{"id":32260,"date":"2016-11-03T18:54:29","date_gmt":"2016-11-03T15:54:29","guid":{"rendered":"https:\/\/www.altoros.com\/blog\/?p=32260"},"modified":"2019-06-09T19:20:28","modified_gmt":"2019-06-09T16:20:28","slug":"tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis","status":"publish","type":"post","link":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/","title":{"rendered":"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_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\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#Medical_analysis_with_deep_learning_and_HPC\" >Medical analysis with deep learning and HPC<\/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\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#How_it_works\" >How it works<\/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\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#TensorFlow_cluster_details\" >TensorFlow cluster: details<\/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\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#How_to_optimize\" >How to optimize?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#Want_details_View_the_slides\" >Want details? View the slides!<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#Further_reading\" >Further reading<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#About_the_experts\" >About the experts<\/a><\/li><\/ul><\/nav><\/div>\n<h3><span class=\"ez-toc-section\" id=\"Medical_analysis_with_deep_learning_and_HPC\"><\/span>Medical analysis with deep learning and HPC<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>At IBM Edge 2016 in Las Vegas, a use case featured possible cancer detection with a machine learning solution analysing images of lymph nodes. Relying on a distributed model of TensorFlow and high-performing nature of the <a href=\"https:\/\/openpowerfoundation.org\/\" target=\"_blank\" rel=\"noopener noreferrer\">OpenPOWER<\/a> infrastructure, the demonstrated system could accelerate medical data analysis.<\/p>\n<div id=\"attachment_32262\" style=\"width: 160px\" class=\"wp-caption alignleft\"><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/andrei-yurkevich-altoros-v1.jpg\"><img decoding=\"async\" aria-describedby=\"caption-attachment-32262\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/andrei-yurkevich-altoros-v1.jpg\" alt=\"\" width=\"150\" class=\"size-full wp-image-32262\" \/><\/a><p id=\"caption-attachment-32262\" class=\"wp-caption-text\"><small>Andrei Yurkevich<\/small><\/p><\/div>\n<p>The particular subjects of the research were how training time decreases when the cluster grows and whether the accuracy of the results is affected by the <a href=\"https:\/\/www.altoros.com\/research-papers\/performance-of-distributed-tensorflow-a-multi-node-and-multi-gpu-configuration\/\">distributed nature<\/a> of TensorFlow computations.<\/p>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/andreiyurkevich\" target=\"_blank\" rel=\"noopener noreferrer\">Andrei Yurkevich<\/a> of Altoros and <a href=\"https:\/\/www.linkedin.com\/in\/ipoddar\" target=\"_blank\" rel=\"noopener noreferrer\">Indrajit Poddar<\/a> of IBM led this study, investigating the possibility of image analysis acceleration by using high-performance computing (HPC) and varying the number of GPUs and nodes in a cluster.<\/p>\n<div id=\"attachment_32266\" style=\"width: 160px\" class=\"wp-caption alignright\"><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/indrajit-poddar-ibm-v2.jpg\"><img decoding=\"async\" aria-describedby=\"caption-attachment-32266\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/indrajit-poddar-ibm-v2.jpg\" alt=\"\" width=\"150\" class=\"size-full wp-image-32266\" \/><\/a><p id=\"caption-attachment-32266\" class=\"wp-caption-text\"><small>Indrajit Poddar<\/small><\/p><\/div>\n<p>The model was trained on multiple Docker nodes running on OpenPOWER servers equipped with GPUs.<\/p>\n<p>The study used 100,000 images to train the model and test its accuracy. In particular, it researched how scaling out the cluster increases the speed of training and how the accuracy of the results is affected depending on the number of cluster nodes. Training iterations resulted in degradation of typically less than 0.5%.<\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"How_it_works\"><\/span>How it works<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>TensorFlow is an open-source library for machine and deep learning that was originally developed by Google. It incorporates <a href=\"https:\/\/www.altoros.com\/blog\/visualizing-tensorflow-graphs-with-tensorboard\/\" target=\"_blank\" rel=\"noopener noreferrer\">data flow graphs<\/a>, with nodes in the graphs representing mathematical operations, and the edges of the graphs representing multi-dimensional data arrays (i.e., <em>tensors<\/em>).<\/p>\n<p>TensorFlow has a low-level API written in Python and C++, notebooks and examples to learn from, and \u201cthe ability to customize neural network layers&#8230;which gives us great flexibility,\u201d according to Andrei.<\/p>\n<p>Andrei&#8217;s and Indrajit&#8217;s use of GPUs follows recommendations from the TensorFlow community, which encourages this as a way to meet the heavy processing demands of high-load projects.<\/p>\n<p>In their presentation, they briefly discussed the use of machine learning to identify individual faces and objects such as automobiles. They then showed a medical data analysis example, noting they were inspired by the <a href=\"https:\/\/grand-challenge.org\/site\/camelyon16\/\" target=\"_blank\" rel=\"noopener noreferrer\">Camelyon16 Grand Challenge<\/a>, which addressed the issue of automating the detection of metastases of lymph node sections.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/medical-data-analysis-example-image-classification-with-tensorflow-v12.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/medical-data-analysis-example-image-classification-with-tensorflow-v12.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-32268\" \/><\/a><\/center><\/p>\n<p>\u201cWe decided to try the new possibilities given by <a href=\"https:\/\/www.altoros.com\/blog\/distributed-tensorflow-and-classification-of-time-series-data-using-neural-networks\/\">distributed TensorFlow<\/a> and see if we could speed up the whole training using distribution and the OpenPOWER ppc64le architecture,\u201d said Indrajit. \u201cThe (slide above) demonstrates a tumor marked by a researcher, manually at the left side and a tumor detected by an algorithm at the right side.\u201d<\/p>\n<blockquote><p>\u201cAs you can see, the machine is able to catch everything, plus some points missed by human doctors.\u201d \u2014Indrajit Poddar, IBM<\/p><\/blockquote>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"TensorFlow_cluster_details\"><\/span>TensorFlow cluster: details<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>The computer science aspect of the study involved the use of clusters to distribute intensive tasks among nodes. <\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/distributed-deep-learning-using-tensorflow-v12.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/distributed-deep-learning-using-tensorflow-v12.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-32264\" \/><\/a><\/center><\/p>\n<p>The study used 1\u20138 nodes as it scaled up to measure performance and accuracy.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/tensorflow-cluster-v18.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/tensorflow-cluster-v18.png\" alt=\"\" width=\"640\"  class=\"aligncenter size-full wp-image-32269\" \/><\/a><\/center><\/p>\n<p>One of the goals was to improve the training time of the <a href=\"https:\/\/grand-challenge.org\/site\/camelyon16\/data\/\" target=\"_blank\" rel=\"noopener noreferrer\">Camelyon16<\/a> data set without losing any significant accuracy, as illustrated in the slide below. Andrei and Indrajit found that the total time requirement dropped from about 11 hours with one node to about 1.4 hours with an 8-node cluster. The accuracy degraded only from 0.25% and 0.71% as shown in the slide below, \u201cthis method looks promising,\u201d according to Indrajit.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/medical-data-analysis-example-applying-deep-learning-with-tensorflow-v12.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/medical-data-analysis-example-applying-deep-learning-with-tensorflow-v12.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-32267\" \/><\/a><\/center><\/p>\n<p>As also mentioned above, this study employed the use of Dockerfiles. Andrei provided a code example used to create deep learning images.<\/p>\n<p><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/example-dockerfile-to-create-deep-learning-images-v12.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/example-dockerfile-to-create-deep-learning-images-v12.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-32265\" \/><\/a><\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"How_to_optimize\"><\/span>How to optimize?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Andrei and Indrajit concluded their presentation with a discussion of some challenges and future goals. These included adding advanced resource scheduling with Platform Conductor and Kubernetes or Mesos couple of infrastructure issues, and adding more GPUs per system (up to 4\u201316 cards) for improved power consumption and better density. A distributed file system (such as HDFS) integrated with TensorFlow could also enhance the solution.<\/p>\n<p>They also wish to fine-tune the use of TensorFlow, try synchronous training of the system in addition to the asynchronous approach they used in this test, increase the data set to 300,000, and increase the number of iterations.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/deep-learning-cluster-as-a-service-v12.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/deep-learning-cluster-as-a-service-v12.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-32263\" \/><\/a><small>TensorFlow cluster as a service<\/small><\/center><\/p>\n<p>The promise of performance like this and a flexible container model could lead to the idea of Deep Learning as a Service. (Earlier, we <a href=\"https:\/\/www.altoros.com\/blog\/prototype-tensorflow-as-a-service-on-openpower-machines\/\">covered<\/a> the work on this concept.)<\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Want_details_View_the_slides\"><\/span>Want details? View the slides!<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><center><iframe loading=\"lazy\" style=\"border: 1px solid #CCC; border-width: 1px; margin-bottom: 5px; max-width: 100%;\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/r2EUyZ8OWj9tyP\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" allowfullscreen=\"allowfullscreen\"><\/iframe><\/center><\/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\/prototype-tensorflow-as-a-service-on-openpower-machines\/\">Prototype: TensorFlow as a Service on OpenPOWER Machines<\/a><\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/cross-modal-machine-learning-as-a-way-to-prevent-improper-pathology-diagnostics\/\">Cross-Modal Machine Learning as a Way to Prevent Improper Pathology Diagnostics<\/a><\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/experimenting-with-deep-neural-networks-for-x-ray-image-segmentation\/\">Experimenting with Deep Neural Networks for X-ray Image Segmentation<\/a><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"About_the_experts\"><\/span>About the experts<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><small><a href=\"https:\/\/www.linkedin.com\/in\/ipoddar\" target=\"_blank\" rel=\"noopener noreferrer\">Indrajit Poddar<\/a> is a software engineer with 17 years of experience in product development, technical strategy, incubation, and customer support. He has developed scalable distributed software and cloud services, transaction processing, and system management components\u2014delivered through virtualized and cloud environments. Indrajit has expertise in Apache Spark analytics, deep learning, machine learning, and Cloud Foundry\/Docker PaaS cloud services on OpenPOWER systems. He is an IBM Master Inventor with three IBM Outstanding Technical Achievement awards.<\/small><\/p>\n<p><small><a href=\"https:\/\/www.linkedin.com\/in\/andreiyurkevich\" target=\"_blank\" rel=\"noopener noreferrer\">Andrei Yurkevich<\/a> serves as President and Chief Technology Officer at Altoros. Under his supervision, the engineering team has grown from zero to 250+ specialists across seven global locations. Currently, he is responsible for technology alliances in big data and PaaS. Andrei has successfully implemented strategies for software product development, marketing, motivation systems, personnel performance management, and team building.<\/small><\/p>\n<p>&nbsp;<\/p>\n<hr\/>\n<p><center><small>The post was written by Roger Strukhoff, Sophia Turol, and <a href=\"https:\/\/www.altoros.com\/blog\/author\/alex\/\">Alex Khizhniak<\/a>.<\/small><\/center><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Medical analysis with deep learning and HPC<\/p>\n<p>At IBM Edge 2016 in Las Vegas, a use case featured possible cancer detection with a machine learning solution analysing images of lymph nodes. Relying on a distributed model of TensorFlow and high-performing nature of the OpenPOWER infrastructure, the demonstrated system could accelerate medical [&#8230;]<\/p>\n","protected":false},"author":9,"featured_media":32283,"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-32260","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 v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER | Altoros<\/title>\n<meta name=\"description\" content=\"A practical study evaluated the efficiency of training a TensorFlow model in a distributed mode for accelerating the analysis of medical 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\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER | Altoros\" \/>\n<meta property=\"og:description\" content=\"Medical analysis with deep learning and HPC At IBM Edge 2016 in Las Vegas, a use case featured possible cancer detection with a machine learning solution analysing images of lymph nodes. Relying on a distributed model of TensorFlow and high-performing nature of the OpenPOWER infrastructure, the demonstrated system could accelerate medical [...]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/\" \/>\n<meta property=\"og:site_name\" content=\"Altoros\" \/>\n<meta property=\"article:published_time\" content=\"2016-11-03T15:54:29+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2019-06-09T16:20:28+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif\" \/>\n\t<meta property=\"og:image:width\" content=\"640\" \/>\n\t<meta property=\"og:image:height\" content=\"360\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/gif\" \/>\n<meta name=\"author\" content=\"Roger Strukhoff\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Roger Strukhoff\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/\"},\"author\":{\"name\":\"Roger Strukhoff\",\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/#\\\/schema\\\/person\\\/56ea20d6f280f7a442e89e5884b06fd8\"},\"headline\":\"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER\",\"datePublished\":\"2016-11-03T15:54:29+00:00\",\"dateModified\":\"2019-06-09T16:20:28+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/\"},\"wordCount\":895,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/11\\\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif\",\"keywords\":[\"Healthcare\",\"Machine Learning\",\"TensorFlow\"],\"articleSection\":[\"News\\\/Opinion\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/\",\"url\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/\",\"name\":\"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER | Altoros\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/11\\\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif\",\"datePublished\":\"2016-11-03T15:54:29+00:00\",\"dateModified\":\"2019-06-09T16:20:28+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/#\\\/schema\\\/person\\\/56ea20d6f280f7a442e89e5884b06fd8\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/11\\\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif\",\"contentUrl\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/11\\\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif\",\"width\":640,\"height\":360},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER\"}]},{\"@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\\\/56ea20d6f280f7a442e89e5884b06fd8\",\"name\":\"Roger Strukhoff\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/03\\\/roger_strukhoff_user_icon-150x150.jpg\",\"url\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/03\\\/roger_strukhoff_user_icon-150x150.jpg\",\"contentUrl\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/wp-content\\\/uploads\\\/2016\\\/03\\\/roger_strukhoff_user_icon-150x150.jpg\",\"caption\":\"Roger Strukhoff\"},\"description\":\"Roger Strukhoff is Director of Research at Altoros. He also serves as Executive Director of the Tau Institute for Global ICT Research, Conference Chair of Cloud Expo and Things Expo, Co-Chair of the Big Data World Forum, and Open-Source Chair for the global DCD Converged conference series. He received his BA from Knox College, and conducted MBA studies at California State University\\\/East Bay. Previously in his career, he was VP of New Products at International Data Group and Director of Global Publications at TIBCO Software.\",\"url\":\"https:\\\/\\\/www.altoros.com\\\/blog\\\/author\\\/rstrukhoff\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER | Altoros","description":"A practical study evaluated the efficiency of training a TensorFlow model in a distributed mode for accelerating the analysis of medical 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\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/","og_locale":"en_US","og_type":"article","og_title":"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER | Altoros","og_description":"Medical analysis with deep learning and HPC At IBM Edge 2016 in Las Vegas, a use case featured possible cancer detection with a machine learning solution analysing images of lymph nodes. Relying on a distributed model of TensorFlow and high-performing nature of the OpenPOWER infrastructure, the demonstrated system could accelerate medical [...]","og_url":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/","og_site_name":"Altoros","article_published_time":"2016-11-03T15:54:29+00:00","article_modified_time":"2019-06-09T16:20:28+00:00","og_image":[{"width":640,"height":360,"url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif","type":"image\/gif"}],"author":"Roger Strukhoff","twitter_misc":{"Written by":"Roger Strukhoff","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#article","isPartOf":{"@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/"},"author":{"name":"Roger Strukhoff","@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/56ea20d6f280f7a442e89e5884b06fd8"},"headline":"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER","datePublished":"2016-11-03T15:54:29+00:00","dateModified":"2019-06-09T16:20:28+00:00","mainEntityOfPage":{"@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/"},"wordCount":895,"commentCount":0,"image":{"@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#primaryimage"},"thumbnailUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif","keywords":["Healthcare","Machine Learning","TensorFlow"],"articleSection":["News\/Opinion"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/","url":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/","name":"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER | Altoros","isPartOf":{"@id":"https:\/\/www.altoros.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#primaryimage"},"image":{"@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#primaryimage"},"thumbnailUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif","datePublished":"2016-11-03T15:54:29+00:00","dateModified":"2019-06-09T16:20:28+00:00","author":{"@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/56ea20d6f280f7a442e89e5884b06fd8"},"breadcrumb":{"@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#primaryimage","url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif","contentUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/11\/TensorFlow-OpenPOWER-Cancer-Recognition-Diagnosis.gif","width":640,"height":360},{"@type":"BreadcrumbList","@id":"https:\/\/www.altoros.com\/blog\/tensorflow-and-openpower-driving-faster-cancer-recognition-and-diagnosis\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.altoros.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Identifying Cancer Faster with Distributed TensorFlow on OpenPOWER"}]},{"@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\/56ea20d6f280f7a442e89e5884b06fd8","name":"Roger Strukhoff","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/03\/roger_strukhoff_user_icon-150x150.jpg","url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/03\/roger_strukhoff_user_icon-150x150.jpg","contentUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2016\/03\/roger_strukhoff_user_icon-150x150.jpg","caption":"Roger Strukhoff"},"description":"Roger Strukhoff is Director of Research at Altoros. He also serves as Executive Director of the Tau Institute for Global ICT Research, Conference Chair of Cloud Expo and Things Expo, Co-Chair of the Big Data World Forum, and Open-Source Chair for the global DCD Converged conference series. He received his BA from Knox College, and conducted MBA studies at California State University\/East Bay. Previously in his career, he was VP of New Products at International Data Group and Director of Global Publications at TIBCO Software.","url":"https:\/\/www.altoros.com\/blog\/author\/rstrukhoff\/"}]}},"_links":{"self":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/32260","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\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/comments?post=32260"}],"version-history":[{"count":38,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/32260\/revisions"}],"predecessor-version":[{"id":44094,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/32260\/revisions\/44094"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/media\/32283"}],"wp:attachment":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/media?parent=32260"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/categories?post=32260"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/tags?post=32260"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}