{"id":295,"date":"2019-10-01T15:17:23","date_gmt":"2019-10-01T13:17:23","guid":{"rendered":"http:\/\/www.itec.aau.at\/~mt\/?p=295"},"modified":"2020-01-15T12:57:53","modified_gmt":"2020-01-15T11:57:53","slug":"mmm20-instrument-classification","status":"publish","type":"post","link":"http:\/\/www.itec.aau.at\/~mt\/2019\/10\/mmm20-instrument-classification\/","title":{"rendered":"MMM&#8217;20: Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos"},"content":{"rendered":"\n<p>Our paper has been accepted for publication at the <a href=\"http:\/\/mmm2020.kr\/\">MMM 2020 Conference on Multimedia Modeling<\/a>. The work was conducted in the context of the ongoing <a href=\"http:\/\/ovid.itec.aau.at\/\">OVID project<\/a>.<\/p>\n\n\n\n<p><strong>Authors:<\/strong> Natalia Sokolova, Klaus Schoeffmann, Mario Taschwer (AAU Klagenfurt); Doris Putzgruber-Adamitsch, Yosuf El-Shabrawi (Klinikum Klagenfurt)<\/p>\n\n\n\n<p><strong>Abstract:<\/strong><br> In the field of ophthalmic surgery, many clinicians nowadays record  their microscopic procedures with a video camera and use the recorded  footage for later purpose, such as forensics, teaching, or training.  However, in order to efficiently use the video material after surgery,  the video content needs to be analyzed automatically. Important semantic  content to be analyzed and indexed in these short videos are operation  instruments, since they provide an indication of the corresponding  operation phase and surgical action. Related work has already shown that  it is possible to accurately detect instruments in cataract surgery  videos. However, their underlying dataset (from the CATARACTS challenge)  has very good visual quality, which is not reflecting the typical  quality of videos acquired in general hospitals. In this paper, we  therefore analyze the generalization performance of deep learning models  for instrument recognition in terms of dataset change. More precisely,  we trained such models as ResNet-50, Inception v3 and NASNet Mobile  using a dataset of high visual quality (CATARACT) and test it on another  dataset with low visual quality (Cataract-101), and vice versa. Our  results show that the generalizability is rather low in general, but  clearly worse for the model trained on the high-quality dataset. Another  important observation is the fact that the trained models are able to  detect similar instruments in the other dataset even if their appearance  is different.<\/p>\n\n\n\n<p><strong>URL:<\/strong> <a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-37734-2_51\">https:\/\/link.springer.com\/chapter\/10.1007\/978-3-030-37734-2_51<\/a><\/p>\n\n\n\n<p><strong>Bibtex:<\/strong><\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">@InProceedings{Sokolova2020,<br>   author    = {Sokolova, Natalia and Schoeffmann, Klaus and Taschwer, Mario and Putzgruber-Adamitsch, Doris and El-Shabrawi, Yosuf},<br>   title     = {Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos},<br>   booktitle = {MultiMedia Modeling},<br>   year      = {2020},<br>   editor    = {Cheng, Wen-Huang and Kim, Junmo and Chu, Wei-Ta and Cui, Peng and Choi, Jung-Woo and Hu, Min-Chun and De Neve, Wesley},<br>   pages     = {626--636},<br>   address   = {Cham},<br>   publisher = {Springer International Publishing},<br>   doi       = {10.1007\/978-3-030-37734-2_51},<br>   isbn      = {978-3-030-37734-2}<br> }<\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Our paper has been accepted for publication at the MMM 2020 Conference on Multimedia Modeling. The work was conducted in the context of the ongoing OVID project. Authors: Natalia Sokolova, Klaus Schoeffmann, Mario Taschwer (AAU Klagenfurt); Doris Putzgruber-Adamitsch, Yosuf El-Shabrawi (Klinikum Klagenfurt) Abstract: In the field of ophthalmic surgery, many clinicians nowadays record their microscopic [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-295","post","type-post","status-publish","format-standard","hentry","category-research"],"_links":{"self":[{"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/posts\/295","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/comments?post=295"}],"version-history":[{"count":2,"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/posts\/295\/revisions"}],"predecessor-version":[{"id":305,"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/posts\/295\/revisions\/305"}],"wp:attachment":[{"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/media?parent=295"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/categories?post=295"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.itec.aau.at\/~mt\/wp-json\/wp\/v2\/tags?post=295"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}