Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 42.157
Filtrar
1.
Int J Mol Sci ; 22(10)2021 May 13.
Artículo en Inglés | MEDLINE | ID: mdl-34067987

RESUMEN

Intraepithelial lymphocytes (IEL) are widely distributed within the small intestinal epithelial cell (IEC) layer and represent one of the largest T cell pools of the body. While implicated in the pathogenesis of intestinal inflammation, detailed insight especially into the cellular cross-talk between IELs and IECs is largely missing in part due to lacking methodologies to monitor this interaction. To overcome this shortcoming, we employed and validated a murine IEL-IEC (organoids) ex vivo co-culture model system. Using livecell imaging we established a protocol to visualize and quantify the spatio-temporal migratory behavior of IELs within organoids over time. Applying this methodology, we found that IELs lacking CD103 (i.e., integrin alpha E, ITGAE) surface expression usually functioning as a retention receptor for IELs through binding to E-cadherin (CD324) expressing IECs displayed aberrant mobility and migration patterns. Specifically, CD103 deficiency affected the ability of IELs to migrate and reduced their speed during crawling within organoids. In summary, we report a new technology to monitor and quantitatively assess especially migratory characteristics of IELs communicating with IEC ex vivo. This approach is hence readily applicable to study the effects of targeted therapeutic interventions on IEL-IEC cross-talk.


Asunto(s)
Antígenos CD/metabolismo , Movimiento Celular , Procesamiento de Imagen Asistido por Computador/métodos , Cadenas alfa de Integrinas/metabolismo , Mucosa Intestinal/metabolismo , Linfocitos Intraepiteliales/metabolismo , Organoides/metabolismo , Linfocitos T/fisiología , Animales , Técnicas de Cocultivo , Técnica del Anticuerpo Fluorescente , Mucosa Intestinal/citología , Linfocitos Intraepiteliales/citología , Ratones , Organoides/citología , Análisis Espacio-Temporal
2.
Medicine (Baltimore) ; 100(22): e26212, 2021 Jun 04.
Artículo en Inglés | MEDLINE | ID: mdl-34087897

RESUMEN

ABSTRACT: To investigate the diagnostic value of a computed tomography (CT) scan-based radiomics model for acute aortic dissection.For the dissection group, we retrospectively selected 50 patients clinically diagnosed with acute aortic dissection between October 2018 and November 2019, for whom non-contrast CT and CT angiography images were available. Fifty individuals with available non-contrast CT and CT angiography images for other causes were selected for inclusion in the non-dissection group. Based on the aortic dissection locations on the CT angiography images, we marked the corresponding regions-of-interest on the non-contrast CT images of both groups. We collected 1203 characteristic parameters from these regions by extracting radiomics features. Subsequently, we used a random number table to include 70 individuals in the training group and 30 in the validation group. Finally, we used the Lasso regression for dimension reduction and predictive model construction. The diagnostic performance of the model was evaluated by a receiver operating characteristic (ROC) curve.Fourteen characteristic parameters with non-zero coefficients were selected after dimension reduction. The accuracy, sensitivity, specificity, and area under the ROC curve of the prediction model for the training group were 94.3% (66/70), 91.2% (31/34), 97.2% (35/36), and 0.988 (95% confidence interval [CI]: 0.970-0.998), respectively. The respective values for the validation group were 90.0% (27/30), 94.1% (16/17), 84.6% (11/13), and 0.952 (95% CI: 0.883-0.986).Our non-contrast CT scan-based radiomics model accurately facilitated acute aortic dissection diagnosis.


Asunto(s)
Aneurisma Disecante/diagnóstico por imagen , Aorta/patología , Aneurisma de la Aorta/complicaciones , Tomografía Computarizada por Rayos X/métodos , Enfermedad Aguda , Adulto , Anciano , Angiografía por Tomografía Computarizada/métodos , Femenino , Humanos , Aumento de la Imagen/instrumentación , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , Persona de Mediana Edad , Curva ROC , Estudios Retrospectivos , Sensibilidad y Especificidad
3.
Medicine (Baltimore) ; 100(22): e25878, 2021 Jun 04.
Artículo en Inglés | MEDLINE | ID: mdl-34087829

RESUMEN

ABSTRACT: The study aimed to explore the value of ultrasound (US) texture analysis in the differential diagnosis of triple-negative breast cancer (TNBC) and non-TNBC.Retrospective analysis was done on 93 patients with breast cancer (35 patients with TNBC and 38 patients with non-TNBC) who were admitted to Taizhou people's hospital from July 2015 to June 2019. All lesions were pathologically proven at surgery. US images of all patients were collected. Texture analysis of US images was performed using MaZda software package. The differences between textural features in TNBC and non-TNBC were assessed. Receiver operating characteristic curve analysis was used to compare the diagnostic performance of textural parameters showing significant difference.Five optimal texture feature parameters were extracted from gray level run-length matrix, including gray level non-uniformity (GLNU) in horizontal direction, vertical gray level non-uniformity, GLNU in the 45 degree direction, run length non-uniformity in 135 degree direction, GLNU in the 135 degree direction. All these texture parameters were statistically higher in TNBC than in non-TNBC (P <.05). Receiver operating characteristic curve analysis indicated that at a threshold of 268.9068, GLNU in horizontal direction exhibited best diagnostic performance for differentiating TNBC from non-TNBC. Logistic regression model established based on all these parameters showed a sensitivity of 69.3%, specificity of 91.4% and area under the curve of 0.834.US texture features were significantly different between TNBC and non-TNBC, US texture analysis can be used for preliminary differentiation of TNBC from non-TNBC.


Asunto(s)
Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/patología , Procesamiento de Imagen Asistido por Computador/métodos , Ultrasonografía/métodos , Adulto , Anciano , Anciano de 80 o más Años , Neoplasias de la Mama/cirugía , Femenino , Humanos , Persona de Mediana Edad , Curva ROC , Estudios Retrospectivos , Neoplasias de la Mama Triple Negativas/diagnóstico por imagen , Neoplasias de la Mama Triple Negativas/patología
4.
Nat Commun ; 12(1): 2963, 2021 05 20.
Artículo en Inglés | MEDLINE | ID: mdl-34017001

RESUMEN

Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation.


Asunto(s)
Enfermedades Cardiovasculares/epidemiología , Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Neoplasias Pulmonares/diagnóstico , Tamizaje Masivo/estadística & datos numéricos , Adulto , Anciano , Anciano de 80 o más Años , Enfermedades Cardiovasculares/diagnóstico , Enfermedades Cardiovasculares/etiología , Ensayos Clínicos como Asunto , Vasos Coronarios/diagnóstico por imagen , Conjuntos de Datos como Asunto , Electrocardiografía , Femenino , Estudios de Seguimiento , Humanos , Pulmón/diagnóstico por imagen , Neoplasias Pulmonares/complicaciones , Masculino , Tamizaje Masivo/métodos , Persona de Mediana Edad , Curva ROC , Estudios Retrospectivos , Medición de Riesgo/métodos , Medición de Riesgo/estadística & datos numéricos , Factores de Riesgo , Tomografía Computarizada por Rayos X/estadística & datos numéricos
5.
Comput Intell Neurosci ; 2021: 5527923, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-33936188

RESUMEN

This paper aims to investigate the use of transfer learning architectures in the detection of COVID-19 from CT lung scans. The study evaluates the performances of various transfer learning architectures, as well as the effects of the standard Histogram Equalization and Contrast Limited Adaptive Histogram Equalization. The findings of this study suggest that transfer learning-based frameworks are an alternative to the contemporary methods used to detect the presence of the virus in patients. The highest performing model, the VGG-19 implemented with the Contrast Limited Adaptive Histogram Equalization, on a SARS-CoV-2 dataset, achieved an accuracy and recall of 95.75% and 97.13%, respectively.


Asunto(s)
COVID-19/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Pulmón/diagnóstico por imagen , Aprendizaje Automático , SARS-CoV-2 , Tomografía Computarizada por Rayos X/métodos , Área Bajo la Curva , Conjuntos de Datos como Asunto , Diagnóstico por Computador , Humanos , Pulmón/virología , Curva ROC
6.
Nat Commun ; 12(1): 2646, 2021 05 11.
Artículo en Inglés | MEDLINE | ID: mdl-33976168

RESUMEN

Positron Emission Tomography (PET) is a widely-used imaging modality for medical research and clinical diagnosis. Imaging of the radiotracer is obtained from the detected hit positions of the two positron annihilation photons in a detector array. The image is degraded by backgrounds from random coincidences and in-patient scatter events which require correction. In addition to the geometric information, the two annihilation photons are predicted to be produced in a quantum-entangled state, resulting in enhanced correlations between their subsequent interaction processes. To explore this, the predicted entanglement in linear polarisation for the two photons was incorporated into a simulation and tested by comparison with experimental data from a cadmium zinc telluride (CZT) PET demonstrator apparatus. Adapted apparati also enabled correlation measurements where one of the photons had undergone a prior scatter process. We show that the entangled simulation describes the measured correlations and, through simulation of a larger preclinical PET scanner, illustrate a simple method to quantify and remove the unwanted backgrounds in PET using the quantum entanglement information alone.


Asunto(s)
Algoritmos , Cadmio/química , Modelos Teóricos , Fotones , Tomografía de Emisión de Positrones/métodos , Telurio/química , Zinc/química , Simulación por Computador , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Fantasmas de Imagen , Tomografía de Emisión de Positrones/instrumentación
7.
Biomed Phys Eng Express ; 7(4)2021 05 20.
Artículo en Inglés | MEDLINE | ID: mdl-33979791

RESUMEN

Segmenting lesion regions of Coronavirus Disease 2019 (COVID-19) from computed tomography (CT) images is a challenge owing to COVID-19 lesions characterized by high variation, low contrast between infection lesions and around normal tissues, and blurred boundaries of infections. Moreover, a shortage of available CT dataset hinders deep learning techniques applying to tackling COVID-19. To address these issues, we propose a deep learning-based approach known as PPM-Unet to segmenting COVID-19 lesions from CT images. Our method improves an Unet by adopting pyramid pooling modules instead of the conventional skip connection and then enhances the representation of the neural network by aiding the global attention mechanism. We first pre-train PPM-Unet on COVID-19 dataset of pseudo labels containing1600 samples producing a coarse model. Then we fine-tune the coarse PPM-Unet on the standard COVID-19 dataset consisting of 100 pairs of samples to achieve a fine PPM-Unet. Qualitative and quantitative results demonstrate that our method can accurately segment COVID-19 infection regions from CT images, and achieve higher performance than other state-of-the-art segmentation models in this study. It offers a promising tool to lay a foundation for quantitatively detecting COVID-19 lesions.


Asunto(s)
COVID-19/complicaciones , Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Enfermedades Pulmonares/patología , Redes Neurales de la Computación , SARS-CoV-2/aislamiento & purificación , Tomografía Computarizada por Rayos X/métodos , Algoritmos , COVID-19/virología , Humanos , Enfermedades Pulmonares/diagnóstico por imagen , Enfermedades Pulmonares/virología , Manejo de Especímenes
8.
Methods Mol Biol ; 2274: 3-14, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34050457

RESUMEN

The nuclear envelope (NE), a double membrane that separates nuclear components from the cytoplasm, undergoes a breakdown and reformation during cell division. To trace NE dynamics, the NE needs to be labeled with a fluorescent marker, and for this purpose, markers based on inner nuclear membrane (INM) proteins are normally used. However, NE labeling with INM proteins has some limitations. Here, we introduce a protocol for fluorescent labeling and imaging of NE that does not rely on INM proteins, along with protocols for simultaneously imaging two nuclear components and for time-lapse imaging of labeled cells.


Asunto(s)
Núcleo Celular/metabolismo , Proteínas Fluorescentes Verdes/metabolismo , Procesamiento de Imagen Asistido por Computador/métodos , Membrana Nuclear/metabolismo , Espectrometría de Fluorescencia/métodos , Células HeLa , Humanos
9.
Methods Mol Biol ; 2274: 37-42, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34050460

RESUMEN

The current standard murine model of bone metastasis by using intracardiac injection (IC) has some limitations despite the great utility of this model. This fact emphasizes the need for a new murine model to accelerate basic research of bone metastasis. The present protocol provides instructions on caudal artery (CA) injection that is an easy-to-use method to reliably construct a murine bone metastasis model with a variety type of cancer cell lines. Bioluminescence imaging visualized that cancer cells injected via the caudal artery in the tail were efficiently delivered to a hind limb bone, where it is a common site affected with bone metastasis in mice. CA injection rarely causes stress-induced acute death in mice and enables us to inject a large number of cancer cells, thereby greatly increasing the frequency of bone metastasis in hind limb bones. Importantly, CA injection is technically as easy as tail vein injection and causes no lethal stress, indicating that it is a model that also contributes to animal welfare. CA injection model, therefore, could represent a powerful tool for many researchers to study molecular mechanisms of bone metastasis in mice.


Asunto(s)
Neoplasias Óseas/secundario , Carcinoma Pulmonar de Lewis/patología , Arterias Carótidas/patología , Procesamiento de Imagen Asistido por Computador/métodos , Mediciones Luminiscentes/métodos , Animales , Neoplasias Óseas/diagnóstico por imagen , Carcinoma Pulmonar de Lewis/diagnóstico por imagen , Arterias Carótidas/diagnóstico por imagen , Ratones
10.
Methods Mol Biol ; 2274: 69-78, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34050463

RESUMEN

G Protein-coupled receptors (GPCRs) transduce signals elicited by bioactive chemical agents (ligands), such as hormones, neurotransmitters, or cytokines, across the cellular membrane. Upon ligand binding, the receptor undergoes structural rearrangements, which cause the activation of G proteins. This triggers the activation of signaling cascades involving amplification, which takes place after every stage of the cascade. Consequently, signals from early stages can be masked when the activation of the signaling cascade is probed remote (distal) from the receptor. This led to the development of several techniques, which probe the activation of such signaling cascades as proximal to the receptor as possible. However, these methods often require specialized equipment or are limited in throughput. By applying split-luciferase complementation to the interaction between the Gαq protein and its effector the phospholipase C-ß3 (PLC-ß3), we introduce a protocol with a conventional plate reader at high throughput. The method is applicable to live cells and additionally allows imaging of the probe by bioluminescence microscopy.


Asunto(s)
Membrana Celular/metabolismo , Procesamiento de Imagen Asistido por Computador/métodos , Luciferasas/metabolismo , Mediciones Luminiscentes/métodos , Fosfolipasa C beta/metabolismo , Receptores Acoplados a Proteínas G/metabolismo , Células HEK293 , Humanos , Ligandos , Unión Proteica , Transducción de Señal
11.
Methods Mol Biol ; 2274: 385-389, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34050487

RESUMEN

Confocal microscopy is a simple, super-resolution technique, which does not produce a marked increase in resolution compared to other advanced techniques, such as super-resolution nanoscopy. Here, we present a simple protocol to acquire "slightly, but easily resolved" images by pinhole closure (<1 airy unit) in a conventional confocal scanning microscope equipped with an avalanche photodiode, a detector with high sensitivity. We use murine neuroblastoma Neuro2a cells to demonstrate the image resolution obtained via this protocol without the use of any special software to enhance image quality.


Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Microscopía Confocal/instrumentación , Microscopía Fluorescente/instrumentación , Imagen Molecular/métodos , Neuroblastoma/patología , Programas Informáticos , Animales , Ratones , Microscopía Confocal/métodos , Microscopía Fluorescente/métodos , Células Tumorales Cultivadas
12.
Methods Mol Biol ; 2255: 87-95, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34033097

RESUMEN

Neutrophils are innate immune cells that play important roles in many physiological and pathological processes, including immune defense and cancer metastasis. In addition to the release of proinflammatory cytokines, chemokines, and cytoplasmic granules containing digestive proteins, in recent years, neutrophils have been observed to release neutrophil extracellular traps (NETs) that consist of extracellular DNA associated with antimicrobial proteins, such as histones and myeloperoxidase. These NETs are increasingly being recognized as an important mechanism of neutrophil host defense and function. This chapter will summarize the current literature on the known processes of NET formation and describe in detail an immunofluorescence approach that can be employed to visualize and quantify NETs in vitro.


Asunto(s)
ADN/análisis , Trampas Extracelulares/metabolismo , Histonas/análisis , Procesamiento de Imagen Asistido por Computador/métodos , Microscopía Fluorescente/métodos , Peroxidasa/metabolismo , Humanos
13.
Methods Mol Biol ; 2255: 97-117, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34033098

RESUMEN

Neutrophils release web like-structures known as neutrophil extracellular traps (NETs) that ensnare and kill microorganisms. These networks are constituted of a DNA scaffold with associated antimicrobial proteins, which are released to the extracellular space as an effective mechanism to fight against invading microorganisms. In parallel with this beneficial role to avoid microbial dissemination and wall off infections, accumulating evidence supports that under certain circumstances, NETs can exert deleterious effects in inflammatory, autoimmune, and thrombotic pathologies. Research on NET properties and their role in pathophysiological processes is a rapidly evolving and expanding field. Here, we describe a combination of methods to achieve a successful in vitro NET visualization, semiquantification, and isolation.


Asunto(s)
Separación Celular/métodos , ADN/análisis , Trampas Extracelulares/metabolismo , Procesamiento de Imagen Asistido por Computador/métodos , Microscopía Fluorescente/métodos , Elastasa Pancreática/análisis , Peroxidasa/metabolismo , Humanos , Técnicas In Vitro
14.
Methods Mol Biol ; 2255: 197-212, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34033105

RESUMEN

The rapid, efficient detection of cell death is critical for characterizing the underlying biology of in vitro disease models and, in particular, immunotherapy products used for preclinical therapeutic research. Traditional endpoint assays are laborious to perform for mass screening of therapeutic candidates and may fail to fully capture the kinetics of events surrounding the initiation, duration, and mechanisms of cell death-important events that may affect translational relevance and impact therapeutic decision-making during development. Here, we describe simple, efficient methods to measure apoptosis and immune cell killing in both adherent and nonadherent cell populations using the Incucyte® Live-Cell Analysis system and associated nonperturbing reagents, cells, and protocols. Assays are performed in the user's own incubator with minimal disturbance and may be readily incorporated into existing workflows. Users may multiplex to maximize data collection from each sample. The integrated, user-friendly software does not require advanced technical training, enabling rapid analysis. Taken together, this method provides essential kinetic insight for greater understanding of cell death and the dynamic interactions between immune cells and their targets.


Asunto(s)
Apoptosis , Caspasas/metabolismo , Adhesión Celular , Procesamiento de Imagen Asistido por Computador/métodos , Imagen Molecular/métodos , Neoplasias/patología , Linfocitos T/patología , Humanos , Cinética , Neoplasias/metabolismo , Linfocitos T/inmunología , Células Tumorales Cultivadas
15.
J Vis Exp ; (170)2021 04 18.
Artículo en Inglés | MEDLINE | ID: mdl-33938878

RESUMEN

Precise measurements of between- and within-strain heterogeneity in microbial growth rates are essential for understanding genetic and environmental inputs into stress tolerance, pathogenicity, and other key components of fitness. This manuscript describes a microscope-based assay that tracks approximately 105 Saccharomyces cerevisiae microcolonies per experiment. After automated time-lapse imaging of yeast immobilized in a multiwell plate, microcolony growth rates are easily analyzed with custom image-analysis software. For each microcolony, expression and localization of fluorescent proteins and survival of acute stress can also be monitored. This assay allows precise estimation of strains' average growth rates, as well as comprehensive measurement of heterogeneity in growth, gene expression, and stress tolerance within clonal populations.


Asunto(s)
Expresión Génica , Procesamiento de Imagen Asistido por Computador/métodos , Microscopía , Saccharomyces cerevisiae/metabolismo , Programas Informáticos
16.
J Vis Exp ; (170)2021 04 13.
Artículo en Inglés | MEDLINE | ID: mdl-33938876

RESUMEN

The acute mouse pancreatic tissue slice is a unique in situ preparation with preserved intercellular communication and tissue architecture that entails significantly fewer preparation-induced changes than isolated islets, acini, ducts, or dispersed cells described in typical in vitro studies. By combining the acute pancreatic tissue slice with live-cell calcium imaging in confocal laser scanning microscopy (CLSM), calcium signals can be studied in a large number of endocrine and exocrine cells simultaneously, with a single-cell or even subcellular resolution. The sensitivity permits the detection of changes and enables the study of intercellular waves and functional connectivity as well as the study of the dependence of physiological responses of cells on their localization within the islet and paracrine relationship with other cells. Finally, from the perspective of animal welfare, recording signals from a large number of cells at a time lowers the number of animals required in experiments, contributing to the 3R-replacement, reduction, and refinement-principle.


Asunto(s)
Señalización del Calcio , Calcio/metabolismo , Procesamiento de Imagen Asistido por Computador/métodos , Microscopía Confocal/métodos , Páncreas/metabolismo , Animales , Ratones , Páncreas/citología
17.
Sci Rep ; 11(1): 11112, 2021 05 27.
Artículo en Inglés | MEDLINE | ID: mdl-34045510

RESUMEN

We report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of the disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with the average Area Under the Curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in a single patient and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in the early stages of the disease. This use of AI to assess the severity and possibly predicting the future stages of the disease early on, will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.


Asunto(s)
COVID-19/diagnóstico , Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Algoritmos , Área Bajo la Curva , Inteligencia Artificial , COVID-19/diagnóstico por imagen , Simulación por Computador , Progresión de la Enfermedad , Femenino , Humanos , Masculino , Persona de Mediana Edad , Redes Neurales de la Computación , Radiografía , Índice de Severidad de la Enfermedad
18.
Int J Mol Sci ; 22(7)2021 Mar 30.
Artículo en Inglés | MEDLINE | ID: mdl-33808317

RESUMEN

As critical components of DNA, enhancers can efficiently and specifically manipulate the spatial and temporal regulation of gene transcription. Malfunction or dysregulation of enhancers is implicated in a slew of human pathology. Therefore, identifying enhancers and their strength may provide insights into the molecular mechanisms of gene transcription and facilitate the discovery of candidate drug targets. In this paper, a new enhancer and its strength predictor, iEnhancer-GAN, is proposed based on a deep learning framework in combination with the word embedding and sequence generative adversarial net (Seq-GAN). Considering the relatively small training dataset, the Seq-GAN is designed to generate artificial sequences. Given that each functional element in DNA sequences is analogous to a "word" in linguistics, the word segmentation methods are proposed to divide DNA sequences into "words", and the skip-gram model is employed to transform the "words" into digital vectors. In view of the powerful ability to extract high-level abstraction features, a convolutional neural network (CNN) architecture is constructed to perform the identification tasks, and the word vectors of DNA sequences are vertically concatenated to form the embedding matrices as the input of the CNN. Experimental results demonstrate the effectiveness of the Seq-GAN to expand the training dataset, the possibility of applying word segmentation methods to extract "words" from DNA sequences, the feasibility of implementing the skip-gram model to encode DNA sequences, and the powerful prediction ability of the CNN. Compared with other state-of-the-art methods on the training dataset and independent test dataset, the proposed method achieves a significantly improved overall performance. It is anticipated that the proposed method has a certain promotion effect on enhancer related fields.


Asunto(s)
ADN/genética , Elementos de Facilitación Genéticos/genética , Procesamiento de Imagen Asistido por Computador/métodos , Algoritmos , Aprendizaje Profundo , Modelos Teóricos , Redes Neurales de la Computación , Secuencias Reguladoras de Ácidos Nucleicos/genética , Análisis de Secuencia de ADN/métodos
19.
AJR Am J Roentgenol ; 216(6): 1668-1677, 2021 06.
Artículo en Inglés | MEDLINE | ID: mdl-33852337

RESUMEN

OBJECTIVE. Previous advances over filtered back projection (FBP) have incorporated model-based iterative reconstruction. The purpose of this study was to characterize the latest advance in image reconstruction, that is, deep learning. The focus was on applying characterization results of a deep learning approach to decisions about clinical CT protocols. MATERIALS AND METHODS. A proprietary deep learning image reconstruction (DLIR) method was characterized against an existing advanced adaptive statistical iterative reconstruction method (ASIR-V) and FBP from the same vendor. The metrics used were contrast-to-noise ratio, spatial resolution as a function of contrast level, noise texture (i.e., noise power spectra [NPS]), noise scaling as a function of slice thickness, and CT number consistency. The American College of Radiology accreditation phantom and a uniform water phantom were used at a range of doses and slice thicknesses for both axial and helical acquisition modes. RESULTS. ASIR-V and DLIR were associated with improved contrast-to-noise ratio over FBP for all doses and slice thicknesses. No dose or contrast dependencies of spatial resolution were observed for ASIR-V or DLIR. NPS results showed DLIR maintained an FBP-like noise texture whereas ASIR-V shifted the NPS to lower frequencies. Noise changed with dose and slice thickness in the same manner for ASIR-V and FBP. DLIR slice thickness noise scaling differed from FBP, exhibiting less noise penalty with decreasing slice thickness. No clinically significant changes were observed in CT numbers for any measurement condition. CONCLUSION. In a phantom model, DLIR does not suffer from the concerns over reduction in spatial resolution and introduction of poor noise texture associated with previous methods.


Asunto(s)
Aprendizaje Profundo , Procesamiento de Imagen Asistido por Computador/métodos , Fantasmas de Imagen , Tomografía Computarizada por Rayos X/métodos , Humanos , Guías de Práctica Clínica como Asunto
20.
Int J Mol Sci ; 22(6)2021 Mar 11.
Artículo en Inglés | MEDLINE | ID: mdl-33799794

RESUMEN

The role of the blood-brain barrier (BBB) breakdown has been recognized as being important in Alzheimer's disease pathogenesis. We aimed to evaluate whether regional BBB integrity differed according to sex and whether differences in BBB integrity changed as a consequence of aging or cognitive decline, using dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI). In total, 75 participants with normal cognition (NC) or mild cognitive impairment (MCI) underwent cognitive assessments and MRI examination including DCE-MRI. Regional Ktrans was calculated in cortical regions and the Patlak permeability model was used to calculate BBB permeability (Ktrans, min-1). Females had a lower median Ktrans in the cingulate and occipital cortices. In the "older old" group, sex differences in Ktrans were only observed in the occipital cortex. In the MCI group, sex differences in Ktrans were only observed in the occipital cortex. Age was the only predictor of cognitive assessment scores in the male MCI group; however, educational years and Ktrans in the occipital cortex could predict cognitive scores in the female MCI group. Our study revealed that females may have better BBB integrity in cingulate and occipital cortices. We also found that sex-related differences in BBB integrity are attenuated with aging or cognitive decline.


Asunto(s)
Barrera Hematoencefálica/metabolismo , Encéfalo/metabolismo , Cognición/fisiología , Disfunción Cognitiva/metabolismo , Anciano , Envejecimiento/metabolismo , Envejecimiento/fisiología , Barrera Hematoencefálica/diagnóstico por imagen , Encéfalo/diagnóstico por imagen , Encéfalo/fisiopatología , Disfunción Cognitiva/diagnóstico por imagen , Disfunción Cognitiva/fisiopatología , Femenino , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Masculino , Persona de Mediana Edad , Permeabilidad , Factores Sexuales
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA
...