{"id":23774,"date":"2022-01-31T08:57:35","date_gmt":"2022-01-31T14:57:35","guid":{"rendered":"https:\/\/saluddigital.com\/?p=23774"},"modified":"2025-10-21T10:24:47","modified_gmt":"2025-10-21T16:24:47","slug":"investigadores-crean-algoritmo-para-analizar-lesiones-potenciales-en-mamografias","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/investigadores-crean-algoritmo-para-analizar-lesiones-potenciales-en-mamografias\/","title":{"rendered":"Researchers create algorithm to analyze potential lesions in mammograms"},"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

Researchers at Duke University created an Artificial Intelligence (AI) platform that would be capable of detecting and analyzing lesions in mammography images. Its objective is to be a valuable support in the decision-making of professionals.<\/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

Researchers at Duke University in Durham, North Carolina, suggest that this platform can determine if patients require biopsies if the lesions detected are potentially cancerous. The AI algorithm was trained on 1,136 images taken from 484 patients in the University Health System.<\/p>

The team from the aforementioned university trained the platform's algorithm to detect and evaluate lesions as if it were a real radiologist. Unlike other algorithms that are freely trained in their procedures.<\/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

\u201cIf a computer is going to help make important medical decisions, doctors need to trust that the AI is basing its conclusions on something that makes sense. We need algorithms that not only work, but are self-explanatory and show examples of what they are basing their conclusions on. That way, whether a doctor agrees with the result or not, the AI is helping make better decisions," said Joseph Lo, a professor of radiology at Duke.<\/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

In the press release from Duke University, they explained that the algorithms that read medical images represent a large industry, since the Food and Drug Administration (FDA) has approved more than 100 for clinical use. However, there is a lot of room for improvement especially to use larger validation data sets, especially when it comes to medical images, or to include demographic information.<\/p>

\u201cOur idea was instead to build a system to say that this specific part of a possible cancerous lesion looks a lot like this one I've seen before,\u201d said Alina Barnett, a PhD in computer science at Duke and first author of the study.<\/p>

In this sense, the AI system, proposed by the university, does not seek to replace the specialist's experience, but to be a support so that professionals have more information for decision making.<\/p>

The Duke University study was published in the journal Nature Machine Intelligence<\/em> in December 2021: https:\/\/www.nature.com\/articles\/s42256-021-00423-x<\/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\t BIBLIOGRAPHY<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t

DUKE UNIVERSITY<\/strong><\/p>

https:\/\/pratt.duke.edu\/about\/news\/ai-breast-cancer<\/a><\/p>

HEALTH IT ANALYTICS <\/strong><\/p>

https:\/\/healthitanalytics.com\/news\/ai-detectscancerouslesions-in-mammography-scans<\/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":"

Investigadores de la Duke University, crearon una plataforma de Inteligencia Artificial (IA), que ser\u00eda capaz de detectar y analizar lesiones en im\u00e1genes de mamograf\u00edas. Su objetivo es ser un apoyo de valor en la toma de decisiones de los profesionales. Los investigadores de la Duke University en Durham, Carolina del Norte, plantean que esta plataforma puede determinar si las pacientes requieren biopsias en caso de que las lesiones detectadas sean potencialmente cancer\u00edgenas. El algoritmo de IA fue entrenado con 1,136 im\u00e1genes tomadas de 484 pacientes en el Sistema de Salud de la Universidad. El equipo de la universidad mencionada, entren\u00f3 el algoritmo de la plataforma para detectar y evaluar lesiones como si se tratara de un verdadero radi\u00f3logo. A diferencia de otros algoritmos que son entrenados de manera libre en sus procedimientos. \u201cSi una computadora va a ayudar a tomar decisiones m\u00e9dicas importantes, los m\u00e9dicos deben confiar en que la IA est\u00e1 basando sus conclusiones en algo que tiene sentido. Necesitamos algoritmos que no solo funcionen, sino que se expliquen por s\u00ed mismos y muestren ejemplos de en qu\u00e9 est\u00e1n basando sus conclusiones. De esa manera, ya sea que un m\u00e9dico est\u00e9 de acuerdo con el resultado o no, la IA est\u00e1 ayudando a tomar mejores decisiones\u201d, explic\u00f3 Joseph Lo, profesor de radiolog\u00eda en Duke. En el comunicado de prensa de la Duke University, explicaron que los algoritmos que leen im\u00e1genes m\u00e9dicas representan una gran industria, ya que la Administraci\u00f3n de Alimentos y Medicamentos (FDA), ha aprobado m\u00e1s de 100 para su uso cl\u00ednico. No obstante, existe un gran margen de mejora especialmente para utilizar conjuntos de datos de validaci\u00f3n m\u00e1s extensos, sobre todo cuando se trata de im\u00e1genes m\u00e9dicas, o bien incluir informaci\u00f3n demogr\u00e1fica. \u201cNuestra idea era, en cambio, construir un sistema para decir que esta parte espec\u00edfica de una posible lesi\u00f3n cancerosa se parece mucho a esta otra que he visto antes\u201d, dijo Alina Barnett, doctorante en inform\u00e1tica en Duke y primera autora del estudio. En este sentido el sistema de IA, propuesto por la universidad, no busca reemplazar la experiencia del especialista, sino ser un apoyo para que los profesionales tengan mayor informaci\u00f3n para la toma de decisiones. El estudio de la Duke University fue publicado en la revista Nature Machine Intelligence en diciembre de 2021: https:\/\/www.nature.com\/articles\/s42256-021-00423-x BIBLIOGRAF\u00cdA DUKE UNIVERSITY https:\/\/pratt.duke.edu\/about\/news\/ai-breast-cancer HEALTH IT ANALYTICS https:\/\/healthitanalytics.com\/news\/ai-detectscancerouslesions-in-mammography-scans<\/p>","protected":false},"author":1,"featured_media":23776,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3399,156,3393,160,1418],"tags":[145],"class_list":["post-23774","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-analitica","category-big-data","category-inteligencia-artificial-y-ciencia","category-noticias","category-resena-de-publicaciones-cientificas","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/23774","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=23774"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/23774\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/23776"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=23774"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=23774"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=23774"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}