Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 14 de 14
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
iScience ; 25(11): 105382, 2022 Nov 18.
Artigo em Inglês | MEDLINE | ID: mdl-36345339

RESUMO

Immunotherapy shows durable response but only in a subset of patients, and test for predictive biomarkers requires procedures in addition to routine workflow. We proposed a confounder-aware representation learning-based system, genopathomic biomarker for immunotherapy response (PITER), that uses only diagnosis-acquired hematoxylin-eosin (H&E)-stained pathological slides by leveraging histopathological and genetic characteristics to identify candidates for immunotherapy. PITER was generated and tested with three datasets containing 1944 slides of 1239 patients. PITER was found to be a useful biomarker to identify patients of lung adenocarcinoma with both favorable progression-free and overall survival in the immunotherapy cohort (p < 0.05). PITER was significantly associated with pathways involved in active cell division and a more immune activating microenvironment, which indicated the biological basis in identifying patients with favorable outcome of immunotherapy. Thus, PITER may be a potential biomarker to identify patients of lung adenocarcinoma with a good response to immunotherapy, and potentially provide precise treatment.

2.
Commun Biol ; 5(1): 1263, 2022 Nov 18.
Artigo em Inglês | MEDLINE | ID: mdl-36400937

RESUMO

Upcoming technologies enable routine collection of highly multiplexed (20-60 channel), subcellular resolution images of mammalian tissues for research and diagnosis. Extracting single cell data from such images requires accurate image segmentation, a challenging problem commonly tackled with deep learning. In this paper, we report two findings that substantially improve image segmentation of tissues using a range of machine learning architectures. First, we unexpectedly find that the inclusion of intentionally defocused and saturated images in training data substantially improves subsequent image segmentation. Such real augmentation outperforms computational augmentation (Gaussian blurring). In addition, we find that it is practical to image the nuclear envelope in multiple tissues using an antibody cocktail thereby better identifying nuclear outlines and improving segmentation. The two approaches cumulatively and substantially improve segmentation on a wide range of tissue types. We speculate that the use of real augmentations will have applications in image processing outside of microscopy.


Assuntos
Aprendizado Profundo , Humanos , Animais , Processamento de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Núcleo Celular , Mamíferos
3.
Micromachines (Basel) ; 13(9)2022 Aug 26.
Artigo em Inglês | MEDLINE | ID: mdl-36144018

RESUMO

With the development of cross-fertilisation in various disciplines, flexible wearable sensing technologies have emerged, bringing together many disciplines, such as biomedicine, materials science, control science, and communication technology. Over the past few years, the development of multiple types of flexible wearable devices that are widely used for the detection of human physiological signals has proven that flexible wearable devices have strong biocompatibility and a great potential for further development. These include electronic skin patches, soft robots, bio-batteries, and personalised medical devices. In this review, we present an updated overview of emerging flexible wearable sensor devices for biomedical applications and a comprehensive summary of the research progress and potential of flexible sensors. First, we describe the selection and fabrication of flexible materials and their excellent electrochemical properties. We evaluate the mechanisms by which these sensor devices work, and then we categorise and compare the unique advantages of a variety of sensor devices from the perspective of in vitro and in vivo sensing, as well as some exciting applications in the human body. Finally, we summarise the opportunities and challenges in the field of flexible wearable devices.

4.
Sci Rep ; 12(1): 11349, 2022 07 05.
Artigo em Inglês | MEDLINE | ID: mdl-35790766

RESUMO

Following significant advances in image acquisition, synapse detection, and neuronal segmentation in connectomics, researchers have extracted an increasingly diverse set of wiring diagrams from brain tissue. Neuroscientists frequently represent these wiring diagrams as graphs with nodes corresponding to a single neuron and edges indicating synaptic connectivity. The edges can contain "colors" or "labels", indicating excitatory versus inhibitory connections, among other things. By representing the wiring diagram as a graph, we can begin to identify motifs, the frequently occurring subgraphs that correspond to specific biological functions. Most analyses on these wiring diagrams have focused on hypothesized motifs-those we expect to find. However, one of the goals of connectomics is to identify biologically-significant motifs that we did not previously hypothesize. To identify these structures, we need large-scale subgraph enumeration to find the frequencies of all unique motifs. Exact subgraph enumeration is a computationally expensive task, particularly in the edge-dense wiring diagrams. Furthermore, most existing methods do not differentiate between types of edges which can significantly affect the function of a motif. We propose a parallel, general-purpose subgraph enumeration strategy to count motifs in the connectome. Next, we introduce a divide-and-conquer community-based subgraph enumeration strategy that allows for enumeration per brain region. Lastly, we allow for differentiation of edges by types to better reflect the underlying biological properties of the graph. We demonstrate our results on eleven connectomes and publish for future analyses extensive overviews for the 26 trillion subgraphs enumerated that required approximately 9.25 years of computation time.


Assuntos
Conectoma , Encéfalo/diagnóstico por imagem , Neurônios , Editoração , Sinapses
5.
IEEE Trans Med Imaging ; 41(9): 2360-2370, 2022 09.
Artigo em Inglês | MEDLINE | ID: mdl-35377840

RESUMO

As connectomic datasets exceed hundreds of terabytes in size, accurate and efficient skeleton generation of the label volumes has evolved into a critical component of the computation pipeline used for analysis, evaluation, visualization, and error correction. We propose a novel topological thinning strategy that uses biological-constraints to produce accurate centerlines from segmented neuronal volumes while still maintaining biologically relevant properties. Current methods are either agnostic to the underlying biology, have non-linear running times as a function of the number of input voxels, or both. First, we eliminate from the input segmentation biologically-infeasible bubbles, pockets of voxels incorrectly labeled within a neuron, to improve segmentation accuracy, allow for more accurate centerlines, and increase processing speed. Next, a Convolutional Neural Network (CNN) detects cell bodies from the input segmentation, allowing us to anchor our skeletons to the somata. Lastly, a synapse-aware topological thinning approach produces expressive skeletons for each neuron with a nearly one-to-one correspondence between endpoints and synapses. We simultaneously estimate geometric properties of neurite width and geodesic distance between synapse and cell body, improving accuracy by 47.5% and 62.8% over baseline methods. We separate the skeletonization process into a series of computation steps, leveraging data-parallel strategies to increase throughput significantly. We demonstrate our results on over 1250 neurons and neuron fragments from three different species, processing over one million voxels per second per CPU with linear scalability.


Assuntos
Conectoma , Processamento de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Esqueleto
6.
J Hazard Mater ; 423(Pt B): 127137, 2022 02 05.
Artigo em Inglês | MEDLINE | ID: mdl-34560486

RESUMO

Most natural polymers exhibit limited functional groups, which is not favourable for the adsorption of various ions and their utilisation. To overcome this drawback, a novel in-situ-doped nano-calcium carbonate (CaCO3) chitin hydrogel was synthesised as an efficient adsorbent for Cu (II) and Cd (II) ions. Scanning electron microscopy and Brunauer-Emmett-Teller results revealed that the synthesised CaCO3/chitin hydrogel exhibited loose macropores and mesopores. Subsequently, Fourier transform infrared, Raman, and X-ray diffraction characterisation characterisation proved that chitin was successfully doped with nano-CaCO3. The mechanical properties of CaCO3/chitin hydrogel were superior to those of the unmodified chitin hydrogel and could efficiently adsorb Cu (II) and Cd (II) ions in water. The effect of pH, initial concentration, adsorbent dosage, and temperature was assessed to determine the adsorption properties of the hydrogel. Under suitable experimental conditions, the maximum adsorption rate of the CaCO3/chitin hydrogel was approximately 96%. The time-dependent adsorption kinetics followed a quasi-second order model, and the adsorption process followed the Langmuir model. The maximum adsorption capacities of Cu (II) and Cd (II) according to the Langmuir curve were 194.61 and 191.58 mg/g, respectively. Compared with the binary competitive system, the material exhibited a specific selectivity to the adsorption of Cu (II). X-ray photoelectron spectroscopy (XPS) revealed that nitrogen and oxygen atoms were involved in chelation with the metal ions. The successful compounding of calcium carbonate nanoparticles provided more active adsorption sites for the gel. The novel material exhibited excellent adsorption effects on Cu (II) and Cd (II) ions when applied to a water sample. Thus, the novel material exhibits excellent potential for application. The Cu (II) and Cd (II)ion removal efficiencies after five successive adsorption cycles were higher than 90%, which indicated that the composite material exhibited excellent stability and reproducibility.


Assuntos
Cádmio , Poluentes Químicos da Água , Adsorção , Carbonato de Cálcio , Quitina , Cobre , Hidrogéis , Concentração de Íons de Hidrogênio , Íons , Cinética , Reprodutibilidade dos Testes , Poluentes Químicos da Água/análise
7.
Artigo em Inglês | MEDLINE | ID: mdl-34671767

RESUMO

The developmental process of embryos follows a monotonic order. An embryo can progressively cleave from one cell to multiple cells and finally transform to morula and blastocyst. For time-lapse videos of embryos, most existing developmental stage classification methods conduct per-frame predictions using an image frame at each time step. However, classification using only images suffers from overlapping between cells and imbalance between stages. Temporal information can be valuable in addressing this problem by capturing movements between neighboring frames. In this work, we propose a two-stream model for developmental stage classification. Unlike previous methods, our two-stream model accepts both temporal and image information. We develop a linear-chain conditional random field (CRF) on top of neural network features extracted from the temporal and image streams to make use of both modalities. The linear-chain CRF formulation enables tractable training of global sequential models over multiple frames while also making it possible to inject monotonic development order constraints into the learning process explicitly. We demonstrate our algorithm on two time-lapse embryo video datasets: i) mouse and ii) human embryo datasets. Our method achieves 98.1% and 80.6% for mouse and human embryo stage classification, respectively. Our approach will enable more pro-found clinical and biological studies and suggests a new direction for developmental stage classification by utilizing temporal information.

8.
Proc IEEE Int Conf Comput Vis ; 2021: 4268-4277, 2021 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-35368831

RESUMO

Deep convolutional neural networks (CNNs) have pushed forward the frontier of super-resolution (SR) research. However, current CNN models exhibit a major flaw: they are biased towards learning low-frequency signals. This bias becomes more problematic for the image SR task which targets reconstructing all fine details and image textures. To tackle this challenge, we propose to improve the learning of high-frequency features both locally and globally and introduce two novel architectural units to existing SR models. Specifically, we propose a dynamic highpass filtering (HPF) module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals. We also propose a matrix multi-spectral channel attention (MMCA) module that predicts the attention map of features decomposed in the frequency domain. This module operates in a global context to adaptively recalibrate feature responses at different frequencies. Extensive qualitative and quantitative results demonstrate that our proposed modules achieve better accuracy and visual improvements against state-of-the-art methods on several benchmark datasets.

9.
Artigo em Inglês | MEDLINE | ID: mdl-33283211

RESUMO

Interest is growing rapidly in using deep learning to classify biomedical images, and interpreting these deep-learned models is necessary for life-critical decisions and scientific discovery. Effective interpretation techniques accelerate biomarker discovery and provide new insights into the etiology, diagnosis, and treatment of disease. Most interpretation techniques aim to discover spatially-salient regions within images, but few techniques consider imagery with multiple channels of information. For instance, highly multiplexed tumor and tissue images have 30-100 channels and require interpretation methods that work across many channels to provide deep molecular insights. We propose a novel channel embedding method that extracts features from each channel. We then use these features to train a classifier for prediction. Using this channel embedding, we apply an interpretation method to rank the most discriminative channels. To validate our approach, we conduct an ablation study on a synthetic dataset. Moreover, we demonstrate that our method aligns with biological findings on highly multiplexed images of breast cancer cells while outperforming baseline pipelines. Code is available at https://sabdelmagid.github.io/miccai2020-project/.

10.
Med Image Comput Comput Assist Interv ; 12265: 66-76, 2020 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-33283212

RESUMO

Electron microscopy (EM) allows the identification of intracellular organelles such as mitochondria, providing insights for clinical and scientific studies. However, public mitochondria segmentation datasets only contain hundreds of instances with simple shapes. It is unclear if existing methods achieving human-level accuracy on these small datasets are robust in practice. To this end, we introduce the MitoEM dataset, a 3D mitochondria instance segmentation dataset with two (30µm)3 volumes from human and rat cortices respectively, 3, 600× larger than previous benchmarks. With around 40K instances, we find a great diversity of mitochondria in terms of shape and density. For evaluation, we tailor the implementation of the average precision (AP) metric for 3D data with a 45× speedup. On MitoEM, we find existing instance segmentation methods often fail to correctly segment mitochondria with complex shapes or close contacts with other instances. Thus, our MitoEM dataset poses new challenges to the field. We release our code and data: https://donglaiw.github.io/page/mitoEM/index.html.

11.
Comput Vis ECCV ; 12363: 103-120, 2020 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-33345257

RESUMO

For large-scale vision tasks in biomedical images, the labeled data is often limited to train effective deep models. Active learning is a common solution, where a query suggestion method selects representative unlabeled samples for annotation, and the new labels are used to improve the base model. However, most query suggestion models optimize their learnable parameters only on the limited labeled data and consequently become less effective for the more challenging unlabeled data. To tackle this, we propose a two-stream active query suggestion approach. In addition to the supervised feature extractor, we introduce an unsupervised one optimized on all raw images to capture diverse image features, which can later be improved by fine-tuning on new labels. As a use case, we build an end-to-end active learning framework with our query suggestion method for 3D synapse detection and mitochondria segmentation in connectomics. With the framework, we curate, to our best knowledge, the largest connectomics dataset with dense synapses and mitochondria annotation. On this new dataset, our method outperforms previous state-of-the-art methods by 3.1% for synapse and 3.8% for mitochondria in terms of region-of-interest proposal accuracy. We also apply our method to image classification, where it outperforms previous approaches on CIFAR-10 under the same limited annotation budget. The project page is https://zudi-lin.github.io/projects/#two_stream_active.

12.
Sci Adv ; 6(18): eaaz1166, 2020 May.
Artigo em Inglês | MEDLINE | ID: mdl-32494671

RESUMO

The unique properties of nonlinear waves have been recently exploited to enable a wide range of applications, including impact mitigation, asymmetric transmission, switching, and focusing. Here, we demonstrate that the propagation of nonlinear waves can be as well harnessed to make flexible structures crawl. By combining experimental and theoretical methods, we show that such pulse-driven locomotion reaches a maximum efficiency when the initiated pulses are solitons and that our simple machine can move on a wide range of surfaces and even steer. Our study expands the range of possible applications of nonlinear waves and demonstrates that they offer a new platform to make flexible machines to move.

13.
Proc Natl Acad Sci U S A ; 114(44): 11639-11644, 2017 10 31.
Artigo em Inglês | MEDLINE | ID: mdl-29078275

RESUMO

Although the human visual system is remarkable at perceiving and interpreting motions, it has limited sensitivity, and we cannot see motions that are smaller than some threshold. Although difficult to visualize, tiny motions below this threshold are important and can reveal physical mechanisms, or be precursors to large motions in the case of mechanical failure. Here, we present a "motion microscope," a computational tool that quantifies tiny motions in videos and then visualizes them by producing a new video in which the motions are made large enough to see. Three scientific visualizations are shown, spanning macroscopic to nanoscopic length scales. They are the resonant vibrations of a bridge demonstrating simultaneous spatial and temporal modal analysis, micrometer vibrations of a metamaterial demonstrating wave propagation through an elastic matrix with embedded resonating units, and nanometer motions of an extracellular tissue found in the inner ear demonstrating a mechanism of frequency separation in hearing. In these instances, the motion microscope uncovers hidden dynamics over a variety of length scales, leading to the discovery of previously unknown phenomena.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Microscopia/métodos , Gravação em Vídeo , Lasers , Movimento (Física)
14.
Bioinformatics ; 27(18): 2486-93, 2011 Sep 15.
Artigo em Inglês | MEDLINE | ID: mdl-21788211

RESUMO

MOTIVATION: RNA secondary structure plays an important role in the function of many RNAs, and structural features are often key to their interaction with other cellular components. Thus, there has been considerable interest in the prediction of secondary structures for RNA families. In this article, we present a new global structural alignment algorithm, RNAG, to predict consensus secondary structures for unaligned sequences. It uses a blocked Gibbs sampling algorithm, which has a theoretical advantage in convergence time. This algorithm iteratively samples from the conditional probability distributions P(Structure | Alignment) and P(Alignment | Structure). Not surprisingly, there is considerable uncertainly in the high-dimensional space of this difficult problem, which has so far received limited attention in this field. We show how the samples drawn from this algorithm can be used to more fully characterize the posterior space and to assess the uncertainty of predictions. RESULTS: Our analysis of three publically available datasets showed a substantial improvement in RNA structure prediction by RNAG over extant prediction methods. Additionally, our analysis of 17 RNA families showed that the RNAG sampled structures were generally compact around their ensemble centroids, and at least 11 families had at least two well-separated clusters of predicted structures. In general, the distance between a reference structure and our predicted structure was large relative to the variation among structures within an ensemble. AVAILABILITY: The Perl implementation of the RNAG algorithm and the data necessary to reproduce the results described in Sections 3.1 and 3.2 are available at http://ccmbweb.ccv.brown.edu/rnag.html CONTACT: charles_lawrence@brown.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.


Assuntos
Conformação de Ácido Nucleico , RNA/química , Análise de Sequência de RNA/métodos , Algoritmos , Sequência de Bases , Análise por Conglomerados , Dados de Sequência Molecular , Alinhamento de Sequência
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...