{"id":2815,"date":"2022-02-02T09:00:36","date_gmt":"2022-02-02T09:00:36","guid":{"rendered":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/?p=2815"},"modified":"2022-02-02T18:03:06","modified_gmt":"2022-02-02T18:03:06","slug":"blog-secondment-esr4-ugr","status":"publish","type":"post","link":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/blog-secondment-esr4-ugr\/","title":{"rendered":"ESR4 – Probabilistic methods for detecting anomalies in Whole Slide Images (WSI)"},"content":{"rendered":"

[et_pb_section fb_built=”1″ _builder_version=”3.22″ global_colors_info=”{}”][et_pb_row _builder_version=”3.25″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text _builder_version=”4.14.1″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n

\n

Detection of anomalies in whole slide images can retain relevant histological features in\u00a0<\/span><\/span>training ML models<\/span>\u00a0<\/span>for\u00a0<\/span><\/span>improved<\/span>\u00a0<\/span>diagnostics.\u00a0<\/span><\/h3>\n<\/blockquote>\n

<\/h2>\n\n\t\t
\n\t\t\t
\n\t\t\t\t
\n\t\t\t\n\t\t\t
<\/div>\n\t\t<\/div> \n\t\t
\n\t\t\tHi<\/span>\u00a0<\/span>everyone<\/span>! I am ESR4, Neel Kanwal, and I\u00a0<\/span><\/span>am back\u00a0<\/span><\/span>discussing<\/span>\u00a0<\/span>what I learn<\/span>ed<\/span>\u00a0<\/span>from my stay in Granada.<\/span><\/span>\u00a0\n\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n

 <\/p>\n

Visiting\u00a0new\u00a0places\u00a0and learning from diversity\u00a0has always been\u00a0joyful\u00a0to me. I believe that learning from a culture is like finding a\u00a0unique\u00a0personality in yourself. Thanks to the CLARIFY network-wide training framework. I have finished my three-month secondment at the University of Granada. The charm of\u00a0Andalucia, with lovely\u00a0tapas arrangements and\u00a0Granadian\u00a0traditions,\u00a0left\u00a0a deep engraving in my memories.\u00a0\u00a0<\/span>\u00a0<\/span><\/p>\n

The secondment commenced in September of 2021,\u00a0briefly introducing\u00a0project objectives, current progress,\u00a0and short-term objectives. ESR presented his work and had an interactive discussion on possible advancements. Recommendations and concluded suggestions by\u00a0the\u00a0research group of Prof. Rafael Molina were later selected for active secondment goals.\u00a0A dataset of the histological artifacts is used to test probabilistic\u00a0modeling\u00a0methods.\u00a0\u00a0<\/span>\u00a0<\/span><\/p>\n

The technical perspective of this stay was equally fruitful in learning\u00a0and applying\u00a0new methods\u00a0to preprocessing area of the project. This secondment\u00a0helped\u00a0to familiarize\u00a0probabilistic models and their benefits over traditional machine learning methods.\u00a0Gaussian Processes,\u00a0a non-parametric kernel learning approach,\u00a0helps in estimating multivariate Gaussian distribution on input data using mean and covariance values of\u00a0the\u00a0training dataset.\u00a0A covariance matrix is calculated using a kernel that measures similarity between two input patches within the dataset. The\u00a0encoded prior knowledge is later used to find a predictive distribution for new points.\u00a0\u00a0\u00a0<\/span>\u00a0<\/span><\/p>\n

For\u00a0the\u00a0artifact detection task,\u00a0a\u00a0deep kernel learning\u00a0(DKL)\u00a0approach combines\u00a0the power of hidden representations of neural networks and\u00a0the\u00a0power of Gaussian processes. A range of experiments was\u00a0established to understand the ability of\u00a0the\u00a0model to discriminate and delineate patches with\u00a0the\u00a0presence of significant\u00a0anomalies. Optimization of\u00a0the DKL\u00a0model is still in progress\u00a0and will converge into peer-reviewed work. A\u00a0tuned\u00a0model will have\u00a0broader applications in preprocessing pipeline and automated quality control for better performing CAD systems. Overall, this three-month stay\u00a0impacted project goals and personal development significantly.\u00a0<\/span>\u00a0<\/span><\/p>\n

Special thanks to Prof. Rafael Molina for hosting\u00a0and providing with necessary resources for this work.<\/span><\/p>\n

\n

\"\"<\/p>\n

\u00a0<\/span><\/span>A v<\/span>isit to\u00a0<\/span><\/span>Herradura<\/span>\u00a0<\/span><\/span>on\u00a0<\/span><\/span>the\u00a0<\/span><\/span>invitation of Prof. Rafael Molina<\/span><\/p>\n

\"\"<\/span><\/p>\n

A<\/span>\u00a0<\/span>v<\/span>isit to\u00a0<\/span><\/span>Alhambra<\/span><\/span><\/p>\n

 <\/p>\n

Neel Kanwal – ESR4<\/em><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"

Hi everyone! I am ESR4, Neel Kanwal, and I am back discussing what I learned from my stay in Granada.<\/p>\n","protected":false},"author":8,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","_eb_attr":"","footnotes":""},"categories":[11],"tags":[],"class_list":["post-2815","post","type-post","status-publish","format-standard","hentry","category-secondment"],"_links":{"self":[{"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/posts\/2815","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/comments?post=2815"}],"version-history":[{"count":0,"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/posts\/2815\/revisions"}],"wp:attachment":[{"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/media?parent=2815"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/categories?post=2815"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cvblab.webs.upv.es\/clarify-project.eu\/wp-json\/wp\/v2\/tags?post=2815"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}