{"id":40190,"date":"2016-06-20T21:24:51","date_gmt":"2016-06-20T18:24:51","guid":{"rendered":"https:\/\/www.altoros.com\/blog\/?p=40190"},"modified":"2019-06-09T18:09:38","modified_gmt":"2019-06-09T15:09:38","slug":"experimenting-with-deep-neural-networks-for-x-ray-image-segmentation","status":"publish","type":"post","link":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/","title":{"rendered":"Experimenting with Deep Neural Networks for X-Ray Image Segmentation"},"content":{"rendered":"<p>Deep <a href=\"https:\/\/www.altoros.com\/blog\/recurrent-neural-networks-classifying-diagnoses-with-long-short-term-memory\/\">neural networks<\/a> possess a variety of possibilities for improving medical image segmentation. This article shares some of the results of a research conducted by our partners at the Biomedical Image Analysis Department of the United Institute of Informatics Problems, National Academy of Sciences of Belarus. The study aimed at examining the potential of deep learning and encoder-decoder <a href=\"https:\/\/www.altoros.com\/blog\/using-convolutional-neural-networks-and-tensorflow-for-image-classification\/\">convolutional neural networks<\/a> for lung image segmentation.<\/p>\n<p>&nbsp;<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_79_2 counter-hierarchy ez-toc-counter ez-toc-transparent ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#Source_data\" >Source data<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#Network_architecture_and_parameters\" >Network architecture and parameters<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#Brief_analysis\" >Brief analysis<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#Further_reading\" >Further reading<\/a><\/li><\/ul><\/nav><\/div>\n<h3><span class=\"ez-toc-section\" id=\"Source_data\"><\/span>Source data<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>The training data set consisted of 354 chest X-ray images accompanied by the lung masks obtained through manual segmentation. Two different image sources were used:<\/p>\n<ul>\n<li>107 images from the <a href=\"http:\/\/tuberculosis.by\/\" target=\"_blank\" rel=\"noopener noreferrer\">Belarus tuberculosis portal<\/a> manually segmented during the preliminary phase of this project<\/li>\n<li style=\"margin-bottom: 12px\">247 images from the <a href=\"http:\/\/db.jsrt.or.jp\/eng.php\" rel=\"noopener noreferrer\" target=\"_blank\">JSRT database<\/a><\/li>\n<\/ul>\n<p>Examples of the original images and corresponding lung masks are illustrated in the following figure.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/examples-xray-image-segmentation.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/examples-xray-image-segmentation.png\" alt=\"examples-xray-image-segmentation\" width=\"640\" class=\"aligncenter size-full wp-image-40192\" \/><\/a><small>Examples of X-ray images and corresponding lung masks<\/small><\/center><\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Network_architecture_and_parameters\"><\/span>Network architecture and parameters<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>In the figure below, you can find the neural network architecture that was used during the study.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/deep-neural-network-architecture.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/deep-neural-network-architecture.png\" alt=\"deep-neural-network-architecture\" width=\"640\" class=\"aligncenter size-full wp-image-40193\" \/><\/a><small>A simplified scheme of the encoder-decoder neural network architecture<\/small><\/center><\/p>\n<p>The network had a typical deep architecture with the following key elements:<\/p>\n<ul>\n<li>26 convolutional layers<\/li>\n<li>25 batch normalization layers<\/li>\n<li>25 ReLU layers<\/li>\n<li>5 upsampling layers<\/li>\n<\/ul>\n<p>All experiments and testing were performed using the <a href=\"http:\/\/caffe.berkeleyvision.org\/\" target=\"_blank\" rel=\"noopener noreferrer\">Caffe<\/a> framework. The input and output network fragments are illustrated in the figure below.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/neural-network-elements-top.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/neural-network-elements-top.png\" alt=\"neural-network-elements-top\" width=\"640\" class=\"aligncenter size-full wp-image-40194\" \/><\/a><\/center><\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/neural-network-elements-bottom.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/neural-network-elements-bottom.png\" alt=\"neural-network-elements-bottom\" width=\"640\" class=\"aligncenter size-full wp-image-40195\" \/><\/a><small>The input (top) and output (bottom) network elements<\/small><\/center><\/p>\n<p>The neural network was trained on the NVIDIA TITAN X graphics processor with 12 GB of GDDR5 memory. The network training parameters were as follows.<\/p>\n<ul>\n<li>Batch size: 6<\/li>\n<li>Caffe solver: SGD<\/li>\n<li>Number of iterations: 5,000<\/li>\n<li>Number of epochs: 85<\/li>\n<\/ul>\n<p>The total time of the neural network training was approximately three hours. During the training stage, the neural network used approximately 11 GB of GPU memory.<\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Brief_analysis\"><\/span>Brief analysis<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>As a result, the segmentation accuracy was assessed by comparing the automatically obtained lung areas with the manual version using Dice\u2019s coefficient, which is calculated as shown in the formula below.<\/p>\n<p><center><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/dice-coefficient-formula.png\" alt=\"dice-coefficient-formula\" width=\"150\" class=\"aligncenter size-medium wp-image-40196\" \/><\/center><\/p>\n<p>where:<\/p>\n<ul>\n<li><code style=\"color: black; background-color: #e6e6e6;\">T<\/code> is the lung area resulted from manual segmentation and considered as ground truth.<\/li>\n<li><code style=\"color: black; background-color: #e6e6e6;\">S<\/code> is the area obtained through automatic segmentation using the neural network.<\/li>\n<\/ul>\n<p>During the testing stage, the average accuracy was estimated as 0.962 (the minimum score value was 0.926 and the maximum score value was 0.974) with the standard deviation of 0.008.<\/p>\n<p>Examples of the best and worst segmentation results are given in the following figures. The red area in the image below presents the results of segmentation using the trained neural network, and the white line shows the ground truth lung mask boundary.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/segmentation-results-max-dice-score.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/segmentation-results-max-dice-score.png\" alt=\"segmentation-results-max-dice-score\" width=\"640\" class=\"aligncenter size-full wp-image-40191\" \/><\/a><small>Examples of segmentation results with the maximum Dice score<\/small><\/center><\/p>\n<p>Similar to the previous image, the red area in the figure below shows the results of segmentation using the trained neural network, and the white line presents the ground truth lung mask boundary.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/segmentation-results-min-dice-score.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/12\/segmentation-results-min-dice-score.png\" alt=\"segmentation-results-min-dice-score\" width=\"640\" class=\"aligncenter size-full wp-image-40197\" \/><\/a><small>Examples of segmentation results with the minimum Dice score<\/small><\/center><\/p>\n<p>The results obtained during this study have demonstrated that encoder-decoder convolutional neural networks can be considered as a  promising  tool  for  automatic  lung  segmentation  in large-scale projects. For more details about the conducted research, read the paper, <em>&#8220;Lung Image Segmentation Using Deep Learning Methods and Convolutional Neural Networks&#8221;<\/em> (<a href=\"https:\/\/www.researchgate.net\/publication\/301927359_Lung_Image_Segmentation_Using_Deep_Learning_Methods_and_Convolutional_Neural_Networks\" target=\"_blank\" rel=\"noopener noreferrer\">PDF<\/a>).<\/p>\n<p>The described scenario was implemented with the Caffe deep learning framework. If you have tried to use <a href=\"https:\/\/www.altoros.com\/research-papers\/performance-of-deep-learning-frameworks-caffe-deeplearning4j-tensorflow-theano-and-torch\/\">Deeplearning4j, TensorFlow, Theano, or Torch<\/a> for similar purposes, share your experience in the comments.<\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Further_reading\"><\/span>Further reading<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ul>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/recurrent-neural-networks-classifying-diagnoses-with-long-short-term-memory\/\">Recurrent Neural Networks: Classifying Diagnoses with Long Short-Term Memory<\/a><\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/\">TensorFlow and OpenPOWER Driving Faster Cancer Recognition and Diagnosis<\/a><\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/using-convolutional-neural-networks-and-tensorflow-for-image-classification\/\">Using Convolutional Neural Networks and TensorFlow for Image Classification<\/a><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<hr\/>\n<p><center><small>The post was written by Sergey Kovalev; edited and published by Victoria Fedzkovich and <a href=\"https:\/\/www.altoros.com\/blog\/author\/alex\/\">Alex Khizhniak<\/a>.<\/small><\/center><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Deep neural networks possess a variety of possibilities for improving medical image segmentation. This article shares some of the results of a research conducted by our partners at the Biomedical Image Analysis Department of the United Institute of Informatics Problems, National Academy of Sciences of Belarus. The study aimed at [&#8230;]<\/p>\n","protected":false},"author":122,"featured_media":40223,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","footnotes":"","_links_to":"","_links_to_target":""},"categories":[7],"tags":[914,748,749],"class_list":["post-40190","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-opinion","tag-healthcare","tag-machine-learning","tag-tensorflow"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.6 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Experimenting with Deep Neural Networks for X-Ray Image Segmentation | Altoros<\/title>\n<meta name=\"description\" content=\"Learn how neural networks and deep learning frameworks  such as Caffe can help with identifying diagnoses based on X-ray images.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Experimenting with Deep Neural Networks for X-Ray Image Segmentation | Altoros\" \/>\n<meta property=\"og:description\" content=\"Deep neural networks possess a variety of possibilities for improving medical image segmentation. This article shares some of the results of a research conducted by our partners at the Biomedical Image Analysis Department of the United Institute of Informatics Problems, National Academy of Sciences of Belarus. The study aimed at [...]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/\" \/>\n<meta property=\"og:site_name\" content=\"Altoros\" \/>\n<meta property=\"article:published_time\" content=\"2016-06-20T18:24:51+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2019-06-09T15:09:38+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif\" \/>\n\t<meta property=\"og:image:width\" content=\"640\" \/>\n\t<meta property=\"og:image:height\" content=\"381\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/gif\" \/>\n<meta name=\"author\" content=\"Sergey Kovalev\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sergey Kovalev\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/\",\"url\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/\",\"name\":\"Experimenting with Deep Neural Networks for X-Ray Image Segmentation | Altoros\",\"isPartOf\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif\",\"datePublished\":\"2016-06-20T18:24:51+00:00\",\"dateModified\":\"2019-06-09T15:09:38+00:00\",\"author\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/7bb3c35a84eeaa32af69b53773e7fe1a\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#primaryimage\",\"url\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif\",\"contentUrl\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif\",\"width\":640,\"height\":381},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.altoros.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Experimenting with Deep Neural Networks for X-Ray Image Segmentation\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.altoros.com\/blog\/#website\",\"url\":\"https:\/\/www.altoros.com\/blog\/\",\"name\":\"Altoros\",\"description\":\"Insight\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.altoros.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/7bb3c35a84eeaa32af69b53773e7fe1a\",\"name\":\"Sergey Kovalev\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2017\/01\/3faf706-150x150.jpg\",\"contentUrl\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2017\/01\/3faf706-150x150.jpg\",\"caption\":\"Sergey Kovalev\"},\"description\":\"Sergey Kovalev is a senior software engineer with extensive experience in high-load application development, big data and NoSQL solutions, cloud computing, data warehousing, and machine learning. He has strong expertise in back-end engineering, applying the best approaches for development, architecture design, and scaling. He has solid background in software development practices, such as the Agile methodology, prototyping, patterns, refactoring, and code review. Now, Sergey\u2019s main interest lies in big data distributed computing and machine learning.\",\"url\":\"https:\/\/www.altoros.com\/blog\/author\/s-kovalev\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Experimenting with Deep Neural Networks for X-Ray Image Segmentation | Altoros","description":"Learn how neural networks and deep learning frameworks  such as Caffe can help with identifying diagnoses based on X-ray images.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/","og_locale":"en_US","og_type":"article","og_title":"Experimenting with Deep Neural Networks for X-Ray Image Segmentation | Altoros","og_description":"Deep neural networks possess a variety of possibilities for improving medical image segmentation. This article shares some of the results of a research conducted by our partners at the Biomedical Image Analysis Department of the United Institute of Informatics Problems, National Academy of Sciences of Belarus. The study aimed at [...]","og_url":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/","og_site_name":"Altoros","article_published_time":"2016-06-20T18:24:51+00:00","article_modified_time":"2019-06-09T15:09:38+00:00","og_image":[{"width":640,"height":381,"url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif","type":"image\/gif"}],"author":"Sergey Kovalev","twitter_misc":{"Written by":"Sergey Kovalev","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/","url":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/","name":"Experimenting with Deep Neural Networks for X-Ray Image Segmentation | Altoros","isPartOf":{"@id":"https:\/\/www.altoros.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#primaryimage"},"image":{"@id":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#primaryimage"},"thumbnailUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif","datePublished":"2016-06-20T18:24:51+00:00","dateModified":"2019-06-09T15:09:38+00:00","author":{"@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/7bb3c35a84eeaa32af69b53773e7fe1a"},"breadcrumb":{"@id":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#primaryimage","url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif","contentUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/06\/Experimenting-with-Deep-Neural-Networks-for-X-Ray-Image-Segmentation-machine-learning.gif","width":640,"height":381},{"@type":"BreadcrumbList","@id":"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.altoros.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Experimenting with Deep Neural Networks for X-Ray Image Segmentation"}]},{"@type":"WebSite","@id":"https:\/\/www.altoros.com\/blog\/#website","url":"https:\/\/www.altoros.com\/blog\/","name":"Altoros","description":"Insight","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.altoros.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/7bb3c35a84eeaa32af69b53773e7fe1a","name":"Sergey Kovalev","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2017\/01\/3faf706-150x150.jpg","contentUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2017\/01\/3faf706-150x150.jpg","caption":"Sergey Kovalev"},"description":"Sergey Kovalev is a senior software engineer with extensive experience in high-load application development, big data and NoSQL solutions, cloud computing, data warehousing, and machine learning. He has strong expertise in back-end engineering, applying the best approaches for development, architecture design, and scaling. He has solid background in software development practices, such as the Agile methodology, prototyping, patterns, refactoring, and code review. Now, Sergey\u2019s main interest lies in big data distributed computing and machine learning.","url":"https:\/\/www.altoros.com\/blog\/author\/s-kovalev\/"}]}},"_links":{"self":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/40190","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/users\/122"}],"replies":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/comments?post=40190"}],"version-history":[{"count":11,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/40190\/revisions"}],"predecessor-version":[{"id":44077,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/40190\/revisions\/44077"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/media\/40223"}],"wp:attachment":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/media?parent=40190"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/categories?post=40190"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/tags?post=40190"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}