Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 68
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
PLoS Comput Biol ; 17(8): e1009284, 2021 08.
Artigo em Inglês | MEDLINE | ID: mdl-34347784

RESUMO

Modeling the impact of amino acid mutations on protein-protein interaction plays a crucial role in protein engineering and drug design. In this study, we develop GeoPPI, a novel structure-based deep-learning framework to predict the change of binding affinity upon mutations. Based on the three-dimensional structure of a protein, GeoPPI first learns a geometric representation that encodes topology features of the protein structure via a self-supervised learning scheme. These representations are then used as features for training gradient-boosting trees to predict the changes of protein-protein binding affinity upon mutations. We find that GeoPPI is able to learn meaningful features that characterize interactions between atoms in protein structures. In addition, through extensive experiments, we show that GeoPPI achieves new state-of-the-art performance in predicting the binding affinity changes upon both single- and multi-point mutations on six benchmark datasets. Moreover, we show that GeoPPI can accurately estimate the difference of binding affinities between a few recently identified SARS-CoV-2 antibodies and the receptor-binding domain (RBD) of the S protein. These results demonstrate the potential of GeoPPI as a powerful and useful computational tool in protein design and engineering. Our code and datasets are available at: https://github.com/Liuxg16/GeoPPI.


Assuntos
Substituição de Aminoácidos , Modelos Químicos , Proteínas/metabolismo , Mutação Puntual , Ligação Proteica , Proteínas/química , Proteínas/genética
2.
J Neurophysiol ; 125(6): 2228-2236, 2021 06 01.
Artigo em Inglês | MEDLINE | ID: mdl-33978485

RESUMO

The infants experience withdrawal from opiates, and time-dependent adaptations in neuronal activity of nucleus accumbens (NAc) may be crucial for this process. A key adaptation is an increased release of acetylcholine. The present study investigates muscarinic acetylcholine receptors (mAChRs) functions in the NAc at short-term (SWT) and long-term (LWT) withdrawal time following chronic morphine exposure in neonatal rats. The inhibitory role of presynaptic mAChRs activation in spontaneous excitatory postsynaptic currents (sEPSCs) in medium spiny neurons was decreased at LWT but not at SWT. Whereas, the excitatory role of post/extrasynaptic mAChRs activation in membrane currents was reduced at LWT but enhanced at SWT. Furthermore, the inhibitory effect of acute morphine on post/extrasynaptic mAChRs-mediated inward currents was enhanced at SWT but not at LWT. These results suggest that withdrawal from morphine leads to downregulation of presynaptic and post/extrasynaptic mAChRs functions in the NAc, which may coregulate the development of withdrawal in neonates.NEW & NOTEWORTHY We investigated for the first time how the duration of withdrawal affects mAChRs functions in the nucleus accumbens in neonatal rats. Compared with short-term withdrawal time, rats showed downregulation of presynaptic and post/extrasynaptic mAChRs functions during long-term withdrawal time. Our finding introduces a new possible correlation between the mAChRs dysfunction in the nucleus accumbens and the development of withdrawal in neonates.

3.
Brief Bioinform ; 2021 May 03.
Artigo em Inglês | MEDLINE | ID: mdl-33940598

RESUMO

How to produce expressive molecular representations is a fundamental challenge in artificial intelligence-driven drug discovery. Graph neural network (GNN) has emerged as a powerful technique for modeling molecular data. However, previous supervised approaches usually suffer from the scarcity of labeled data and poor generalization capability. Here, we propose a novel molecular pre-training graph-based deep learning framework, named MPG, that learns molecular representations from large-scale unlabeled molecules. In MPG, we proposed a powerful GNN for modelling molecular graph named MolGNet, and designed an effective self-supervised strategy for pre-training the model at both the node and graph-level. After pre-training on 11 million unlabeled molecules, we revealed that MolGNet can capture valuable chemical insights to produce interpretable representation. The pre-trained MolGNet can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of drug discovery tasks, including molecular properties prediction, drug-drug interaction and drug-target interaction, on 14 benchmark datasets. The pre-trained MolGNet in MPG has the potential to become an advanced molecular encoder in the drug discovery pipeline.

4.
Neurosci Bull ; 37(5): 623-640, 2021 May.
Artigo em Inglês | MEDLINE | ID: mdl-33548029

RESUMO

The nucleus accumbens shell (NAcSh) plays an important role in reward and aversion. Traditionally, NAc dopamine receptor 2-expressing (D2) neurons are assumed to function in aversion. However, this has been challenged by recent reports which attribute positive motivational roles to D2 neurons. Using optogenetics and multiple behavioral tasks, we found that activation of D2 neurons in the dorsomedial NAcSh drives preference and increases the motivation for rewards, whereas activation of ventral NAcSh D2 neurons induces aversion. Stimulation of D2 neurons in the ventromedial NAcSh increases movement speed and stimulation of D2 neurons in the ventrolateral NAcSh decreases movement speed. Combining retrograde tracing and in situ hybridization, we demonstrated that glutamatergic and GABAergic neurons in the ventral pallidum receive inputs differentially from the dorsomedial and ventral NAcSh. All together, these findings shed light on the controversy regarding the function of NAcSh D2 neurons, and provide new insights into understanding the heterogeneity of the NAcSh.


Assuntos
Prosencéfalo Basal , Núcleo Accumbens , Neurônios GABAérgicos , Optogenética , Recompensa
5.
Brief Bioinform ; 22(5)2021 09 02.
Artigo em Inglês | MEDLINE | ID: mdl-33479731

RESUMO

Translation elongation is a crucial phase during protein biosynthesis. In this study, we develop a novel deep reinforcement learning-based framework, named Riboexp, to model the determinants of the uneven distribution of ribosomes on mRNA transcripts during translation elongation. In particular, our model employs a policy network to perform a context-dependent feature selection in the setting of ribosome density prediction. Our extensive tests demonstrated that Riboexp can significantly outperform the state-of-the-art methods in predicting ribosome density by up to 5.9% in terms of per-gene Pearson correlation coefficient on the datasets from three species. In addition, Riboexp can indicate more informative sequence features for the prediction task than other commonly used attribution methods in deep learning. In-depth analyses also revealed the meaningful biological insights generated by the Riboexp framework. Moreover, the application of Riboexp in codon optimization resulted in an increase of protein production by around 31% over the previous state-of-the-art method that models ribosome density. These results have established Riboexp as a powerful and useful computational tool in the studies of translation dynamics and protein synthesis. Availability: The data and code of this study are available on GitHub: https://github.com/Liuxg16/Riboexp. Contact:zengjy321@tsinghua.edu.cn; songsen@tsinghua.edu.cn.

6.
Brief Bioinform ; 2020 Nov 04.
Artigo em Inglês | MEDLINE | ID: mdl-33147620

RESUMO

MOTIVATION: Computational methods accelerate drug discovery and play an important role in biomedicine, such as molecular property prediction and compound-protein interaction (CPI) identification. A key challenge is to learn useful molecular representation. In the early years, molecular properties are mainly calculated by quantum mechanics or predicted by traditional machine learning methods, which requires expert knowledge and is often labor-intensive. Nowadays, graph neural networks have received significant attention because of the powerful ability to learn representation from graph data. Nevertheless, current graph-based methods have some limitations that need to be addressed, such as large-scale parameters and insufficient bond information extraction. RESULTS: In this study, we proposed a graph-based approach and employed a novel triplet message mechanism to learn molecular representation efficiently, named triplet message networks (TrimNet). We show that TrimNet can accurately complete multiple molecular representation learning tasks with significant parameter reduction, including the quantum properties, bioactivity, physiology and CPI prediction. In the experiments, TrimNet outperforms the previous state-of-the-art method by a significant margin on various datasets. Besides the few parameters and high prediction accuracy, TrimNet could focus on the atoms essential to the target properties, providing a clear interpretation of the prediction tasks. These advantages have established TrimNet as a powerful and useful computational tool in solving the challenging problem of molecular representation learning. AVAILABILITY: The quantum and drug datasets are available on the website of MoleculeNet: http://moleculenet.ai. The source code is available in GitHub: https://github.com/yvquanli/trimnet. CONTACT: xjyao@lzu.edu.cn, songsen@tsinghua.edu.cn.

7.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 841-846, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018116

RESUMO

Investigating the electroencephalography (EEG) correlates of human emotional experiences has attracted increasing interest in the field of affective computing. Substantial progress has been made during the past decades, mainly by using EEG features extracted from localized brain activities. The present study explored a brain network-based feature defined by EEG microstates for a possible representation of emotional experiences. A publicly available and widely used benchmarking EEG dataset called DEAP was used, in which 32 participants watched 40 one-minute music videos with their 32channel EEG recorded. Four quasi-stable prototypical microstates were obtained, and their temporal parameters were extracted as features. In random forest regression, the microstate features showed better performances for decoding valence (model fitting mean squared error (MSE) = 3.85±0.28 and 4.07 ± 0.30, respectively, p = 0.022) and comparable performances for decoding arousal (MSE = 3.30±0.30 and 3.41 ±0.31, respectively, p = 0.169), as compared to conventional spectral power features. As microstate features describe neural activities from a global spatiotemporal dynamical perspective, our findings demonstrate a possible new mechanism for understanding human emotion and provide a promising type of EEG feature for affective computing.


Assuntos
Nível de Alerta , Eletroencefalografia , Encéfalo , Mapeamento Encefálico , Emoções , Humanos
8.
Sci Rep ; 10(1): 18160, 2020 10 23.
Artigo em Inglês | MEDLINE | ID: mdl-33097742

RESUMO

Recent years have witnessed tremendous progress of intelligent robots brought about by mimicking human intelligence. However, current robots are still far from being able to handle multiple tasks in a dynamic environment as efficiently as humans. To cope with complexity and variability, further progress toward scalability and adaptability are essential for intelligent robots. Here, we report a brain-inspired robotic platform implemented by an unmanned bicycle that exhibits scalability of network scale, quantity and diversity to handle the changing needs of different scenarios. The platform adopts rich coding schemes and a trainable and scalable neural state machine, enabling flexible cooperation of hybrid networks. In addition, an embedded system is developed using a cross-paradigm neuromorphic chip to facilitate the implementation of diverse neural networks in spike or non-spike form. The platform achieved various real-time tasks concurrently in different real-world scenarios, providing a new pathway to enhance robots' intelligence.

9.
Nature ; 586(7829): 378-384, 2020 10.
Artigo em Inglês | MEDLINE | ID: mdl-33057220

RESUMO

Neuromorphic computing draws inspiration from the brain to provide computing technology and architecture with the potential to drive the next wave of computer engineering1-13. Such brain-inspired computing also provides a promising platform for the development of artificial general intelligence14,15. However, unlike conventional computing systems, which have a well established computer hierarchy built around the concept of Turing completeness and the von Neumann architecture16-18, there is currently no generalized system hierarchy or understanding of completeness for brain-inspired computing. This affects the compatibility between software and hardware, impairing the programming flexibility and development productivity of brain-inspired computing. Here we propose 'neuromorphic completeness', which relaxes the requirement for hardware completeness, and a corresponding system hierarchy, which consists of a Turing-complete software-abstraction model and a versatile abstract neuromorphic architecture. Using this hierarchy, various programs can be described as uniform representations and transformed into the equivalent executable on any neuromorphic complete hardware-that is, it ensures programming-language portability, hardware completeness and compilation feasibility. We implement toolchain software to support the execution of different types of program on various typical hardware platforms, demonstrating the advantage of our system hierarchy, including a new system-design dimension introduced by the neuromorphic completeness. We expect that our study will enable efficient and compatible progress in all aspects of brain-inspired computing systems, facilitating the development of various applications, including artificial general intelligence.

10.
Curr Biol ; 30(20): 3986-3998.e5, 2020 10 19.
Artigo em Inglês | MEDLINE | ID: mdl-32822608

RESUMO

A fundamental question of physiology is how gut-brain signaling stimulates appetite. While many studies have emphasized the importance of vagal afferents to the brain in inducing satiation, little is known about whether and how the vagal-mediated gut-brain pathway senses orexigenic signals and stimulates feeding. Here, we identified a previously uncharacterized population of fasting-activated catecholaminergic neurons in the nucleus of the solitary tract (NTS). After characterizing the anatomical complexity among NTS catecholaminergic neurons, we surprisingly found that activation of NTS epinephrine (ENTS) neurons co-expressing neuropeptide Y (NPY) stimulated feeding, whereas activation of NTS norepinephrine (NENTS) neurons suppressed feeding. Monosynaptic tracing/activation experiments then showed that these NTS neurons receive direct vagal afferents from nodose neurons. Moreover, activation of the vagal→NPY/ENTS neural circuit stimulated feeding. Our study reveals an orexigenic role of the vagal→NTS pathway in controlling feeding, thereby providing important insights about how gut-brain signaling regulates feeding behavior.

11.
Nat Nanotechnol ; 15(9): 776-782, 2020 09.
Artigo em Inglês | MEDLINE | ID: mdl-32601451

RESUMO

In the nervous system, dendrites, branches of neurons that transmit signals between synapses and soma, play a critical role in processing functions, such as nonlinear integration of postsynaptic signals. The lack of these critical functions in artificial neural networks compromises their performance, for example in terms of flexibility, energy efficiency and the ability to handle complex tasks. Here, by developing artificial dendrites, we experimentally demonstrate a complete neural network fully integrated with synapses, dendrites and soma, implemented using scalable memristor devices. We perform a digit recognition task and simulate a multilayer network using experimentally derived device characteristics. The power consumption is more than three orders of magnitude lower than that of a central processing unit and 70 times lower than that of a typical application-specific integrated circuit chip. This network, equipped with functional dendrites, shows the potential of substantial overall performance improvement, for example by extracting critical information from a noisy background with significantly reduced power consumption and enhanced accuracy.


Assuntos
Células Artificiais , Dendritos , Animais , Bases de Dados Factuais , Dendritos/fisiologia , Eletrônica , Desenho de Equipamento , Processamento de Imagem Assistida por Computador , Camundongos , Modelos Neurológicos , Redes Neurais de Computação , Neurônios/fisiologia , Oxigênio/química , Sinapses
12.
J Biomater Sci Polym Ed ; 31(12): 1552-1565, 2020 08.
Artigo em Inglês | MEDLINE | ID: mdl-32403996

RESUMO

The biodegradable material poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV) scaffold has good biodegradability, but poor biocompatibility limits its application in the biological field. And it can effectively improve its biological activity by compounding with the bone conduction activity material of Barium titanate (BT). The PHBV and piezoelectric material BT were prepared into porous composite scaffolds with porosity of 45-50%. The mechanical properties and electrical properties of BT/PHBV scaffolds were systematically studied. The results showed that the piezoelectric coefficient d33 was 0.2-1.5 pC/N. Moreover, the compressive strength and elastic modulus were 1.0-2.0 MPa and 100-200 MPa, respectively. The results of degradation and mineralization showed that BT/PHBV scaffolds had good degradation and mineralization performance which was indicated that the materials had good biological activity.

14.
J Dig Dis ; 21(4): 237-245, 2020 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-32166900

RESUMO

OBJECTIVE: To explore the prevalence of and risk factors for gallstone disease in Shanghai, China. METHODS: A population-based cross-sectional study was conducted in Shanghai between 2016 and 2017. Using a three-stage stratified sampling strategy, 4009 participants (1753 men and 2256 women) from 10 districts were enrolled. RESULTS: The overall prevalence of gallstones was 6.83% (6.22% for men vs 7.31% for women, P = 0.173). According to the multivariate analysis, individuals aged ≥40 years (odds ratio [OR] 3.058, 95% confidence interval [CI] 2.110-4.433, P < 0.001), hypertension (OR 1.479, 95% CI 1.076-2.034, P = 0.016), thyroid disease (OR 1.409, 95% CI 1.029-1.928, P = 0.032), a family history of gallstones (OR 2.234, 95% CI 1.362-3.662, P = 0.001) and a waist-to-height ratio ≥0.5 (OR 1.656, 95% CI 1.197-2.292, P = 0.002) had an increased risk of developing gallstones. The risk of gallstone disease was 2.232 (95% CI 1.167-4.268, P = 0.015) times higher in individuals with elevated C4 levels than in those with normal C4 levels. Diabetes (OR 4.144, 95% CI 1.171-14.671, P = 0.028) was a risk factor for the formation of gallstones with diameters ≥1 cm, and men were more susceptible to develop multiple stones (OR 2.356, 95% CI 1.321-4.200, P = 0.004). CONCLUSION: Individuals aged ≥40 years, with a history of hypertension and familial gallstones, a high waist-to-height ratio, thyroid disease and high C4 levels were related to an increased risk of gallstone disease.


Assuntos
Cálculos Biliares/epidemiologia , Cálculos Biliares/etiologia , Adolescente , Adulto , Idoso , China , Complemento C4/análise , Estudos Transversais , Diabetes Mellitus , Feminino , Humanos , Hipertensão/complicações , Masculino , Pessoa de Meia-Idade , Análise Multivariada , Razão de Chances , Prevalência , Fatores de Risco , Doenças da Glândula Tireoide/complicações , Razão Cintura-Estatura , Adulto Jovem
15.
Nucleic Acids Res ; 48(7): 3619-3637, 2020 04 17.
Artigo em Inglês | MEDLINE | ID: mdl-32064513

RESUMO

REV3L, the catalytic subunit of DNA polymerase ζ (Pol ζ), is indispensable for translesion DNA synthesis, which protects cells from deleterious DNA lesions resulting from various intrinsic and environmental sources. However, REV3L lacks a proofreading exonuclease activity and consequently bypasses DNA lesions at the expense of increased mutations, which poses a severe threat to genome stability. Here we report a site-specific proteolytic event of human REV3L. We show that REV3L is cleaved by a threonine aspartase, Taspase1 (TASP1), to generate an N-terminal 70-kDa fragment (N70) and a polypeptide carrying the C-terminal polymerase catalytic domain in human cells. Strikingly, such a post-translational cleavage event plays a vital role in controlling REV3L stability by preventing ubiquitination and proteasome-mediated degradation of REV3L. Indicative of the biological importance of the above REV3L post-translational processing, cellular responses to UV and cisplatin-induced DNA lesions are markedly impaired in human HCT116 cell derivatives bearing defined point mutations in the endogenous REV3L gene that compromise REV3L cleavage. These findings establish a new paradigm in modulating the abundance of REV3L through site-specific proteolysis in human cells.


Assuntos
Proteínas de Ligação a DNA/metabolismo , DNA Polimerase Dirigida por DNA/metabolismo , Motivos de Aminoácidos , Sequência de Aminoácidos , Linhagem Celular , Dano ao DNA , Proteínas de Ligação a DNA/química , DNA Polimerase Dirigida por DNA/química , Endopeptidases/metabolismo , Humanos , Complexo de Endopeptidases do Proteassoma/metabolismo , Estabilidade Proteica , Proteólise , Ubiquitinação
16.
Commun Biol ; 2: 356, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31583287

RESUMO

Sensory responses of the neocortex are strongly influenced by brain state changes. However, it remains unclear whether and how the sensory responses of the midbrain are affected. Here we addressed this issue by using in vivo two-photon calcium imaging to monitor the spontaneous and sound-evoked activities in the mouse inferior colliculus (IC). We developed a method enabling us to image the first layer of non-lemniscal IC (IC shell L1) in awake behaving mice. Compared with the awake state, spectral tuning selectivity of excitatory neurons was decreased during isoflurane anesthesia. Calcium imaging in behaving animals revealed that activities of inhibitory neurons were highly correlated with locomotion. Compared with stationary periods, spectral tuning selectivity of excitatory neurons was increased during locomotion. Taken together, our studies reveal that neuronal activities in the IC shell L1 are brain state dependent, whereas the brain state modulates the excitatory and inhibitory neurons differentially.


Assuntos
Colículos Inferiores/citologia , Colículos Inferiores/fisiologia , Locomoção/fisiologia , Neurônios/citologia , Neurônios/fisiologia , Percepção/fisiologia , Anestésicos Inalatórios/farmacologia , Animais , Cálcio/metabolismo , Feminino , Colículos Inferiores/efeitos dos fármacos , Isoflurano/farmacologia , Masculino , Camundongos Endogâmicos C57BL , Camundongos Transgênicos , Neurônios/efeitos dos fármacos , Percepção/efeitos dos fármacos , Uretana/farmacologia , Vigília/efeitos dos fármacos , Vigília/fisiologia
17.
Adv Mater ; 31(49): e1902761, 2019 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-31550405

RESUMO

As the research on artificial intelligence booms, there is broad interest in brain-inspired computing using novel neuromorphic devices. The potential of various emerging materials and devices for neuromorphic computing has attracted extensive research efforts, leading to a large number of publications. Going forward, in order to better emulate the brain's functions, its relevant fundamentals, working mechanisms, and resultant behaviors need to be re-visited, better understood, and connected to electronics. A systematic overview of biological and artificial neural systems is given, along with their related critical mechanisms. Recent progress in neuromorphic devices is reviewed and, more importantly, the existing challenges are highlighted to hopefully shed light on future research directions.


Assuntos
Biomimética/instrumentação , Eletrônica/instrumentação , Rede Nervosa/fisiologia , Animais , Materiais Biomiméticos/química , Desenho de Equipamento , Humanos , Rede Nervosa/anatomia & histologia , Redes Neurais de Computação
18.
Nature ; 572(7767): 106-111, 2019 08.
Artigo em Inglês | MEDLINE | ID: mdl-31367028

RESUMO

There are two general approaches to developing artificial general intelligence (AGI)1: computer-science-oriented and neuroscience-oriented. Because of the fundamental differences in their formulations and coding schemes, these two approaches rely on distinct and incompatible platforms2-8, retarding the development of AGI. A general platform that could support the prevailing computer-science-based artificial neural networks as well as neuroscience-inspired models and algorithms is highly desirable. Here we present the Tianjic chip, which integrates the two approaches to provide a hybrid, synergistic platform. The Tianjic chip adopts a many-core architecture, reconfigurable building blocks and a streamlined dataflow with hybrid coding schemes, and can not only accommodate computer-science-based machine-learning algorithms, but also easily implement brain-inspired circuits and several coding schemes. Using just one chip, we demonstrate the simultaneous processing of versatile algorithms and models in an unmanned bicycle system, realizing real-time object detection, tracking, voice control, obstacle avoidance and balance control. Our study is expected to stimulate AGI development by paving the way to more generalized hardware platforms.

19.
IEEE Trans Neural Netw Learn Syst ; 30(11): 3484-3495, 2019 11.
Artigo em Inglês | MEDLINE | ID: mdl-30794190

RESUMO

Automatic diagnosing lung cancer from computed tomography scans involves two steps: detect all suspicious lesions (pulmonary nodules) and evaluate the whole-lung/pulmonary malignancy. Currently, there are many studies about the first step, but few about the second step. Since the existence of nodule does not definitely indicate cancer, and the morphology of nodule has a complicated relationship with cancer, the diagnosis of lung cancer demands careful investigations on every suspicious nodule and integration of information of all nodules. We propose a 3-D deep neural network to solve this problem. The model consists of two modules. The first one is a 3-D region proposal network for nodule detection, which outputs all suspicious nodules for a subject. The second one selects the top five nodules based on the detection confidence, evaluates their cancer probabilities, and combines them with a leaky noisy-OR gate to obtain the probability of lung cancer for the subject. The two modules share the same backbone network, a modified U-net. The overfitting caused by the shortage of the training data is alleviated by training the two modules alternately. The proposed model won the first place in the Data Science Bowl 2017 competition.


Assuntos
Diagnóstico por Computador/métodos , Imageamento Tridimensional/métodos , Neoplasias Pulmonares/diagnóstico por imagem , Redes Neurais de Computação , Tomografia Computadorizada por Raios X/métodos , Humanos
20.
IEEE Trans Cybern ; 49(2): 495-504, 2019 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-29990055

RESUMO

Segmenting human left ventricle (LV) in magnetic resonance imaging images and calculating its volume are important for diagnosing cardiac diseases. The latter task became the topic of the Second Annual Data Science Bowl organized by Kaggle. The dataset consisted of a large number of cases with only systole and diastole volume labels. We designed a system based on neural networks to solve this problem. It began with a detector to detect the regions of interest (ROI) containing LV chambers. Then a deep neural network named hypercolumns fully convolutional network was used to segment LV in ROI. The 2-D segmentation results were integrated across different images to estimate the volume. With ground-truth volume labels, this model was trained end-to-end. To improve the result, an additional dataset with only segmentation labels was used. The model was trained alternately on these two tasks. We also proposed a variance estimation method for the final prediction. Our algorithm ranked the fourth on the test set in this competition.


Assuntos
Ventrículos do Coração/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Redes Neurais de Computação , Algoritmos , Bases de Dados Factuais , Humanos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...