{"id":30161,"date":"2022-08-01T08:21:07","date_gmt":"2022-08-01T13:21:07","guid":{"rendered":"https:\/\/saluddigital.com\/?p=30161"},"modified":"2025-10-20T11:30:21","modified_gmt":"2025-10-20T17:30:21","slug":"aprendizaje-profundo-permite-estimar-la-distribucion-de-grasa-corporal-en-imagenes-medicas-y-el-riesgo-cardiometabolico","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/aprendizaje-profundo-permite-estimar-la-distribucion-de-grasa-corporal-en-imagenes-medicas-y-el-riesgo-cardiometabolico\/","title":{"rendered":"Deep learning allows estimation of body fat distribution in medical images and cardiometabolic risk"},"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

A study showed that through medical images of the body silhouette it is possible to measure the distribution of body fat and the risk of suffering from cardiovascular diseases.<\/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

The distribution of fat in the body is clinically important however it is not always routinely assessed in practice. For example, the body mass index (BMI), is an indicator of the total fat load, which is used to define obesity in clinical practice and as an evaluator of the risk of cardiovascular diseases and type 2 diabetes. Although it is than a useful indicator, fat distribution may be more helpful in defining metabolic risk profiles.<\/p>

MIT researchers developed a deep learning model that uses magnetic resonance imaging (MRI) to identify fat deposits in the body to better identify metabolic risk. Previous studies had used images such as: computed tomography (CT) and dual energy X-ray absorptiometry (DEXA).<\/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\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
\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

The study involved 40,032 people from the UK Biobank's sub-study of body MRI. The mean age of the participants was 65 years, and 20,597 (51%) were women. For the study, they took into account the following variables in the recovered images: visceral adipose tissue (VAT), which is the fat that surrounds the internal organs; abdominal subcutaneous adipose tissue (ASAT), that is, the accumulation of fat just under the skin; and gluteofemoral adipose tissue (GFAT).<\/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

For the study, coronal and sagittal silhouettes of each patient were generated, performing segmentation of the body contour in axial MRI. In turn, they calculated a surface map of the resulting segmentation volume. Finally, three-dimensional surface images were projected into two-dimensional images and pixel intensity converted to binary values.<\/p>

Finally, the resulting silhouettes were used as inputs for training a convolutional neural network, capable of predicting VAT, ASAT and GFAT volumes using MRI measurements and a cross-validation procedure.<\/p>

"Cross-validated deep learning models trained on these images, using previously computed whole-body MRI estimated volumes as truth labels, demonstrate highly accurate estimation of VAT, ASAT, and GFAT volumes," the authors explained.<\/p>

Check the full study at the following link:<\/p>

https:\/\/www.nature.com\/articles\/s41746-022-00654-1<\/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

NATURE<\/strong><\/p>

https:\/\/www.nature.com\/articles\/s41746-022-00654-1<\/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":"

Estudio mostr\u00f3 que a trav\u00e9s de im\u00e1genes m\u00e9dicas de la silueta del cuerpo es posible medir la distribuci\u00f3n de la grasa corporal y el riesgo de padecer enfermedades cardiovasculares. La distribuci\u00f3n de la grasa en el cuerpo es cl\u00ednicamente importante sin embargo no siempre se eval\u00faa en la pr\u00e1ctica de manera rutinaria. Por ejemplo, el \u00edndice de masa corporal (IMC), es un indicador de la carga total de grasa, que se utiliza para definir la obesidad en la pr\u00e1ctica cl\u00ednica y como un evaluador del riesgo de enfermedades cardiovasculares y diabetes tipo 2. Aunque se trata de un indicador \u00fatil, la distribuci\u00f3n de grasa puede ser m\u00e1s \u00fatil para definir los perfiles de riesgo metab\u00f3lico. Investigadores del MIT desarrollaron un modelo de aprendizaje profundo que utiliza im\u00e1genes por resonancia magn\u00e9tica (IRM), para identificar dep\u00f3sitos de grasa en el cuerpo y as\u00ed identificar mejor el riesgo metab\u00f3lico. Estudios previos hab\u00edan utilizado im\u00e1genes como: tomograf\u00eda computarizada (TC) y absorciometr\u00eda de rayos X de energ\u00eda dual (DEXA). El estudio incluy\u00f3 la participaci\u00f3n de 40 mil 32 personas del sub estudio de IRM corporal del Biobanco del Reino Unido. La edad media de los participantes fue de 65 a\u00f1os, y 20,597 (51%) eran mujeres. Para el estudio tomaron en cuenta las siguientes variables en las im\u00e1genes recuperadas: tejido adiposo visceral (VAT, en ingl\u00e9s), que es la grasa que rodea los \u00f3rganos internos; tejido adiposo subcut\u00e1neo abdominal (ASAT, en ingl\u00e9s) es decir la acumulaci\u00f3n de grasa justo debajo de la piel; y el tejido adiposo gluteofemoral (GFAT, en ingl\u00e9s). Para el estudio se generaron siluetas coronales y sagitales de cada paciente, realizando segmentaci\u00f3n del contorno del cuerpo en IRM axial. A su vez calcularon un mapa de superficie del volumen de segmentaci\u00f3n resultante. Finalmente, las im\u00e1genes de superficies tridimensionales fueron proyectadas en im\u00e1genes bidimensionales y convirtieron la intensidad de pixeles en valores binarios. Finalmente, las siluetas resultantes se utilizaron como entradas para el entrenamiento de una red neuronal convolucional, capaz de predecir vol\u00famenes de VAT, ASAT y GFAT utilizando mediciones logradas por IRM y un procedimiento de validaci\u00f3n cruzada. \u201cLos modelos de aprendizaje profundo con validaci\u00f3n cruzada entrenados en estas im\u00e1genes, utilizando vol\u00famenes estimados de resonancia magn\u00e9tica de todo el cuerpo calculados previamente como etiquetas de verdad, demuestran una estimaci\u00f3n muy precisa de los vol\u00famenes VAT, ASAT y GFAT\u201d, explicaron los autores. Consulta el estudio completo en el siguiente enlace: https:\/\/www.nature.com\/articles\/s41746-022-00654-1 BIBLIOGRAF\u00cdA NATURE https:\/\/www.nature.com\/articles\/s41746-022-00654-1<\/p>","protected":false},"author":1,"featured_media":30162,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,3400,160],"tags":[],"class_list":["post-30161","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-diagnostico","category-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/30161","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=30161"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/30161\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/30162"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=30161"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=30161"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=30161"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}