Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 23
Filtrar
1.
Artigo em Inglês | MEDLINE | ID: mdl-33522229

RESUMO

Activating upconversion nanoparticle-based photoresponsive nanovectors (UCPNVs) by upconversion visible light at low-power near-infrared (NIR) excitation can realize deeper biotissue stimulation with a minimized overheating effect and photodamage. Here, we demonstrate a facile strategy to construct new surface-decorated UCPNVs based on Passerini three-component reaction (P-3CR) in highly convenient and effective manners. Such UCPNVs materials have a tailored deprotecting wavelength that overlaps upconversion blue light. By using 3-perylenecarboxaldehyde, Tm3+/Yb3+ ion-doped UCNP-containing isocyanides, and antitumor agent chlorambucil as the three components, the resulting monodisperse UCPNV exhibits an efficient release of caged chlorambucil under a very low 976 nm power. This approach expands the synthetic toolbox to enable quick development of UCPNVs for UCNP-assisted low-power NIR photochemistry.

3.
IEEE Trans Med Imaging ; PP2020 Nov 27.
Artigo em Inglês | MEDLINE | ID: mdl-33245693

RESUMO

Clusters of viral pneumonia occurrences over a short period may be a harbinger of an outbreak or pandemic. Rapid and accurate detection of viral pneumonia using chest X-rays can be of significant value for large-scale screening and epidemic prevention, particularly when other more sophisticated imaging modalities are not readily accessible. However, the emergence of novel mutated viruses causes a substantial dataset shift, which can greatly limit the performance of classification-based approaches. In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into a one-class classification-based anomaly detection problem. We therefore propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module. If the anomaly score produced by the anomaly detection module is large enough, or the confidence score estimated by the confidence prediction module is small enough, the input will be accepted as an anomaly case (i.e., viral pneumonia). The major advantage of our approach over binary classification is that we avoid modeling individual viral pneumonia classes explicitly and treat all known viral pneumonia cases as anomalies to improve the one-class model. The proposed model outperforms binary classification models on the clinical X-VIRAL dataset that contains 5,977 viral pneumonia (no COVID-19) cases, 37,393 non-viral pneumonia or healthy cases. Moreover, when directly testing on the X-COVID dataset that contains 106 COVID-19 cases and 107 normal controls without any fine-tuning, our model achieves an AUC of 83.61% and sensitivity of 71.70%, which is comparable to the performance of radiologists reported in the literature.

4.
J Agric Food Chem ; 68(44): 12326-12335, 2020 Nov 04.
Artigo em Inglês | MEDLINE | ID: mdl-33107299

RESUMO

Toona sinensis, popularly known as Chinese toon or Chinese mahogany, is a perennial deciduous arbor belonging to the genus Toona in the Meliaceae family, which is widely distributed and cultivated in eastern and southeastern Asia. Its fresh young leaves and buds have been consumed as a very popular nutritious vegetable in China and confirmed to display a wide variety of biological activities. To investigate the chemical constituents and their potential health benefits from the fresh young leaves and buds of T. sinensis, a phytochemical study on its fresh young leaves and buds was therefore undertaken. In our current investigation, 16 limonoids (1-16), including four new limonoids, toonasinenoids A-D (1-4), and a new naturally occurring limonoid, toonasinenoid E (5), were isolated and characterized from the fresh young leaves and buds of T. sinensis. The chemical structures and absolute configurations of limonoids 1-5 were elucidated by comprehensive spectroscopic data analyses. All known limonoids (6-16) were identified via comparing their experimental spectral data containing mass spectrometry data, 1H and 13C nuclear magnetic resonance data, and optical rotation values to the data reported in the literature. All known limonoids (6-16) were isolated from T. sinensis for the first time. Furthermore, the neuroprotective effects of all isolated limonoids 1-16 against 6-hydroxydopamine-induced cell death in human neuroblastoma SH-SY5Y cells were assessed in vitro. Limonoids 1-16 exhibited notable neuroprotective activities, with EC50 values in the range from 0.27 ± 0.03 to 17.28 ± 0.16 µM. These results suggest that regular consumption of the fresh young leaves and buds of T. sinensis might prevent the occurrence and development of Parkinson's disease (PD). Moreover, the isolation and characterization of these limonoids that exhibit notable neuroprotective activities from the fresh young leaves and buds of T. sinensis could be very significant for researching and developing new neuroprotective drugs used for the prevention and treatment of PD.

5.
IEEE Trans Med Imaging ; PP2020 Oct 30.
Artigo em Inglês | MEDLINE | ID: mdl-33125324

RESUMO

Automated and accurate 3D medical image segmentation plays an essential role in assisting medical professionals to evaluate disease progresses and make fast therapeutic schedules. Although deep convolutional neural networks (DCNNs) have widely applied to this task, the accuracy of these models still need to be further improved mainly due to their limited ability to 3D context perception. In this paper, we propose the 3D context residual network (ConResNet) for the accurate segmentation of 3D medical images. This model consists of an encoder, a segmentation decoder, and a context residual decoder. We design the context residual module and use it to bridge both decoders at each scale. Each context residual module contains both context residual mapping and context attention mapping, the formal aims to explicitly learn the inter-slice context information and the latter uses such context as a kind of attention to boost the segmentation accuracy. We evaluated this model on the MICCAI 2018 Brain Tumor Segmentation (BraTS) dataset and NIH Pancreas Segmentation (Pancreas-CT) dataset. Our results not only demonstrate the effectiveness of the proposed 3D context residual learning scheme but also indicate that the proposed ConResNet is more accurate than six top-ranking methods in brain tumor segmentation and seven top-ranking methods in pancreas segmentation.

6.
IEEE Trans Med Imaging ; PP2020 Sep 21.
Artigo em Inglês | MEDLINE | ID: mdl-32956049

RESUMO

Medical image segmentation is an essential task in computer-aided diagnosis. Despite their prevalence and success, deep convolutional neural networks (DCNNs) still need to be improved to produce accurate and robust enough segmentation results for clinical use. In this paper, we propose a novel and generic framework called Segmentation-Emendation-reSegmentation-Verification (SESV) to improve the accuracy of existing DCNNs in medical image segmentation, instead of designing a more accurate segmentation model. Our idea is to predict the segmentation errors produced by an existing model and then correct them. Since predicting segmentation errors is challenging, we design two ways to tolerate the mistakes in the error prediction. First, rather than using a predicted segmentation error map to correct the segmentation mask directly, we only treat the error map as the prior that indicates the locations where segmentation errors are prone to occur, and then concatenate the error map with the image and segmentation mask as the input of a re-segmentation network. Second, we introduce a verification network to determine whether to accept or reject the refined mask produced by the re-segmentation network on a region-by-region basis. The experimental results on the CRAG, ISIC, and IDRiD datasets suggest that using our SESV framework can improve the accuracy of DeepLabv3+ substantially and achieve advanced performance in the segmentation of gland cells, skin lesions, and retinal microaneurysms. Consistent conclusions can also be drawn when using PSPNet, U-Net, and FPN as the segmentation network, respectively. Therefore, our SESV framework is capable of improving the accuracy of different DCNNs on different medical image segmentation tasks.

7.
Bioorg Chem ; 102: 104101, 2020 09.
Artigo em Inglês | MEDLINE | ID: mdl-32721778

RESUMO

Three new carbazole alkaloids, zanthoaustrones A-C (1-3), as well as nine known compounds 4-12, were isolated and characterized from the roots of Zanthoxylum austrosinense Huang (Rutaceae). Their chemical structures were elucidated on the basis of extensive and comprehensive spectroscopic methods, while the known alkaloids were identified by the comparison of their observed spectroscopic data including NMR data, MS data and optical rotation values with the data described in the literature. Furthermore, the antiproliferative activities as well as the anti-inflammatory effects of all isolated alkaloids in vitro were evaluated. All obtained alkaloids 1-12 displayed notable antiproliferative activities against diverse human cancer cell lines exhibiting IC50 values in range of 0.85 ± 0.06 to 29.56 ± 0.17 µM, which is equivalent to the positive control (cisplatin) showing IC50 values ranging from 1.58 ± 0.09 to 28.69 ± 0.21 µM. Moreover, compounds 1-12 exhibited pronounced inhibitory activities on nitric oxide (NO) production with IC50 values displaying IC50 values in range of 0.89 ± 0.05 to 9.62 ± 0.15 µM, which is comparable to the positive control (hydrocortisone) holding an IC50 value of 4.06 ± 0.11 µM. These findings indicate that the separation and characterization of these alkaloids displaying significant antiproliferative activities together with anti-inflammatory effects from the roots of Z. austrosinense could be meaningful to the research and development of new anti-cancer drugs as well as anti-inflammatory agents.

8.
Stem Cell Res ; 44: 101759, 2020 04.
Artigo em Inglês | MEDLINE | ID: mdl-32224418

RESUMO

Although human adipose derived stem cells (hADSCs) hold great promises for regenerative medicine, their key biological properties remain poorly understood. In particular, proliferation defects resulted from deep quiescence (dormancy) and senescence represent a major hurdle in hADSC production and clinical application. We have developed a model system for mechanistic dissection of hADSC quiescence and senescence. p57Kip2, a major CDK inhibitor, was highly expressed in quiescent and senescent hADSCs but its level quickly declined upon stem cell activation. p57Kip2 overexpression induced quiescence in spite of proliferative signals and its knockdown promoted cell cycle reentry even with induction of quiescence presumably through modulating the CDK2-CyclinE1 complex. Given its key role in quiescence and senescence, p57Kip2 may be exploited for innovative strategies to amplify hADSCs of high quality for clinics.

9.
Bioorg Chem ; 97: 103699, 2020 04.
Artigo em Inglês | MEDLINE | ID: mdl-32146173

RESUMO

The phytochemical study on the stems of Clausena lenis resulted in the isolation of three new prenylated coumarins, clauselenins A-C (1-3), together with nine known prenylated coumarins (4-12). The chemical structures of new prenylated coumarins (1-3) were elucidated by means of comprehensive spectral analyses and the known compounds (4-12) were determined by means of comparing their experimental spectral data with those described data in the literatures. All isolated prenylated coumarins were assessed for their anti-inflammatory effects together with anti-HIV activities in vitro. Prenylated coumarins 1-12 displayed remarkable inhibitory effects against nitric oxide (NO) production induced by lipopolysaccharide in mouse macrophage RAW 264.7 cells in vitro with the IC50 values which are comparable to hydrocortisone. Meanwhile, prenylated coumarins 1-12 exhibited considerable anti-HIV-1 reverse transcriptase (RT) activities possessing EC50 values in the range of 0.17-9.08 µM. These findings indicate that the isolation and identification of these prenylated coumarins with pronounced anti-inflammatory effects as well as anti-HIV activities separated from the stems of C. lenis could be of great significance to the development of new anti-inflammatory and anti-HIV agents and their potential applications in the pharmaceutical industry.

10.
J Agric Food Chem ; 68(7): 2024-2030, 2020 Feb 19.
Artigo em Inglês | MEDLINE | ID: mdl-32037814

RESUMO

Artocarpus heterophyllus (jack tree) is an evergreen fruit tree belonging to the genus Artocarpus (Moraceae), which is widely distributed in subtropical and tropical regions of Asia. Its fruits (jackfruit), well-known as the world's largest tree-borne fruit, are being consumed in our daily diets as a very popular tropical fruit throughout the world and have been confirmed to hold various health benefits. In this study, five new prenylated chromones, artocarheterones A-E (1-5), as well as seven known prenylated chromones (6-12) were purified and isolated from the ripe fruits of A. heterophyllus (jackfruit). Their chemical structures were determined through comprehensive spectroscopic methods. This is the first report on prenylated chromones isolated from A. heterophyllus. The anti-HIV-1 effects of all isolated chromones were assessed in vitro. As a result, prenylated chromones (1-12) showed remarkable anti-HIV-1 effects with EC50 values ranging from 0.09 to 9.72 µM. These research results indicate that the isolation and characterization of these prenylated chromones with remarkable anti-HIV-1 activities from the ripe fruits of A. heterophyllus could be significant to the discovery and development of new anti-HIV-1 drugs.


Assuntos
Fármacos Anti-HIV/química , Fármacos Anti-HIV/farmacologia , Artocarpus/química , Cromonas/química , Cromonas/farmacologia , Extratos Vegetais/química , Extratos Vegetais/farmacologia , Frutas/química , HIV-1/efeitos dos fármacos , HIV-1/fisiologia , Estrutura Molecular , Prenilação
11.
IEEE Trans Med Imaging ; 39(7): 2482-2493, 2020 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-32070946

RESUMO

Automated skin lesion segmentation and classification are two most essential and related tasks in the computer-aided diagnosis of skin cancer. Despite their prevalence, deep learning models are usually designed for only one task, ignoring the potential benefits in jointly performing both tasks. In this paper, we propose the mutual bootstrapping deep convolutional neural networks (MB-DCNN) model for simultaneous skin lesion segmentation and classification. This model consists of a coarse segmentation network (coarse-SN), a mask-guided classification network (mask-CN), and an enhanced segmentation network (enhanced-SN). On one hand, the coarse-SN generates coarse lesion masks that provide a prior bootstrapping for mask-CN to help it locate and classify skin lesions accurately. On the other hand, the lesion localization maps produced by mask-CN are then fed into enhanced-SN, aiming to transfer the localization information learned by mask-CN to enhanced-SN for accurate lesion segmentation. In this way, both segmentation and classification networks mutually transfer knowledge between each other and facilitate each other in a bootstrapping way. Meanwhile, we also design a novel rank loss and jointly use it with the Dice loss in segmentation networks to address the issues caused by class imbalance and hard-easy pixel imbalance. We evaluate the proposed MB-DCNN model on the ISIC-2017 and PH2 datasets, and achieve a Jaccard index of 80.4% and 89.4% in skin lesion segmentation and an average AUC of 93.8% and 97.7% in skin lesion classification, which are superior to the performance of representative state-of-the-art skin lesion segmentation and classification methods. Our results suggest that it is possible to boost the performance of skin lesion segmentation and classification simultaneously via training a unified model to perform both tasks in a mutual bootstrapping way.

12.
Oral Oncol ; 101: 104506, 2020 02.
Artigo em Inglês | MEDLINE | ID: mdl-31863964

RESUMO

OBJECTIVES: In this study, we presented a novel hybrid perfusion mode in an attempt to provide a new strategy to improve the survival of an extended large flap and discuss its possible mechanisms. MATERIALS AND METHODS: A 14 × 10 cm flap was designed on the rabbit abdomen. Ninety-six rabbits were randomly divided into three groups based on the flap perfusion mode: control group I (CON 1, physiological perfusion mode with bilateral deep inferior epigastric vascular pedicles intact), control group II (CON 2, physiological perfusion mode with single deep inferior epigastric vascular pedicle intact), hybrid nourished group (physiological perfusion as in CON 2 combined with arterialized venous nonphysiological perfusion mode, referred to as a hybrid perfusion mode). Flap survival, status of vascular perfusion, microvasculature, histopathology, expression of CD34, eNOs, VEGF and metabolic status of the flaps by LC-MS were assessed in each group. RESULTS: The results of "hybrid nourished" flaps were similar to the traditional flaps in terms of flap survival, level of vascular perfusion and microvasculature except the status of metabolites. CONCLUSIONS: The feasibility of this novel hybrid perfusion mode will greatly extend the indications of flap transfer and efficiently improve the survival reliability of large flaps. In a sense, this mode will be an ideological emancipation for the field of flap surgery.


Assuntos
Retalhos de Tecido Biológico/irrigação sanguínea , Sobrevivência de Enxerto , Microvasos , Modelos Biológicos , Perfusão , Animais , Biomarcadores , Biópsia , Biologia Computacional/métodos , Diagnóstico por Imagem , Imuno-Histoquímica , Masculino , Metaboloma , Coelhos , Reação em Cadeia da Polimerase Via Transcriptase Reversa
13.
Med Image Anal ; 57: 237-248, 2019 10.
Artigo em Inglês | MEDLINE | ID: mdl-31352126

RESUMO

Classification of benign-malignant lung nodules on chest CT is the most critical step in the early detection of lung cancer and prolongation of patient survival. Despite their success in image classification, deep convolutional neural networks (DCNNs) always require a large number of labeled training data, which are not available for most medical image analysis applications due to the work required in image acquisition and particularly image annotation. In this paper, we propose a semi-supervised adversarial classification (SSAC) model that can be trained by using both labeled and unlabeled data for benign-malignant lung nodule classification. This model consists of an adversarial autoencoder-based unsupervised reconstruction network R, a supervised classification network C, and learnable transition layers that enable the adaption of the image representation ability learned by R to C. The SSAC model has been extended to the multi-view knowledge-based collaborative learning, aiming to employ three SSACs to characterize each nodule's overall appearance, heterogeneity in shape and texture, respectively, and to perform such characterization on nine planar views. The MK-SSAC model has been evaluated on the benchmark LIDC-IDRI dataset and achieves an accuracy of 92.53% and an AUC of 95.81%, which are superior to the performance of other lung nodule classification and semi-supervised learning approaches.


Assuntos
Neoplasias Pulmonares/diagnóstico por imagem , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Nódulo Pulmonar Solitário/diagnóstico por imagem , Aprendizado de Máquina Supervisionado , Tomografia Computadorizada por Raios X/métodos , Algoritmos , Conjuntos de Dados como Assunto , Humanos , Neoplasias Pulmonares/patologia , Lesões Pré-Cancerosas/diagnóstico por imagem , Radiografia Torácica , Nódulo Pulmonar Solitário/patologia
14.
Biomed Res Int ; 2019: 8159567, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31139652

RESUMO

This study aimed to investigate the prevalence and antimicrobial resistance of Salmonella spp. isolated from large-scale breeder farms in Shandong Province, China. A total of 63 Salmonella isolates (63/409, 15.4%) were identified from 409 samples collected from five large-scale breeder farms in Shandong Province. These Salmonella isolates were assayed for serotype, antimicrobial susceptibility, prevalence of class 1 integrons, quinolone resistance genes, and ß-lactamase genes and subtyped by multilocus sequence typing (MLST). Among these isolates, S. Enteritidis (100%) was the predominant serovar, and high antimicrobial resistance rates to nalidixic acid (100.0%), streptomycin (100.0%), ampicillin (98.4%), and erythromycin (93.7%) were observed. All of the isolates carried blaTEM. MLST results showed that only one sequence type (ST11) was identified. Our findings indicated that Salmonella was generally prevalent not only on broiler farms but also on breeder farms.


Assuntos
Cruzamento , Fazendas , Salmonella/isolamento & purificação , Animais , Antibacterianos/farmacologia , Galinhas/microbiologia , Farmacorresistência Bacteriana Múltipla/efeitos dos fármacos , Farmacorresistência Bacteriana Múltipla/genética , Integrons/genética , Testes de Sensibilidade Microbiana , Tipagem de Sequências Multilocus , Fenótipo , Salmonella/efeitos dos fármacos , Salmonella/genética , Sorotipagem
15.
Med Image Anal ; 54: 10-19, 2019 05.
Artigo em Inglês | MEDLINE | ID: mdl-30818161

RESUMO

The classification of medical images is an essential task in computer-aided diagnosis, medical image retrieval and mining. Although deep learning has shown proven advantages over traditional methods that rely on the handcrafted features, it remains challenging due to the significant intra-class variation and inter-class similarity caused by the diversity of imaging modalities and clinical pathologies. In this paper, we propose a synergic deep learning (SDL) model to address this issue by using multiple deep convolutional neural networks (DCNNs) simultaneously and enabling them to mutually learn from each other. Each pair of DCNNs has their learned image representation concatenated as the input of a synergic network, which has a fully connected structure that predicts whether the pair of input images belong to the same class. Thus, if one DCNN makes a correct classification, a mistake made by the other DCNN leads to a synergic error that serves as an extra force to update the model. This model can be trained end-to-end under the supervision of classification errors from DCNNs and synergic errors from each pair of DCNNs. Our experimental results on the ImageCLEF-2015, ImageCLEF-2016, ISIC-2016, and ISIC-2017 datasets indicate that the proposed SDL model achieves the state-of-the-art performance in these medical image classification tasks.


Assuntos
Aprendizado Profundo , Diagnóstico por Computador , Diagnóstico por Imagem , Processamento de Imagem Assistida por Computador , Mineração de Dados , Humanos , Armazenamento e Recuperação da Informação , Redes Neurais de Computação , Sistemas de Informação em Radiologia
16.
IEEE Trans Med Imaging ; 38(9): 2092-2103, 2019 09.
Artigo em Inglês | MEDLINE | ID: mdl-30668469

RESUMO

Automated skin lesion classification in dermoscopy images is an essential way to improve the diagnostic performance and reduce melanoma deaths. Although deep convolutional neural networks (DCNNs) have made dramatic breakthroughs in many image classification tasks, accurate classification of skin lesions remains challenging due to the insufficiency of training data, inter-class similarity, intra-class variation, and the lack of the ability to focus on semantically meaningful lesion parts. To address these issues, we propose an attention residual learning convolutional neural network (ARL-CNN) model for skin lesion classification in dermoscopy images, which is composed of multiple ARL blocks, a global average pooling layer, and a classification layer. Each ARL block jointly uses the residual learning and a novel attention learning mechanisms to improve its ability for discriminative representation. Instead of using extra learnable layers, the proposed attention learning mechanism aims to exploit the intrinsic self-attention ability of DCNNs, i.e., using the feature maps learned by a high layer to generate the attention map for a low layer. We evaluated our ARL-CNN model on the ISIC-skin 2017 dataset. Our results indicate that the proposed ARL-CNN model can adaptively focus on the discriminative parts of skin lesions, and thus achieve the state-of-the-art performance in skin lesion classification.


Assuntos
Interpretação de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Dermatopatias/diagnóstico por imagem , Pele/diagnóstico por imagem , Bases de Dados Factuais , Dermoscopia/métodos , Humanos , Processamento de Sinais Assistido por Computador , Dermatopatias/classificação
17.
IEEE Trans Med Imaging ; 38(4): 991-1004, 2019 04.
Artigo em Inglês | MEDLINE | ID: mdl-30334786

RESUMO

The accurate identification of malignant lung nodules on chest CT is critical for the early detection of lung cancer, which also offers patients the best chance of cure. Deep learning methods have recently been successfully introduced to computer vision problems, although substantial challenges remain in the detection of malignant nodules due to the lack of large training data sets. In this paper, we propose a multi-view knowledge-based collaborative (MV-KBC) deep model to separate malignant from benign nodules using limited chest CT data. Our model learns 3-D lung nodule characteristics by decomposing a 3-D nodule into nine fixed views. For each view, we construct a knowledge-based collaborative (KBC) submodel, where three types of image patches are designed to fine-tune three pre-trained ResNet-50 networks that characterize the nodules' overall appearance, voxel, and shape heterogeneity, respectively. We jointly use the nine KBC submodels to classify lung nodules with an adaptive weighting scheme learned during the error back propagation, which enables the MV-KBC model to be trained in an end-to-end manner. The penalty loss function is used for better reduction of the false negative rate with a minimal effect on the overall performance of the MV-KBC model. We tested our method on the benchmark LIDC-IDRI data set and compared it to the five state-of-the-art classification approaches. Our results show that the MV-KBC model achieved an accuracy of 91.60% for lung nodule classification with an AUC of 95.70%. These results are markedly superior to the state-of-the-art approaches.


Assuntos
Aprendizado Profundo , Neoplasias Pulmonares/diagnóstico por imagem , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Nódulo Pulmonar Solitário/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Algoritmos , Humanos , Pulmão/diagnóstico por imagem
18.
IEEE J Biomed Health Inform ; 22(5): 1521-1530, 2018 09.
Artigo em Inglês | MEDLINE | ID: mdl-29990115

RESUMO

The classification of medical images and illustrations from the biomedical literature is important for automated literature review, retrieval, and mining. Although deep learning is effective for large-scale image classification, it may not be the optimal choice for this task as there is only a small training dataset. We propose a combined deep and handcrafted visual feature (CDHVF) based algorithm that uses features learned by three fine-tuned and pretrained deep convolutional neural networks (DCNNs) and two handcrafted descriptors in a joint approach. We evaluated the CDHVF algorithm on the ImageCLEF 2016 Subfigure Classification dataset and it achieved an accuracy of 85.47%, which is higher than the best performance of other purely visual approaches listed in the challenge leaderboard. Our results indicate that handcrafted features complement the image representation learned by DCNNs on small training datasets and improve accuracy in certain medical image classification problems.


Assuntos
Aprendizado Profundo , Diagnóstico por Imagem/classificação , Processamento de Imagem Assistida por Computador/métodos , Algoritmos , Humanos
19.
Sensors (Basel) ; 18(4)2018 Mar 31.
Artigo em Inglês | MEDLINE | ID: mdl-29614753

RESUMO

In this paper, a new type of electric field sensor is proposed for the health and safety protection of inspection staff in high-voltage environments. Compared with the traditional power frequency electric field measurement instruments, the portable instrument has some special performance requirements and, thus, a new kind of double spherical shell sensor is presented. First, the mathematical relationships between the induced voltage of the sensor, the output voltage of the measurement circuit, and the original electric field in free space are deduced theoretically. These equations show the principle of the proposed sensor to measure the electric field and the effect factors of the measurement. Next, the characteristics of the sensor are analyzed through simulation. The simulation results are in good agreement with the theoretical analysis. The influencing rules of the size and material of the sensor on the measurement results are summarized. Then, the proposed sensor and the matching measurement system are used in a physical experiment. After calibration, the error of the measurement system is discussed. Lastly, the directional characteristic of the proposed sensor is experimentally tested.

20.
Int J Biol Macromol ; 113: 991-995, 2018 Jul 01.
Artigo em Inglês | MEDLINE | ID: mdl-29524490

RESUMO

This study aims to investigate the neuroprotective effects of Coptis chinensis Franch polysaccharide (CCP) on Aß1-42 transgenic CL4176 Caenorhabditis elegans, as well as its mechanism of action. The results in life span experiment showed that CCP could significantly increase the lifespan of C. elegans and the effect is in the descending order of 100mg/L>500mg/L>200mg/L. The behavioral experiments also demonstrated that CCP at the concentration of 100mg/L could delay the paralysis rate of C. elegans, which was significantly different from the control group. In terms of Aß toxicity in C. elegans, morphological observation using Thioflavin S staining method indicated that the deposition of Aß protein in the head area of the untreated C. elegans was much more than those in the CCP (100mg/L)-treated CL4176. In line with this finding, fluorogenic quantitative real-time PCR confirmed that the transcriptional levels of HSP16.2 (Y46H3A.D) and HSP16.41 (Y46H3A.E) in C. elegans was 21 times and 79 times higher than those in untreated control. Thus, these data demonstrate that CCP could reduce Aß-induced toxicity by delaying the aging, decreasing the rate of paralysis, inhibiting the deposition of Aß, and increasing the expression levels of HSP genes in transgenic C. elegans.


Assuntos
Doença de Alzheimer/induzido quimicamente , Doença de Alzheimer/tratamento farmacológico , Peptídeos beta-Amiloides/toxicidade , Caenorhabditis elegans , Coptis/química , Fármacos Neuroprotetores/farmacologia , Polissacarídeos/farmacologia , Doença de Alzheimer/genética , Animais , Animais Geneticamente Modificados , Modelos Animais de Doenças , Regulação da Expressão Gênica/efeitos dos fármacos , Fármacos Neuroprotetores/uso terapêutico , Polissacarídeos/uso terapêutico
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA