{"id":11362,"date":"2020-11-30T09:41:19","date_gmt":"2020-11-30T15:41:19","guid":{"rendered":"https:\/\/saluddigital.com\/?p=11362"},"modified":"2025-10-21T14:07:59","modified_gmt":"2025-10-21T20:07:59","slug":"modelo-de-aprendizaje-profundo-utilizado-para-detectar-neumonia-en-pacientes-con-covid-19-a-traves-de-imagenes-computarizadas","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/plataformas-digitales\/modelo-de-aprendizaje-profundo-utilizado-para-detectar-neumonia-en-pacientes-con-covid-19-a-traves-de-imagenes-computarizadas\/","title":{"rendered":"Deep learning model used to detect pneumonia in patients with COVID-19 through computer imaging"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Through CT scans this method of diagnosis through an algorithm based on deep learning, researchers plan to develop a more effective system than traditional techniques.<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Through computed tomography (CT) scans, most of the diagnoses of pneumonia caused by COVID-19 are obtained. Faced with this, the objective of the scientific report Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography published in Nature<\/em>, was to develop an algorithm based on deep learning that would detect COVID-19-related pneumonia in high-resolution CT. For the development of the model, 46,096 images of 106 patients were collected from Renmin Hospital at Wuhan University, including 51 patients with COVID-19 pneumonia.<\/p>

To test the model, external testing will be performed with other hospitals in China, so scientists determined that the model has 95.24% per patient accuracy and 98.85% image accuracy. Thanks to this deep learning model, radiologists' reading time may be reduced to 65%, speeding up diagnoses and improving the efficiency of clinical practice.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Before applying the Artificial Intelligence tool to support the expert radiologist the average reading to determine viral pneumonia through CT images was 11.2 seconds per patient. Subsequently after using AI as support, the expert reread the CT images of the 27 patients and achieved an average of approximately 40.64 seconds per case.<\/p>

The algorithm is available for free via the following link: https:\/\/github.com\/endo-angel\/ct-angel<\/a>. Through this web platform, specialists will have access to CT imaging as a form of support for a more accurate pneumonia diagnosis.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t

\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

\u201cArtificial intelligence holds great potential to relieve the pressure of frontline radiologists, accelerates the diagnosis, isolation and treatment of COVID19 patients, and therefore contribute to the control of the epidemic,\u201d the authors explain.<\/p>

\u00a0<\/p>

To read the full report go to the following link: https:\/\/www.nature.com\/articles\/s41598-020-76282-0<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tBIBLIOGRAPHY<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t

NATURE<\/strong><\/p>

https:\/\/www.nature.com\/articles\/s41598-020-76282-0<\/a><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

A trav\u00e9s de tomograf\u00edas computarizadas este m\u00e9todo de diagn\u00f3stico a trav\u00e9s de un algoritmo basado en aprendizaje profundo, investigadores planean desarrollar un sistema m\u00e1s eficaz que las t\u00e9cnicas tradicionales. A trav\u00e9s de tomograf\u00edas computarizadas (TC), se obtienen la mayor parte de los diagn\u00f3sticos de neumon\u00eda provocados por COVID-19. Ante ello, el objetivo del informe cient\u00edfico “Modelo basado en aprendizaje profundo para detectar neumon\u00eda por coronavirus nuevo de 2019 en tomograf\u00eda computarizada de alta resoluci\u00f3n” publicado en Nature, fue desarrollar un algoritmo basado en aprendizaje profundo que permitiera detectar la neumon\u00eda relacionada a COVID-19 en TC de alta resoluci\u00f3n. Para el desarrollo del modelo fueron recopiladas 46,096 im\u00e1genes de 106 pacientes del Hospital Renmin de la Universidad de Wuhan, incluidos 51 pacientes de neumon\u00eda por COVID-19. Para probar el modelo se realizar pruebas externas con otros hospitales de China, por lo que los cient\u00edficos determinaron que el modelo tiene una precisi\u00f3n por paciente de 95,24% y una precisi\u00f3n por imagen de 98,85%. Gracias a este modelo de aprendizaje profundo es posible que el tiempo de lectura de los radi\u00f3logos se reduzca hasta 65%, agilizando los diagn\u00f3sticos y mejorando la eficiencia de la pr\u00e1ctica cl\u00ednica. Antes de aplicar la herramienta de Inteligencia Artificial para apoyar al radi\u00f3logo experto el promedio de lectura para determinar neumon\u00eda viral a trav\u00e9s de las im\u00e1genes de TC era de 11,2 segundos por paciente. Posteriormente tras utilizar la IA como apoyo, el experto volvi\u00f3 a leer las im\u00e1genes de TC de los 27 pacientes y logr\u00f3 un promedio aproximado de 40,64 segundos por caso. El algoritmo est\u00e1 disponible de forma gratuita a trav\u00e9s del siguiente enlace: https:\/\/github.com\/endo-angel\/ct-angel. A trav\u00e9s de esta plataforma web, los especialistas tendr\u00e1n acceso a im\u00e1genes por TC, como forma de apoyo para realizar un diagn\u00f3stico de neumon\u00eda m\u00e1s certero. \u201cLa inteligencia artificial tiene un gran potencial para aliviar la presi\u00f3n de los radi\u00f3logos de primera l\u00ednea, acelera el diagn\u00f3stico, el aislamiento y el tratamiento de los pacientes con COVID19 y, por lo tanto, contribuye al control de la epidemia\u201d, explican los autores. Para leer el informe completo ingresa al enlace siguiente: https:\/\/www.nature.com\/articles\/s41598-020-76282-0 BIBLIOGRAF\u00cdA NATURE https:\/\/www.nature.com\/articles\/s41598-020-76282-0<\/p>","protected":false},"author":1,"featured_media":11363,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3399,156,153,1418],"tags":[145],"class_list":["post-11362","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-analitica","category-big-data","category-plataformas-digitales","category-resena-de-publicaciones-cientificas","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/11362","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/comments?post=11362"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/11362\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/11363"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=11362"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=11362"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=11362"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}