Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 13 de 13
Filtrar
1.
Curr Med Imaging ; 2024 Jan 19.
Artigo em Inglês | MEDLINE | ID: mdl-38258593

RESUMO

BACKGROUND: Patients with cancer can develop bone metastasis when a solid tumor invades the bone, which is the third most commonly affected site by metastatic cancer, after the lung and liver. The early detection of bone metastases is crucial for making appropriate treatment decisions and increasing survival rates. Deep learning, a mainstream branch of machine learning, has rapidly become an effective approach to analyzing medical images. OBJECTIVE: To automatically diagnose bone metastasis with bone scintigraphy, in this work, we proposed to cast the bone metastasis diagnosis problem into automated image classification by developing a deep learning-based automated classification model. METHODS: A self-defined convolutional neural network consisting of a feature extraction sub-network and feature classification sub-network was proposed to automatically detect lung cancer bone metastasis, with a feature extraction sub-network extracting hierarchal features from SPECT bone scintigrams and feature classification sub-network classifying high-level features into two categories (i.e., images with metastasis and without metastasis). RESULTS: Using clinical data of SPECT bone scintigrams, the proposed model was evaluated to examine its detection accuracy. The best performance was achieved if the two images (i.e., anterior and posterior scans) acquired from each patient were fused using pixel-wise addition operation on the bladder-excluded images, obtaining the best scores of 0.8038, 0.8051, 0.8039, 0.8039, 0.8036, and 0.8489 for accuracy, precision, recall, specificity, F-1 score, and AUC value, respectively. CONCLUSION: The proposed two-class classification network can predict whether an image contains lung cancer bone metastasis with the best performance as compared to existing classical deep learning models. The high accumulation of 99mTc MDP in the urinary bladder has a negative impact on automated diagnosis of bone metastasis. It is recommended to remove the urinary bladder before automated analysis.

2.
Front Mol Biosci ; 9: 956720, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36387284

RESUMO

To develop a deep image segmentation model that automatically identifies and delineates lesions of skeletal metastasis in bone scan images, facilitating clinical diagnosis of lung cancer-caused bone metastasis by nuclear medicine physicians. A semi-supervised segmentation model is proposed, comprising the feature extraction subtask and pixel classification subtask. During the feature extraction stage, cascaded layers which include the dilated residual convolution, inception connection, and feature aggregation learn the hierarchal representations of low-resolution bone scan images. During the pixel classification stage, each pixel is first classified into categories in a semi-supervised manner, and the boundary of pixels belonging to an individual lesion is then delineated using a closed curve. Experimental evaluation conducted on 2,280 augmented samples (112 original images) demonstrates that the proposed model performs well for automated segmentation of metastasis lesions, with a score of 0.692 for DSC if the model is trained using 37% of the labeled samples. The self-defined semi-supervised segmentation model can be utilized as an automated clinical tool to detect and delineate metastasis lesions in bone scan images, using only a few manually labeled image samples. Nuclear medicine physicians need only attend to those segmented lesions while ignoring the background when they diagnose bone metastasis using low-resolution images. More images of patients from multiple centers are typically needed to further improve the scalability and performance of the model via mitigating the impacts of variability in size, shape, and intensity of bone metastasis lesions.

3.
Front Microbiol ; 13: 977292, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36312947

RESUMO

Plant polyphenol supplementation may improve fish health in aquaculture systems. To assess the potential benefits and function mechanism of plant polyphenols in aquaculture, fish were fed either basal feed (CON) or the basal feed supplemented with 500 mg/kg of curcumin (CUR), oligomeric proanthocyanidins (OPC), chlorogenic acid (CGA), or resveratrol (RES). After an 8-week feeding experiment, blood samples were used to analyze the concentrations of biochemical indices. Gut samples were collected to evaluate microbiota, short chain fatty acid (SCFA) levels, and gene expression. The results indicated that polyphenol administration reduced serum glucose and insulin. Lysozyme activity was enhanced by OPC and CGA, and superoxide dismutase activity was increased by CUR, OPC, and CGA. The gut microbial structure of the RES group was segregated from that of the CON, and the genus Bacteroides was identified as a potential biomarker in the CUR, CGA, and RES groups. Total gut SCFA increased in the CUR, CGA, and RES groups. A strong correlation was observed between Bacteroides and SCFA. In conclusion, dietary polyphenols have distinct anti-inflammatory, anti-oxidant, and anti-hyperglycemic activities that may be closely associated with their microbiota-modulation effects.

4.
Phys Med Biol ; 67(22)2022 Nov 09.
Artigo em Inglês | MEDLINE | ID: mdl-36137545

RESUMO

Objective.To facilitate manual diagnosis of lung cancer-caused metastasis, in this work, we propose a deep learning-based method to automatically identify and locate the hotspots in a bone scan image which denote the lesions metastasized from lung cancer.Approach.An end-to-end metastasis lesion detection model is proposed by following the classical object detection framework single shot multibox object detector (SSD). The proposed model casts lesion detection problem into automatically learning the hierarchal representations of lesion features, locating the spatial position of lesion areas, and boxing the detected lesions.Main results.Experimental evaluation conducted on clinical data of retrospective bone scans shows the comparable performance with a mean score of 0.7911 for average precision. A comparative analysis between our network and others including SSD shows the feasibility of the proposed detection network on automatically detecting multiple lesions of metastasis lesions caused by lung cancer.Significance.The proposed method has the potential to be used as an auxiliary tool for improving the accuracy and efficiency of metastasis diagnosis routinely conducted by nuclear medicine physicians.


Assuntos
Neoplasias Pulmonares , Tomografia Computadorizada por Raios X , Humanos , Estudos Retrospectivos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia
5.
Insights Imaging ; 13(1): 24, 2022 Feb 09.
Artigo em Inglês | MEDLINE | ID: mdl-35138479

RESUMO

BACKGROUND: Whole-body bone scan is the widely used tool for surveying bone metastases caused by various primary solid tumors including lung cancer. Scintigraphic images are characterized by low specificity, bringing a significant challenge to manual analysis of images by nuclear medicine physicians. Convolutional neural network can be used to develop automated classification of images by automatically extracting hierarchal features and classifying high-level features into classes. RESULTS: Using convolutional neural network, a multi-class classification model has been developed to detect skeletal metastasis caused by lung cancer using clinical whole-body scintigraphic images. The proposed method consisted of image aggregation, hierarchal feature extraction, and high-level feature classification. Experimental evaluations on a set of clinical scintigraphic images have shown that the proposed multi-class classification network is workable for automated detection of lung cancer-caused metastasis, with achieving average scores of 0.7782, 0.7799, 0.7823, 0.7764, and 0.8364 for accuracy, precision, recall, F-1 score, and AUC value, respectively. CONCLUSIONS: The proposed multi-class classification model can not only predict whether an image contains lung cancer-caused metastasis, but also differentiate between subclasses of lung cancer (i.e., adenocarcinoma and non-adenocarcinoma). On the context of two-class (i.e., the metastatic and non-metastatic) classification, the proposed model obtained a higher score of 0.8310 for accuracy metric.

6.
Phys Med Biol ; 67(1)2022 01 17.
Artigo em Inglês | MEDLINE | ID: mdl-34933282

RESUMO

A bone scan is widely used for surveying bone metastases caused by various solid tumors. Scintigraphic images are characterized by inferior spatial resolution, bringing a significant challenge to manual analysis of images by nuclear medicine physicians. We present in this work a new framework for automatically classifying scintigraphic images collected from patients clinically diagnosed with lung cancer. The framework consists of data preparation and image classification. In the data preparation stage, data augmentation is used to enlarge the dataset, followed by image fusion and thoracic region extraction. In the image classification stage, we use a self-defined convolutional neural network consisting of feature extraction, feature aggregation, and feature classification sub-networks. The developed multi-class classification network can not only predict whether a bone scan image contains bone metastasis but also tell which subcategory of lung cancer that a bone metastasis metastasized from is present in the image. Experimental evaluations on a set of clinical bone scan images have shown that the proposed multi-class classification network is workable for automated classification of metastatic images, with achieving average scores of 0.7392, 0.7592, 0.7242, and 0.7292 for accuracy, precision, recall, and F-1 score, respectively.


Assuntos
Neoplasias Pulmonares , Tomografia Computadorizada por Raios X , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Redes Neurais de Computação , Cintilografia
7.
Med Phys ; 48(10): 5782-5793, 2021 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-34455613

RESUMO

PURPOSE: A self-defined convolutional neural network is developed to automatically classify whole-body scintigraphic images of concern (i.e., the normal, metastasis, arthritis, and thyroid carcinoma), automatically detecting diseases with whole-body bone scintigraphy. METHODS: A set of parameter transformation operations are first used to augment the original dataset of whole-body bone scintigraphic images. A hybrid attention mechanism including the spatial and channel attention module is then introduced to develop a deep classification network, Dscint, which consists of eight weight layers, one hybrid attention module, two normalization modules, two fully connected layers, and one softmax layer. RESULTS: Experimental evaluations conducted on a set of whole-body scintigraphic images show that the proposed deep classification network, Dscint, performs well for automated detection of diseases by classifying the images of concerns, achieving the accuracy, precision, recall, specificity, and F-1 score of 0.9801, 0.9795, 0.9791, 0.9933, and 0.9792, respectively, on the test data in the augmented dataset. A comparative analysis of Dscint and several classical deep classification networks (i.e., AlexNet, ResNet, VGGNet, DenseNet, and Inception-v4) reveals that our self-defined network, Dscint, performs best on classifying whole-body scintigraphic images on the same dataset. CONCLUSIONS: The self-defined deep classification network, Dscint, can be utilized to automatically determine whether a whole-body scintigraphic image is either normal or contains diseases of concern. Specifically, better performance of Dscint is obtained on images with lesions that are present in relatively fixed locations like thyroid carcinoma than those with lesions occurring in nonfixed locations of bone tissue.


Assuntos
Redes Neurais de Computação , Tomografia Computadorizada por Raios X , Cintilografia , Imagem Corporal Total
8.
BMC Med Imaging ; 21(1): 122, 2021 08 11.
Artigo em Inglês | MEDLINE | ID: mdl-34380441

RESUMO

BACKGROUND: Functional imaging especially the SPECT bone scintigraphy has been accepted as the effective clinical tool for diagnosis, treatment, evaluation, and prevention of various diseases including metastasis. However, SPECT imaging is brightly characterized by poor resolution, low signal-to-noise ratio, as well as the high sensitivity and low specificity because of the visually similar characteristics of lesions between diseases on imaging findings. METHODS: Focusing on the automated diagnosis of diseases with whole-body SPECT scintigraphic images, in this work, a self-defined convolutional neural network is developed to survey the presence or absence of diseases of concern. The data preprocessing mainly including data augmentation is first conducted to cope with the problem of limited samples of SPECT images by applying the geometric transformation operations and generative adversarial network techniques on the original SPECT imaging data. An end-to-end deep SPECT image classification network named dSPIC is developed to extract the optimal features from images and then to classify these images into classes, including metastasis, arthritis, and normal, where there may be multiple diseases existing in a single image. RESULTS: A group of real-world data of whole-body SPECT images is used to evaluate the self-defined network, obtaining a best (worst) value of 0.7747 (0.6910), 0.7883 (0.7407), 0.7863 (0.6956), 0.8820 (0.8273) and 0.7860 (0.7230) for accuracy, precision, sensitivity, specificity, and F-1 score, respectively, on the testing samples from the original and augmented datasets. CONCLUSIONS: The prominent classification performance in contrast to other related deep classifiers including the classical AlexNet network demonstrates that the built deep network dSPIC is workable and promising for the multi-disease, multi-lesion classification task of whole-body SPECT bone scintigraphy images.


Assuntos
Osso e Ossos/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Tomografia Computadorizada de Emissão de Fóton Único , Imagem Corporal Total , Conjuntos de Dados como Assunto , Humanos , Curva ROC
9.
Artigo em Inglês | MEDLINE | ID: mdl-34221095

RESUMO

OBJECTIVES: To evaluate the efficacy and/or safety of acupuncture therapy (AT) in quitting smoking. METHODS: Randomized controlled trials (RCTs) were searched in PubMed, Cochrane Library, Embase, Web of Science, and Chinese Biomedical Database (CBM). We used Cochrane Collaborative Quality Assessment to assess the risk of bias. Bayesian network meta-analysis was utilized to evaluate the efficacy and safety of different interventions. Data analyses were conducted using WinBUGS 1.4.3, Stata 14, and RevMan 5.3.5 software. RESULTS: A total of 2706 patients from 23 studies were included, involving 6 treatment arms. Network meta-analysis demonstrated that there was no significant difference in short-term abstinence rates or changes in Fagerstrom test for nicotine dependence (FTND) scores and daily smoking among these groups (AT, sham acupuncture therapy (SAT), auricular acupressure (AA), sham auricular acupressure (SAA), acupuncture plus auricular acupressure (APAA), and nicotine replacement therapy (NRT)). However, there was a significant difference between SAA and AA with risk ratio (RR) of 2.49 (95% CI 1.14, 5.97) in long-term abstinence rate. The probabilistic ranking results showed that APAA and AA were superior to other interventions in the comparison of abstinence rates. There was no obvious inconsistency between the direct comparison and indirect comparison, using the consistency test. CONCLUSION: AA was superior to SAA in smoke quitting, but there was no difference among other interventions in long-term truncation rates. There was no difference in short-term abstinence rates among these selected groups. We need large sample RCTs to clarify the advantages of interventions such as APAA and AA. In addition, reporting of adverse events that may occur during treatment also should be enhanced to complement evidence-based medicine. The trial is registered with PROSPERO CRD42020164712.

10.
Sci Rep ; 11(1): 4223, 2021 02 19.
Artigo em Inglês | MEDLINE | ID: mdl-33608560

RESUMO

SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the convolutional neural networks, has been widely applied to the classification of medical images. In order to reliably classify SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses, in this paper, we present several deep classifiers based on the deep networks. Specifically, original SPECT images are cropped to extract the thoracic region, followed by a geometric transformation that contributes to augment the original data. We then construct deep classifiers based on the widely used deep networks including VGG, ResNet and DenseNet by fine-tuning their parameters and structures or self-defining new network structures. Experiments on a set of real-world SPECT bone images show that the proposed classifiers perform well in identifying bone metastasis with SPECT imaging. It achieves 0.9807, 0.9900, 0.9830, 0.9890, 0.9802 and 0.9933 for accuracy, precision, recall, specificity, F-1 score and AUC, respectively, on the test samples from the augmented dataset without normalization.


Assuntos
Neoplasias Ósseas/diagnóstico , Neoplasias Ósseas/secundário , Aprendizado Profundo , Processamento de Imagem Assistida por Computador , Tomografia Computadorizada de Emissão de Fóton Único/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Algoritmos , Automação , Análise de Dados , Feminino , Humanos , Interpretação de Imagem Assistida por Computador , Processamento de Imagem Assistida por Computador/métodos , Masculino , Pessoa de Meia-Idade , Curva ROC , Reprodutibilidade dos Testes , Imagem Corporal Total
11.
PLoS One ; 15(12): e0243253, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33270746

RESUMO

SPECT imaging has been identified as an effective medical modality for diagnosis, treatment, evaluation and prevention of a range of serious diseases and medical conditions. Bone SPECT scan has the potential to provide more accurate assessment of disease stage and severity. Segmenting hotspot in bone SPECT images plays a crucial role to calculate metrics like tumor uptake and metabolic tumor burden. Deep learning techniques especially the convolutional neural networks have been widely exploited for reliable segmentation of hotspots or lesions, organs and tissues in the traditional structural medical images (i.e., CT and MRI) due to their ability of automatically learning the features from images in an optimal way. In order to segment hotspots in bone SPECT images for automatic assessment of metastasis, in this work, we develop several deep learning based segmentation models. Specifically, each original whole-body bone SPECT image is processed to extract the thorax area, followed by image mirror, translation and rotation operations, which augments the original dataset. We then build segmentation models based on two commonly-used famous deep networks including U-Net and Mask R-CNN by fine-tuning their structures. Experimental evaluation conducted on a group of real-world bone SEPCT images reveals that the built segmentation models are workable on identifying and segmenting hotspots of metastasis in bone SEPCT images, achieving a value of 0.9920, 0.7721, 0.6788 and 0.6103 for PA (accuracy), CPA (precision), Rec (recall) and IoU, respectively. Finally, we conclude that the deep learning technology have the huge potential to identify and segment hotspots in bone SPECT images.


Assuntos
Processamento de Imagem Assistida por Computador/métodos , Metástase Neoplásica/diagnóstico por imagem , Tomografia Computadorizada com Tomografia Computadorizada de Emissão de Fóton Único/métodos , Aprendizado Profundo , Feminino , Humanos , Imageamento por Ressonância Magnética/métodos , Masculino , Modelos Teóricos , Neoplasias/diagnóstico por imagem , Tórax/diagnóstico por imagem , Tomografia Computadorizada de Emissão de Fóton Único/métodos , Tomografia Computadorizada por Raios X/métodos
12.
Reprod Fertil Dev ; 29(4): 768-777, 2017 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-26748416

RESUMO

The aim of the present study was to clarify the roles of the mammalian target of rapamycin (mTOR) signalling pathway in follicular growth and development of thecal cells. Using in vivo-grown and in vitro-cultured ovaries, histological changes were evaluated using haematoxylin and eosin (HE) staining. Differentially expressed genes (DEGs) from 0 day post partum (d.p.p.) to 8 d.p.p. ovaries were screened by microarray and verified by quantitative real-time polymerase chain reaction. Forty-two DEGs related to cell proliferation and differentiation were screened out, with most DEGs being related to the to mTOR signalling pathway. Then, 3 d.p.p. ovaries were retrieved and used to verify the role of mTOR signalling in follicle and thecal cell development using its activators (Ras homologue enriched in brain (Rheb) and GTP) and inhibitor (rapamycin). The development of follicles and thecal cells was significantly impaired in ovaries cultured in vitro Day 3 to Day 8. In in vitro-cultured ovaries, Rheb and GTP (is 100ngmL-1 Rheb and 500ngmL-1 GTP for 48h) significantly increased follicle diameter, the percentage of primary and secondary follicles and the umber of thecal cells, and upregulated expression of mTOR, phosphorylated eukaryotic translation initiation factor 4E-binding protein 1 (4EBP1), eukaryotic initiation factor (eIF) 4F and cytochrome P450, family 17, subfamily A, polypeptide 1 (CYP17A1). Rapamycin (10nM rapamycin for 24h) had opposite effects to those of Rheb and GTP, and partly abrogated (significant) the effects of Rheb and GTP when added to the culture in combination with these drugs. Thus, mTOR signalling plays an important role in follicle growth and thecal cell development.


Assuntos
Fator de Iniciação 4F em Eucariotos/metabolismo , Folículo Ovariano/metabolismo , Transdução de Sinais/fisiologia , Serina-Treonina Quinases TOR/metabolismo , Células Tecais/metabolismo , Animais , Feminino , Perfilação da Expressão Gênica , Guanosina Trifosfato/farmacologia , Camundongos , Folículo Ovariano/efeitos dos fármacos , Folículo Ovariano/crescimento & desenvolvimento , Fosforilação/efeitos dos fármacos , Proteína Enriquecida em Homólogo de Ras do Encéfalo/farmacologia , Transdução de Sinais/efeitos dos fármacos , Sirolimo/farmacologia , Células Tecais/efeitos dos fármacos
13.
Theriogenology ; 82(3): 461-8, 2014 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-24948525

RESUMO

We constructed a model of apoptosis in mouse preimplantation embryos and investigated the effect of the flavonol icariin on embryonic development in vitro in embryos with reduced microRNA-21 (miR-21). The model was generated by microinjecting an miR-21 inhibitor into the cytoplasm of mouse pronuclear embryos, which were cultured in vitro using modified CZB (mCZB) basal medium (model group), or using mCZB medium with 0.6 µg/mL icariin as an experimental group (model-Ica). These were compared with embryos collected in vivo (vivo group) or not microinjected (control group). Developmental rates in vitro of two- and four-cell embryos and blastocysts were observed, and Hoechst 33342 and terminal deoxynucleotidyl transferase dUTP nick end labeling staining were used to count blastocyst cell numbers and apoptotic cell numbers and percentages. The transcriptional levels of miR-21, the apoptotic genes caspase 3 and phosphatase and tensin homolog deleted on chromosome ten (PTEN), and the antiapoptotic gene Bcl-2 were detected by quantitative polymerase chain reaction (qPCR). Western immunoblotting was used to detect the protein levels of caspase 3, PTEN, and Bcl-2. Compared with the model group, icariin treatment significantly improved blastocyst development in vitro (58.43 ± 7.53% vs. 37.85 ± 6.47%; P < 0.01), whereas it was not significantly different to the control group (60.34 ± 9.86%). Icariin treatment significantly increased the blastocyst cell numbers (47.02 ± 4.93 vs. 37.70 ± 5.80; P < 0.01), and reduced the rates of apoptosis (5.51 ± 2.35% vs. 10.11 ± 4.21%; P < 0.01), whereas the blastocyst cell numbers and apoptotic rates revealed no significant differences between the vivo (46.06 ± 6.50, 5.95 ± 2.56%) and control groups (45.77 ± 4.09, 6.18 ± 2.41%). Icariin treatment significantly improved miR-21 expression in all embryo stages, reduced the transcriptional levels of caspase 3 and PTEN, and increased the levels of Bcl-2. The protein expression levels of caspase 3 and PTEN were decreased in blastocysts and the level of Bcl-2 was increased (P < 0.01). These had no significant differences with the vivo and control groups, and the protein levels revealed no significant differences between two- and four-cell embryos. Thus, miR-21 was necessary for preimplantation embryonic development, and embryo quality was closely associated with the apoptosis-related protein expression levels regulated by miR-21. Icariin upregulated miR-21 expression and reduced apoptosis in embryos with reduced miR-21. It also improved embryonic developmental quality in vitro, indicating an important regulatory role for miR-21 in blastocyst development in vitro.


Assuntos
Apoptose/efeitos dos fármacos , Blastocisto/citologia , Flavonoides/farmacologia , MicroRNAs/genética , Animais , Blastocisto/efeitos dos fármacos , Caspase 3/genética , Caspase 3/metabolismo , Camundongos , MicroRNAs/antagonistas & inibidores , MicroRNAs/metabolismo , PTEN Fosfo-Hidrolase/genética , PTEN Fosfo-Hidrolase/metabolismo , Proteínas Proto-Oncogênicas c-bcl-2/genética , Proteínas Proto-Oncogênicas c-bcl-2/metabolismo
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA