{"id":294,"date":"2015-02-12T11:53:11","date_gmt":"2015-02-12T16:53:11","guid":{"rendered":"https:\/\/my.vanderbilt.edu\/masi\/?p=294"},"modified":"2016-10-31T12:30:00","modified_gmt":"2016-10-31T17:30:00","slug":"toward-content-based-image-retrieval-with-deep-convolutional-neural-networks","status":"publish","type":"post","link":"https:\/\/my.vanderbilt.edu\/masi\/2015\/02\/toward-content-based-image-retrieval-with-deep-convolutional-neural-networks\/","title":{"rendered":"Toward content based image retrieval with deep convolutional neural networks"},"content":{"rendered":"<p>Judah E. Sklan, Andrew J. Plassard, Daniel Fabbri, Bennett A. Landman. \u201cToward content based image retrieval with deep convolutional neural networks \u201d In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2015. \u2020<\/p>\n<p><strong>Full text: <\/strong>https:\/\/www.ncbi.nlm.nih.gov\/pubmed\/?term=%E2%80%9CToward+content+based+image+retrieval+with+deep+convolutional+neural+networks+%E2%80%9D<\/p>\n<h2>Abstract<\/h2>\n<div class=\"abstr\">\n<div class=\"\">\n<p><span class=\"highlight\">Content<\/span>&#8211;<span class=\"highlight\">based<\/span> <span class=\"highlight\">image<\/span> <span class=\"highlight\">retrieval<\/span> (CBIR) offers the potential to identify similar case histories, understand rare disorders, and eventually, improve patient care. Recent advances in database capacity, algorithm efficiency, and <span class=\"highlight\">deep<\/span> <span class=\"highlight\">Convolutional<\/span> <span class=\"highlight\">Neural<\/span> <span class=\"highlight\">Networks<\/span> (dCNN), a machine learning technique, have enabled great CBIR success for general photographic images. Here, we investigate applying the leading ImageNet CBIR technique to clinically acquired medical images captured by the Vanderbilt Medical Center. Briefly, we (1) constructed a dCNN with four hidden layers, reducing dimensionality of an input scaled to 128\u00d7128 to an output encoded layer of 4\u00d7384, (2) trained the network using back-propagation 1 million random magnetic resonance (MR) and computed tomography (CT) images, (3) labeled an independent set of 2100 images, and (4) evaluated classifiers on the projection of the labeled images into manifold space. Quantitative results were disappointing (averaging a true positive rate of only 20%); however, the data suggest that improvements would be possible with more evenly distributed sampling across labels and potential re-grouping of label structures. This prelimainry effort at automated classification of medical images with ImageNet is promising, but shows that more work is needed beyond direct adaptation of existing techniques.<\/p>\n<\/div>\n<\/div>\n<div class=\"keywords\">\n<figure id=\"attachment_386\" aria-describedby=\"caption-attachment-386\" style=\"width: 500px\" class=\"wp-caption alignleft\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-386\" src=\"https:\/\/my.vanderbilt.edu\/masi\/wp-content\/uploads\/sites\/2304\n2661\/2016\/10\/nihms656358f2.jpg\" alt=\"Flowchart of the ImageNet approach applied the the anonylized imaging data from clinical radiology.\" width=\"500\" height=\"472\" \/><figcaption id=\"caption-attachment-386\" class=\"wp-caption-text\">Flowchart of the ImageNet approach applied the the anonylized imaging data from clinical radiology.<\/figcaption><\/figure>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Judah E. Sklan, Andrew J. Plassard, Daniel Fabbri, Bennett A. Landman. \u201cToward content based image retrieval with deep convolutional neural networks \u201d In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2015. \u2020 Full text: https:\/\/www.ncbi.nlm.nih.gov\/pubmed\/?term=%E2%80%9CToward+content+based+image+retrieval+with+deep+convolutional+neural+networks+%E2%80%9D Abstract Content&#8211;based image retrieval (CBIR) offers the potential to identify similar case histories, understand rare disorders, and&#8230;<\/p>\n","protected":false},"author":6311,"featured_media":386,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[23],"tags":[],"class_list":["post-294","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning"],"_links":{"self":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/294","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/users\/6311"}],"replies":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/comments?post=294"}],"version-history":[{"count":1,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/294\/revisions"}],"predecessor-version":[{"id":398,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/posts\/294\/revisions\/398"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/media\/386"}],"wp:attachment":[{"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/media?parent=294"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/categories?post=294"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/my.vanderbilt.edu\/masi\/wp-json\/wp\/v2\/tags?post=294"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}