto(s)
Mapeo Encefálico , Imagen por Resonancia Magnética , Humanos , Mapeo Encefálico/métodos , Imagen por Resonancia Magnética/métodos , Reproducibilidad de los Resultados , Encéfalo/diagnóstico por imagenRESUMEN
Recently, deep learning models have achieved superior performance for mapping functional brain networks from functional magnetic resonance imaging (fMRI) data compared with traditional methods. However, due to the lack of sufficient data and the high dimensionality of brain volume, deep learning models of fMRI tend to suffer from overfitting. In addition, existing methods rarely studied fMRI data augmentation and its application. To address these issues, we developed a VAE-GAN framework that combined a VAE (variational auto-encoder) with a GAN (generative adversarial net) for functional brain network identification and fMRI augmentation. As a generative model, the VAE-GAN models the distribution of fMRI so that it enables the extraction of more generalized features, and thus relieve the overfitting issue. The VAE-GAN is easier to train on fMRI than a standard GAN since it uses latent variables from VAE to generate fake data rather than relying on random noise that is used in a GAN, and it can generate higher quality of fake data than VAE since the discriminator can promote the training of the generator. In other words, the VAE-GAN inherits the advantages of VAE and GAN and avoids their limitations in modeling of fMRI data. Extensive experiments on task fMRI datasets from HCP have proved the effectiveness and superiority of the proposed VAE-GAN framework for identifying both temporal features and functional brain networks compared with existing models, and the quality of fake data is higher than those from VAE and GAN. The results on resting state fMRI of Attention Deficit Hyperactivity Disorder (ADHD)-200 dataset further demonstrated that the fake data generated by the VAE-GAN can help improve the performance of brain network modeling and ADHD classification.
Asunto(s)
Encéfalo , Imagen por Resonancia Magnética , Encéfalo/diagnóstico por imagenRESUMEN
Accurate genotyping of the epidermal growth factor receptor (EGFR) is critical for the treatment planning of lung adenocarcinoma. Currently, clinical identification of EGFR genotyping highly relies on biopsy and sequence testing which is invasive and complicated. Recent advancements in the integration of computed tomography (CT) imagery with deep learning techniques have yielded a non-invasive and straightforward way for identifying EGFR profiles. However, there are still many limitations for further exploration: 1) most of these methods still require physicians to annotate tumor boundaries, which are time-consuming and prone to subjective errors; 2) most of the existing methods are simply borrowed from computer vision field which does not sufficiently exploit the multi-level features for final prediction. To solve these problems, we propose a Denseformer framework to identify EGFR mutation status in a real end-to-end fashion directly from 3D lung CT images. Specifically, we take the 3D whole-lung CT images as the input of the neural network model without manually labeling the lung nodules. This is inspired by the medical report that the mutational status of EGFR is associated not only with the local tumor nodules but also with the microenvironment surrounded by the whole lung. Besides, we design a novel Denseformer network to fully explore the distinctive information across the different level features. The Denseformer is a novel network architecture that combines the advantages of both convolutional neural network (CNN) and Transformer. Denseformer directly learns from the 3D whole-lung CT images, which preserves the spatial location information in the CT images. To further improve the model performance, we designed a combined Transformer module. This module employs the Transformer Encoder to globally integrate the information of different levels and layers and use them as the basis for the final prediction. The proposed model has been tested on a lung adenocarcinoma dataset collected at the Affiliated Hospital of Zunyi Medical University. Extensive experiments demonstrated the proposed method can effectively extract meaningful features from 3D CT images to make accurate predictions. Compared with other state-of-the-art methods, Denseformer achieves the best performance among current methods using deep learning to predict EGFR mutation status based on a single modality of CT images.
RESUMEN
BACKGROUND: It has been recently shown that deep learning models exhibited remarkable performance of representing functional Magnetic Resonance Imaging (fMRI) data for the understanding of brain functional activities. With hierarchical structure, deep learning models can infer hierarchical functional brain networks (FBN) from fMRI. However, the applications of the hierarchical FBNs have been rarely studied. METHODS: In this work, we proposed a hierarchical recurrent variational auto-encoder (HRVAE) to unsupervisedly model the fMRI data. The trained HRVAE encoder can predict hierarchical temporal features from its three hidden layers, and thus can be regarded as a hierarchical feature extractor. Then LASSO (least absolute shrinkage and selection operator) regression was applied to estimate the corresponding hierarchical FBNs. Based on the hierarchical FBNs from each subject, we constructed a novel classification framework for brain disorder identification and test it on the Autism Brain Imaging Data Exchange (ABIDE) dataset, a world-wide multi-site database of autism spectrum disorder (ASD). We analyzed the hierarchy organization of FBNs, and finally used the overlaps of hierarchical FBNs as features to differentiate ASD from typically developing controls (TDC). RESULTS: The experimental results on 871 subjects from ABIDE dataset showed that the HRVAE model can effectively derive hierarchical FBNs including many well-known resting state networks (RSN). Moreover, the classification result improved the state-of-the-art by achieving a very high accuracy of 82.1 %. CONCLUSIONS: This work presents a novel data-driven deep learning method using fMRI data for ASD identification, which could provide valuable reference for clinical diagnosis. The classification results suggest that the interactions of hierarchical FBNs have association with brain disorder, which promotes the understanding of FBN hierarchy and could be applied to other brain disorder analysis.
Asunto(s)
Trastorno del Espectro Autista , Encefalopatías , Conectoma , Aprendizaje Profundo , Humanos , Trastorno del Espectro Autista/diagnóstico por imagen , Encéfalo/diagnóstico por imagen , Conectoma/métodos , Imagen por Resonancia Magnética/métodosRESUMEN
The investigation of functional brain networks (FBNs) using task-based functional magnetic resonance imaging (tfMRI) has gained significant attention in the field of neuroimaging. Despite the availability of several methods for constructing FBNs, including traditional methods like GLM and deep learning methods such as spatiotemporal self-attention mechanism (STAAE), these methods have design and training limitations. Specifically, they do not consider the intrinsic characteristics of fMRI data, such as the possibility that the same signal value at different time points could represent different brain states and meanings. Furthermore, they overlook prior knowledge, such as task designs, during training. This study aims to overcome these limitations and develop a more efficient model by drawing inspiration from techniques in the field of natural language processing (NLP). The proposed model, called the Multi-head Attention-based Masked Sequence Model (MAMSM), uses a multi-headed attention mechanism and mask training approach to learn different states corresponding to the same voxel values. Additionally, it combines cosine similarity and task design curves to construct a novel loss function. The MAMSM was applied to seven task state datasets from the Human Connectome Project (HCP) tfMRI dataset. Experimental results showed that the features acquired by the MAMSM model exhibit a Pearson correlation coefficient with the task design curves above 0.95 on average. Moreover, the model can extract more meaningful networks beyond the known task-related brain networks. The experimental results demonstrated that MAMSM has great potential in advancing the understanding of functional brain networks.
RESUMEN
Fiber tract segmentation is a prerequisite for tract-based statistical analysis. Brain fiber streamlines obtained by diffusion magnetic resonance imaging and tractography technology are usually difficult to be leveraged directly, thus need to be segmented into fiber tracts. Previous research mainly consists of two steps: defining and computing the similarity features of fiber streamlines, then adopting machine learning algorithms for fiber clustering or classification. Defining the similarity feature is the basic premise and determines its potential reliability and application. In this study, we adopt geometric features for fiber tract segmentation and develop a novel descriptor (FiberGeoMap) for the corresponding representation, which can effectively depict fiber streamlines' shapes and positions. FiberGeoMap can differentiate fiber tracts within the same subject, meanwhile preserving the shape and position consistency across subjects, thus can identify common fiber tracts across brains. We also proposed a Transformer-based encoder network called FiberGeoMap Learner, to perform segmentation based on the geometric features. Experimental results showed that the proposed method can differentiate the 103 various fiber tracts, which outperformed the existing methods in both the number of categories and segmentation accuracy. Furthermore, the proposed method identified some fiber tracts that were statistically different on fractional anisotropy (FA), mean diffusion (MD), and fiber number ration in autism.
Asunto(s)
Trastorno Autístico , Sustancia Blanca , Humanos , Trastorno Autístico/diagnóstico por imagen , Trastorno Autístico/patología , Sustancia Blanca/diagnóstico por imagen , Sustancia Blanca/patología , Imagen de Difusión Tensora/métodos , Reproducibilidad de los Resultados , Procesamiento de Imagen Asistido por Computador/métodos , Encéfalo/diagnóstico por imagen , Encéfalo/patología , Imagen de Difusión por Resonancia Magnética/métodosRESUMEN
Despite increasing attention to the influence of unsteady-state volatile organic compounds (VOCs) on the adsorption of activated carbon, studies in this regard are rare. Therefore, in this study, an investigation into the migration and diffusion of unsteady-state VOCs on activated carbon adsorption beds under reverse ventilation was conducted. Here, reverse clean air was introduced when the activated carbon bed reached the penetration point. The influence of reverse ventilation temperature, reverse superficial gas velocity, activated carbon filling height, and different ventilation modes on the adsorption of unsteady toluene by activated carbon were studied. Our experimental results show that when the reverse ventilation temperature increased from 20 °C to 60 °C, the quasi-first-order desorption rate constant increased from 0.00356 min-1 to 0.00807 min-1, an increase in the reverse superficial gas velocity led to a higher rate constant, and at greater reverse superficial gas velocities, the stripping capacity increased. It was observed that the maximum stripping capacity was achieved at a reverse superficial gas velocity of 0.3 m/s. For different activated carbon filling heights, following reverse ventilation, the stripping capacity of a 5 cm and 30 cm activated carbon bed accounted for 41.43% and 65.85% of the original adsorption capacity, respectively. The study concludes that concentration of toluene first increased and then decreased with time under forward ventilation, whereas the concentration gradually decreased under reverse ventilation.
Asunto(s)
Compuestos Orgánicos Volátiles , Adsorción , Carbón Orgánico , Tolueno , DifusiónRESUMEN
Electroencephalogram (EEG) is one of the most widely used brain computer interface (BCI) approaches. Despite the success of existing EEG approaches in brain state recognition studies, it is still challenging to differentiate brain states via explainable and generalizable deep learning approaches. In other words, how to explore meaningful and distinguishing features and how to overcome the huge variability and overfitting problem still need to be further studied. To alleviate these challenges, in this work, a multiple random fragment search-based multilayer recurrent neural network (MRFS-MRNN) is proposed to improve the differentiating performance and explore meaningful patterns. Specifically, an explainable MRNN module is proposed to capture the temporal dependences preserved in EEG time series. Besides, a MRFS module is designed to cut multiple random fragments from the entire EEG signal time course to improve the effectiveness of brain state differentiating ability. MRFS-MRNN is concatenatedto effectively overcome the huge variabilities and overfitting problems. Experiment results demonstrate that the proposed MRFS-MRNN model not only has excellent differentiating performance, but also has good explanation and generalization ability. The classification accuracies reach as high as 95.18% for binary classification and 89.19% for four-category classification on the individual level. Similarly, 95.53% and 85.84% classification accuracies are obtained for the binary and four-category classification on the group level. What's more, 94.28% and 85.43% classification accuracies of binary and four-category classifications are achieved for predicting brand new subjects. The experiment results showed that the proposed method outperformed other state-of-the-art (SOTA) models on the same underlying data and improved the explanation and generalization ability.
RESUMEN
BACKGROUND AND OBJECTIVE: To understand brain cognition and disorders, modeling the mapping between mind and brain has been of great interest to the neuroscience community. The key is the brain representation, including functional brain networks (FBN) and their corresponding temporal features. Recently, it has been proven that deep learning models have superb representation power on functional magnetic resonance imaging (fMRI) over traditional machine learning methods. However, due to the lack of high-quality data and labels, deep learning models tend to suffer from overfitting in the training process. METHODS: In this work, we applied a recurrent Wasserstein generative adversarial net (RWGAN) to learn brain representation from volumetric fMRI data. Generative adversarial net (GAN) is widely used in natural image generation and is able to capture the distribution of the input data, which enables the extraction of generalized features from fMRI and thus relieves the overfitting issue. The recurrent layers in RWGAN are designed to better model the local temporal features of the fMRI time series. The discriminator of RWGAN works as a deep feature extractor. With LASSO regression, the RWGAN model can decompose the fMRI data into temporal features and spatial features (FBNs). Furthermore, the generator of RWGAN can generate high-quality new data for fMRI augmentation. RESULTS: The experimental results on seven tasks from the HCP dataset showed that the RWGAN can learn meaningful and interpretable temporal features and FBNs, compared to HCP task designs and general linear model (GLM) derived networks. Besides, the results on different training datasets showed that the RWGAN performed better on small datasets than other deep learning models. Moreover, we used the generator of RWGAN to yield fake subjects. The result showed that the fake data can also be used to learn meaningful representation compared to those learned from real data. CONCLUSIONS: To our best knowledge, this work is among the earliest attempts of applying generative deep learning for modeling fMRI data. The proposed RWGAN offers a novel methodology for learning brain representation from fMRI, and it can generate high-quality fake data for the potential use of fMRI data augmentation.
Asunto(s)
Encéfalo , Procesamiento de Imagen Asistido por Computador , Encéfalo/diagnóstico por imagen , Cognición , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Aprendizaje Automático , Imagen por Resonancia Magnética/métodosRESUMEN
Objective. Recently, deep learning models have been successfully applied in functional magnetic resonance imaging (fMRI) modeling and associated applications. However, there still exist at least two challenges. Firstly, due to the lack of sufficient data, deep learning models tend to suffer from overfitting in the training process. Secondly, it is still challenging to model the temporal dynamics from fMRI, due to that the brain state is continuously changing over scan time. In addition, existing methods rarely studied and applied fMRI data augmentation.Approach. In this work, we construct a deep recurrent variational auto-encoder (DRVAE) that combined variational auto-encoder and recurrent neural network, aiming to address all of the above mentioned challenges. The encoder of DRVAE can extract more generalized temporal features from assumed Gaussian distribution of input data, and the decoder of DRVAE can generate new data to increase training samples and thus partially relieve the overfitting issue. The recurrent layers in DRVAE are designed to effectively model the temporal dynamics of functional brain activities. LASSO (least absolute shrinkage and selection operator) regression is applied on the temporal features and input fMRI data to estimate the corresponding spatial networks.Main results. Extensive experimental results on seven tasks from HCP dataset showed that the DRVAE and LASSO framework can learn meaningful temporal patterns and spatial networks from both real data and generated data. The results on group-wise data and single subject suggest that the brain activities may follow certain distribution. Moreover, we applied DRVAE on four resting state fMRI datasets from ADHD-200 for data augmentation, and the results showed that the classification performances on augmented datasets have been considerably improved.Significance. The proposed method can not only derive meaningful temporal features and spatial networks from fMRI, but also generate high-quality new data for fMRI data augmentation and associated applications.
Asunto(s)
Mapeo Encefálico , Imagen por Resonancia Magnética , Encéfalo/diagnóstico por imagen , Redes Neurales de la ComputaciónRESUMEN
Exploring the spatial patterns and temporal dynamics of human brain activity has been of great interest, in the quest to better understand connectome-scale brain networks. Though modeling spatial and temporal patterns of functional brain networks have been researched for a long time, the development of a unified and simultaneous spatial-temporal model has yet to be realized. For instance, although some deep learning methods have been proposed recently in order to model functional brain networks, most of them can only represent either spatial or temporal perspective of functional Magnetic Resonance Imaging (fMRI) data and rarely model both domains simultaneously. Due to the recent success in applying sequential auto-encoders for brain decoding, in this paper, we propose a deep sparse recurrent auto-encoder (DSRAE) to be applied unsupervised to learn spatial patterns and temporal fluctuations of brain networks at the same time. The proposed DSRAE was evaluated and validated based on three tasks of the publicly available Human Connectome Project (HCP) fMRI dataset, resulting with promising evidence. To the best of our knowledge, the proposed DSRAE is among the early efforts in developing unified models that can extract connectome-scale spatial-temporal networks from 4D fMRI data simultaneously.
Asunto(s)
Conectoma , Encéfalo/diagnóstico por imagen , Humanos , Imagen por Resonancia MagnéticaRESUMEN
Presently, volatile organic compounds (VOCs) pollution control in China has entered the deep-water zone, facing difficult challenges. The cost-effectiveness of VOCs abatement alternatives will determine the final environmental benefits. Screening of abatement alternatives with good cost-effectiveness and performance is important to form a sound basis for VOCs emission abatement work to create sustainable and stable alternatives. In this study, 12 typical emission scenarios are set up based on the emission characteristics of pollution sources, such as emission concentration, airflow volume, continuous or intermittent emissions, and fluctuations in concentration. Based on these typical scenarios, the operation costs of current mainstream emission abatement alternatives is estimated, and a cost-effectiveness comparison is made using the unit abatement cost (UAC, yuan·kg-1, VOCs) as the index. The results obtained can provide a reference for choosing appropriate VOCs abatement alternatives according to the characteristics of VOCs emission. Results show that for low concentration VOCs, the UAC of emission abatement is normally more than 8 yuan·kg-1. The concentration in the process plays an important role in reducing UAC. Therefore, the reasonable collection of VOCs gas, resulting in smaller emission volume and higher concentration, has a significant impact on the subsequent emission abatement cost-effectiveness. Enhancing the classification collection of VOCs to improve resource attributes of the recovered VOCs liquid is also an effective way to improve the cost effectiveness of VOCs abatement.
RESUMEN
It has been shown that deep neural networks are powerful and flexible models that can be applied on fMRI data with superb representation ability over traditional methods. However, a challenge of neural network architecture design has also attracted attention: due to the high dimension of fMRI volume images, the manual process of network model design is very time-consuming and not optimal. To tackle this problem, we proposed an unsupervised neural architecture search (NAS) framework on a deep belief network (DBN) that models volumetric fMRI data, named NAS-DBN. The NAS-DBN framework is based on Particle Swarm Optimization (PSO) where the swarms of neural architectures can evolve and converge to a feasible optimal solution. The experiments showed that the proposed NAS-DBN framework can quickly find a robust architecture of DBN, yielding a hierarchy organization of functional brain networks (FBNs) and temporal responses. Compared with 3 manually designed DBNs, the proposed NAS-DBN has the lowest testing loss of 0.0197, suggesting an overall performance improvement of up to 47.9 %. For each task, the NAS-DBN identified 260 FBNs, including task-specific FBNs and resting state networks (RSN), which have high overlap rates to general linear model (GLM) derived templates and independent component analysis (ICA) derived RSN templates. The average overlap rate of NAS-DBN to GLM on 20 task-specific FBNs is as high as 0.536, indicating a performance improvement of up to 63.9 % in respect of network modeling. Besides, we showed that the NAS-DBN can simultaneously generate temporal responses that resemble the task designs very well, and it was observed that widespread overlaps between FBNs from different layers of NAS-DBN model form a hierarchical organization of FBNs. Our NAS-DBN framework contributes an effective, unsupervised NAS method for modeling volumetric task fMRI data.
Asunto(s)
Imagen por Resonancia Magnética/métodos , Redes Neurales de la Computación , Encéfalo/diagnóstico por imagen , HumanosRESUMEN
Emission rates of volatile organic compounds (VOCs), H2S and odor unit from the surface of a municipal solid waste (MSW) landfill working area were measured with a wind tunnel sampler. The results show that the emission rate of odor from the non-point source of landfill is the function of environmental temperature and surface sweeping velocity. The emission rate measured in the high temperature season can be 6 times higher of that in the low temperature season. Within the experimental range of 0.6-4 m x s(-1) wind sweeping velocity, the emission rate shows a linear relationship with wind sweeping velocity. In summer, the emission rates of VOCs (measured by PID as isobutylene), H2S and odor unit are 385-680 microg x (m(2) x s)(-1), 4-7 microg x (m(2) x s)(-1), and 46.5-136 OU x (m(2) x s)(-1) respectively. The continuous sweeping experiment shows that the emission rate measured with clean air sweeping is the maximum possible emission rate, which needs to be adjusted when it is used to estimate the odor concentration of more than 10 min sample time or an area emission load.
Asunto(s)
Contaminantes Atmosféricos/análisis , Odorantes/análisis , Residuos Sólidos/análisis , Instalaciones de Eliminación de Residuos , Eliminación de Residuos , Estaciones del Año , Compuestos Orgánicos Volátiles/análisis , VientoRESUMEN
Experiment on process feasibility of adsorption and separating recovery of organic compounds directly from waste gas was conducted with the activated carbon column train consists of 4 units in serial. Isopropyl alcohol and toluene vapor mixture was used as target gas, which are the common constituents of the gas emitted from fine ceramic manufacture. The experimental results showed obvious adsorption stratification phenomena alone the activated carbon column length for the vapor mixture. Under the condition of superficial gas velocity of 0.42 m x s(-1), inlet concentration of 477 mg x m(-3) and 746 mg x m(-3) for isopropyl alcohol and toluene respectively, 26 cm total carbon packing length of the four column serial train, when the adsorption time reached 798 min, the adsorption capacities for toluene and isopropyl alcohol are 184.5 mg x g(-1) and 0 mg x g(-1) respectively in 0-10 cm section, and 0.92 mg x g(-1) and 91.2 mg x g(-1) respectively in 21-26 cm section, liquids with over 99% purity of isopropyl alcohol and toluene were recovered separately from the two end columns of the carbon column train. There is a gaseous concentration amplifier zone in the carbon column for the weaker adsorbate, isopropyl alcohol, which make the adsorption capacity of isopropyl alcohol increase over 27% in part of the down flow zone in this experiment. It is possible to directly recover the pure solvent liquid separately from the vapor mixture by the way of a serial adsorption column with separating stage recovering.