{"id":11309,"date":"2020-11-24T13:27:30","date_gmt":"2020-11-24T19:27:30","guid":{"rendered":"https:\/\/saluddigital.com\/?p=11309"},"modified":"2025-10-21T14:08:58","modified_gmt":"2025-10-21T20:08:58","slug":"publican-estudio-sobre-la-utilizacion-de-aprendizaje-profundo-a-inteligencia-artificial-para-detectar-aneurismas-cerebrales","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/comunidades-conectadas\/publican-estudio-sobre-la-utilizacion-de-aprendizaje-profundo-a-inteligencia-artificial-para-detectar-aneurismas-cerebrales\/","title":{"rendered":"Scientists publish study on the use of deep learning to Artificial Intelligence to detect brain aneurysms"},"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

The study was published in the scientific journal Radiology, and aims to create a high-sensitivity deep learning algorithm that assists in the detection of brain aneurysms in CT images.<\/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

Detection of brain aneurysms could be improved by deep learning, which seeks to perform more accurate interpretations. The research entitled \u201cDeep Learning for Detecting Cerebral Aneurysms with CT Angiography\u201d, was intended to develop an algorithm based on this type of high-sensitivity Artificial Intelligence to improve the detection of brain aneurysms in CT angiography images.<\/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

To conduct the study, researchers consulted two hospital databases to interpret CT angiography images, the recovered images were taken from January 2015 to June 2019. In addition to an independent TC database that was conducted between July and December 2019. They eventually managed to evaluate a total of 1068 patients aged 57, of whom 660 were women.<\/p>

For the development of deep learning, of the 1068 CT angiography, 534 (688 aneurysms), were considered for algorithm training and the remaining 543 (649 aneurysms) were used for validation. The developed algorithm was capable of detecting brain aneurysms in images with a sensitivity of 97.5% i.e. 633 out of 649. And he detected eight new aneurysms that had not been found in the previous reports.<\/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

\u201cWith the help of the algorithm, the overall performance of radiologists in detection of cerebral aneurysms was increased by 0.01 (from 0.60 to 0.61),\u201d the authors mention in the study. \u201cThe developed algorithm revealed eight new aneurysms that were overlooked in the initial reports. With aid of the proposed algorithm, the overall performance in terms of area under the weighted alternative free-response receiver operating characteristic (wAFROC) curve of radiologists improved by 0.01 (P < .05). This improvement was found to be dependent on the level of experience,\u201d the authors concluded on the study.p<\/em>\u00a0<0,05).\u00a0Se encontr\u00f3 que esta mejora depend\u00eda del nivel de experiencia\u201d, concluyeron los autores sobre el estudio.<\/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

RADIOLOGY <\/strong>https:\/\/pubs.rsna.org\/doi\/10.1148\/radiol.2020192154?_ga=2.56306082.882950819.1604435940-24992834.1522856813&<\/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":"

El estudio fue publicado en la revista cient\u00edfica Radiology, y tiene como prop\u00f3sito la creaci\u00f3n de un algoritmo basado en aprendizaje profundo de alta sensibilidad que ayude en la detecci\u00f3n de aneurismas cerebrales en im\u00e1genes obtenidas por tomograf\u00eda computarizada. La detecci\u00f3n de aneurismas cerebrales podr\u00eda mejorar gracias al aprendizaje profundo, que busca realizar interpretaciones m\u00e1s precisas. La investigaci\u00f3n titulada “Aprendizaje profundo para detectar aneurismas cerebrales con angiograf\u00eda por TC”, tuvo como prop\u00f3sito desarrollar un algoritmo basado en este tipo de Inteligencia Artificial de alta sensibilidad para mejorar la detecci\u00f3n de aneurismas cerebrales en im\u00e1genes de angiograf\u00eda por Tomograf\u00eda Computarizada (TC). Para realizar el estudio los investigadores consultaron dos bases de datos de hospitales para interpretar las im\u00e1genes de angiograf\u00eda por TC, las im\u00e1genes recuperadas fueron tomadas de enero de 2015 a junio de 2019. Adem\u00e1s de una base de datos de TC independientes que fueron realizados entre julio y diciembre de 2019. Finalmente lograron evaluar a un total de 1068 pacientes con edad media de 57 a\u00f1os, de las cuales 660 fueron mujeres. Para el desarrollo del aprendizaje profundo, de las 1068 angiograf\u00edas por TC, 534 (688 aneurismas), fueron considerados para el entrenamiento del algoritmo y las 543 (649 aneurismas) restantes fueron utilizados para la validaci\u00f3n del mismo. El algoritmo desarrollado fue capaz de detectas aneurismas cerebrales en im\u00e1genes con una sensibilidad de 97,5% es decir 633 de 649. Y detect\u00f3 ocho nuevos aneurismas que no hab\u00edan sido encontrados en los informes previos. \u201cCon la ayuda del algoritmo, el rendimiento general de los radi\u00f3logos en la detecci\u00f3n de aneurismas cerebrales se increment\u00f3 en 0,01 (de 0,60 a 0,61)\u201d, mencionan los autores en el estudio. \u201cCon la ayuda del algoritmo propuesto, el rendimiento general en t\u00e9rminos de \u00e1rea bajo la curva de caracter\u00edstica operativa del receptor de respuesta libre alternativa ponderada (wAFROC) de los radi\u00f3logos mejor\u00f3 en 0,01 (p <0,05). Se encontr\u00f3 que esta mejora depend\u00eda del nivel de experiencia\u201d, concluyeron los autores sobre el estudio. BIBLIOGRAF\u00cdA RADIOLOGY https:\/\/pubs.rsna.org\/doi\/10.1148\/radiol.2020192154?_ga=2.56306082.882950819.1604435940-24992834.1522856813&<\/p>","protected":false},"author":1,"featured_media":11310,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3399,156,154,1418],"tags":[145],"class_list":["post-11309","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-analitica","category-big-data","category-comunidades-conectadas","category-resena-de-publicaciones-cientificas","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/11309","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=11309"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/11309\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/11310"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=11309"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=11309"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=11309"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}