Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Dig Liver Dis ; 53(2): 216-223, 2021 02.
Artigo em Inglês | MEDLINE | ID: mdl-33272862

RESUMO

BACKGROUND: Observation of the entire stomach during esophagogastroduodenoscopy (EGD) is important; however, there is a lack of effective evaluation tools. AIMS: To develop an artificial intelligence (AI)-assisted EGD system able to automatically monitor blind spots in real-time. METHODS: An AI-based system, called the Intelligent Detection Endoscopic Assistant (IDEA), was developed using a deep convolutional neural network (DCNN) and long short-term memory (LSTM). The performance of IDEA for recognition of gastric sites in images and videos was evaluated. Primary outcomes included diagnostic accuracy, sensitivity, and specificity. RESULTS: A total of 170,297 images and 5779 endoscopic videos were collected to develop the system. As the test group, 3100 EGD images were acquired to evaluate the performance of DCNN in recognition of gastric sites in images. The sensitivity, specificity, and accuracy of DCNN were determined as 97.18%,99.91%, and 99.83%, respectively. To assess the performance of IDEA in recognition of gastric sites in EGD videos, 129 videos were used as the test group. The sensitivity, specificity, and accuracy of IDEA were 96.29%,93.32%, and 95.30%, respectively. CONCLUSIONS: IDEA achieved high accuracy for recognition of gastric sites in real-time. The system can be applied as a powerful assistant tool for monitoring blind spots during EGD.


Assuntos
Inteligência Artificial , Endoscopia do Sistema Digestório , Redes Neurais de Computação , Neoplasias Gástricas/diagnóstico , Competência Clínica , Diagnóstico Diferencial , Humanos , Monitorização Fisiológica , Variações Dependentes do Observador , Sensibilidade e Especificidade
2.
World J Surg ; 39(12): 2955-64, 2015 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-26335901

RESUMO

BACKGROUND: Endoscopic submucosal dissection (ESD) is rapidly becoming a favored method for removing early esophageal cancer, but the residual defects can be complicated with strictures that require repeated endoscopic balloon dilatation. Measures for preventing the post-ESD strictures have been sought. We conducted a systematic review of recent studies to evaluate these methods. METHODS: We searched MEDLINE, Cochrane Central Register of Controlled Trials, Embase, and Google Scholar until November 30, 2014. Included studies were prospective and retrospective one- and two-arm studies. All studies had to include at least on preventive method for post-ESD stricture. Thirteen studies were included in the review. RESULTS: Among the studies that used corticosteroids to prevent post-ESD stricture, we found that (1) injection of triamcinolone acetonide into the esophageal lesion resulted in a substantial reduction in the rate of stricture, and (2) the use of oral prednisolone was associated with a significantly reduced rate of dilatation sessions and stricture. Studies of other preventative measures included more recently developed scaffold-based and cell-based tissue-engineering approaches which seem very promising but require additional rigorously controlled studies to test their effectiveness. CONCLUSIONS: Until a safer and more effective method is developed, our review supports the use of corticosteroids, either through injection or oral route, together with endoscopic dilatation in prevention of post-ESD strictures.


Assuntos
Dissecação/efeitos adversos , Neoplasias Esofágicas/cirurgia , Estenose Esofágica/prevenção & controle , Mucosa/cirurgia , Administração Oral , Anti-Inflamatórios/administração & dosagem , Dilatação , Dissecação/métodos , Neoplasias Esofágicas/patologia , Estenose Esofágica/etiologia , Esofagoscopia , Humanos , Injeções Intralesionais , Prednisolona/administração & dosagem , Engenharia Tecidual , Triancinolona Acetonida/administração & dosagem
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...