{"id":770,"date":"2022-04-07T13:09:34","date_gmt":"2022-04-07T13:09:34","guid":{"rendered":"https:\/\/www.embl.org\/about\/info\/annual-report\/?page_id=770"},"modified":"2022-06-07T09:14:11","modified_gmt":"2022-06-07T09:14:11","slug":"artificial-intelligence-revolutionises-microscopy","status":"publish","type":"page","link":"https:\/\/www.embl.org\/about\/info\/annual-report\/ar2021\/artificial-intelligence-revolutionises-microscopy","title":{"rendered":"Artificial intelligence revolutionises microscopy"},"content":{"rendered":"\n\n  <style>\n    .vf-hero {\n              --vf-hero--bg-image: url('https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/20220524_AR2021_banners-scaled.jpg');\n            }\n\n  <\/style>\n<section id=\"\" class=\"vf-hero | vf-u-fullbleed  | vf-u-margin__bottom--0\">\n  <div class=\"vf-hero__content | vf-box | vf-stack vf-stack--400\">\n        <h1 class=\"vf-hero__heading\">\n              Annual Report 2021          <\/h1>\n\n        <p class=\"vf-hero__subheading\">A year of exceptional life science research, training, service, industry collaboration, and integration of European life science research.<\/p>\n    \n    \n      <\/div>\n<\/section>\n<!--\/vf-hero-->\n\n\n\n\n<div class=\"vf-grid | vf-grid__col-3\"><div class=\"vf-grid__col--span-2\"><!--[vf\/content]-->\n<div class=\"vf-content\">\n\n<h1 class=\"wp-block-heading\"><strong>Artificial intelligence revolutionises microscopy<\/strong><\/h1>\n\n\n\n<h2 class=\"wp-block-heading\">From using artificial neural nets to elevate biological image analysis to applying machine learning to probe organoid cultures, AI-associated techniques contributed significantly to EMBL\u2019s microscopy-based research activities.&nbsp; &nbsp;<\/h2>\n\n\n\n<figure class=\"vf-figure wp-block-image size-full is-style-default\"><img decoding=\"async\" class=\"vf-figure__image\" src=\"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/Labelled-Microtubules-in-single-molecule-localization-microscopy.png\" alt=\"\" class=\"wp-image-2881\"\/><figcaption class=\"vf-figure__caption\">EMBL scientists and their collaborators have developed DECODE, a neural network based fitter that accelerates super-resolution microscopy imaging. Here, microtubules are labelled with a high concentration of anti-\u03b1 and anti-\u03b2-tubulin primary and Alexa Fluor 647 secondary antibodies. Credit: Jonas Ries\/EMBL<\/figcaption><\/figure>\n\n\n\n<p>Artificial intelligence (AI) proved to be a game-changer in the fields of microscopy and image analysis in 2021.&nbsp;&nbsp;<\/p>\n\n\n\n<p>AI can help overcome the limitations of traditional tools. For example, light-sheet microscopy and light-field microscopy hold different advantages and challenges. To take advantage of the benefits of each technique and with the help of \u200b\u200bstrong<a href=\"https:\/\/www.embl.org\/news\/science\/the-rise-gpu-computing-science\/\"> GPU compute power<\/a> provided internally by EMBL IT Services, researchers at<a href=\"https:\/\/www.embl.org\/news\/science\/artificial-intelligence-makes-great-microscopes-better-than-ever\/\"> EMBL developed a machine-learning approach<\/a> that uses light-field microscopy to image large 3D samples and light-sheet microscopy to train AI algorithms, which then create an accurate 3D picture of the sample.<\/p>\n\n\n\n<p>Similarly, the field of super-resolution microscopy also benefited from an injection of AI-driven innovations. \u201cOne of the biggest limitations of super-resolution microscopy is how long it takes to collect data from the microscope,\u201d said Lucas-Raphael M\u00fcller, former master\u2019s degree student in the Ries Group at EMBL Heidelberg.<\/p>\n\n\n\n<p>To overcome this challenge,<a href=\"https:\/\/www.embl.org\/news\/science\/artificial-neural-networks-revolutionise-biological-image-analysis\/\"> EMBL scientists and collaborators developed DECODE<\/a> (DEep COntext DEpendent), an open-source computer program based on a neural network that learns from training data. Using this, imaging speeds can be increased up to tenfold with minimal loss of resolution.<\/p>\n\n\n\n<p>At EMBL Barcelona, researchers developed<a href=\"https:\/\/www.embl.org\/news\/science\/morgana-organoids-and-machine-learning\/\"> MOrgAna, an open-source software<\/a> that uses machine learning to analyse images of organoids and perform segmentation. Due to its ability to capture the complex morphological features of organoids, MOrgAna performs better segmentation than previously existing platforms.<\/p>\n\n\n\n<p>EMBL research results in this area represent the future of science: open, collaborative, interdisciplinary, and designed to accelerate knowledge transfer.<\/p>\n\n<\/div>\n<\/div>\n\n\n<div class=\"\"><!--[vf\/content]-->\n<div class=\"vf-content\">\n\n<div style=\"height:321px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<article class=\"vf-profile vf-profile--very-easy vf-profile--medium vf-profile--block | vf-u-margin__bottom--400\">\n\n    <img decoding=\"async\" width=\"155\" height=\"175\" src=\"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/Jia_Le_Lim_.jpg\" class=\"vf-profile__image\" alt=\"\" loading=\"lazy\" itemprop=\"image\" \/>\n    <h3 class=\"vf-profile__title\" style=\"text-align: center;\">\n                                <\/h3>\n    \n    \n    \n      \n\n    \n<\/article>\n\n\n\n<p class=\"has-text-align-left vf-u-text-color--green vf-text--body vf-text-body--2\"><em><meta charset=\"utf-8\">\u201cThe rapid progress in adopting deep learning\/AI in microscopy and image analysis never fails to amaze me, as such platforms enable us to glean trailblazing insights from mammoth amounts of data or imagery, quickly.\u201d<\/em><\/p>\n\n\n\n<p class=\"has-text-align-left  vf-text--body vf-text-body--5\"><meta charset=\"utf-8\">\u2014 Jia Le Lim, PhD student, <a href=\"https:\/\/www.embl.org\/groups\/trivedi\/\">Trivedi Group<\/a> at EMBL Barcelona, whose response to a pandemic that limited her lab access in 2021 was to help create a \u2018smart\u2019, easy-to-use, open-source software, MOrgAna, for analysing organoid images in a high-throughput manner.<\/p>\n\n\n\n<div class=\"vf-box vf-box--easy vf-box-theme--tertiary | vf-u-margin__bottom--400\">\n      <h3 class=\"vf-box__heading\">\n                Explore more 2021 EMBL AI highlights:                  <\/h3> \n        <p class=\"vf-box__text\"><!-- wp:list --><\/p>\n<ul>\n<li><a href=\"https:\/\/www.embl.org\/news\/science\/artificial-intelligence-makes-great-microscopes-better-than-ever\/\"><span style=\"font-weight: 400;\">Artificial intelligence makes great microscopes better than ever<\/span><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/www.embl.org\/news\/science\/artificial-neural-networks-revolutionise-biological-image-analysis\/\"><span style=\"font-weight: 400;\">Artificial neural networks revolutionise biological image analysis<\/span><\/a><span style=\"font-weight: 400;\">\u00a0<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/www.embl.org\/news\/science\/morgana-organoids-and-machine-learning\/\"><span style=\"font-weight: 400;\">Organoids and machine learning: image analysis software developed during lockdown <\/span><\/a><\/li>\n<\/ul>\n<p class=\"vf-box__text\"><!-- \/wp:list --><\/p>\n<\/div>\n\n\n<h3 class=\"wp-block-heading\">References<\/h3>\n\n\n\n<p class=\"vf-text--body vf-text-body--5\">Wagner N <em>et al. <\/em>(2021). <a href=\"https:\/\/dx.doi.org\/10.1038\/s41592-021-01136-0\">Deep learning-enhanced light-field imaging with continuous validation<\/a>. <em>Nature Methods, <\/em>7 May 2021. DOI: 10.1038\/s41592-021-01136-0<\/p>\n\n\n\n<p class=\"vf-text--body vf-text-body--5\">Speiser A, M\u00fcller LR <em>et al.<\/em> (2021).&nbsp; <a href=\"https:\/\/www.nature.com\/articles\/s41592-021-01236-x?proof=thttps%3A%2F%2Fwww.nature.com%2Farticles%2Fsj.bdj.2014.353%3Fproof%3Dt\">Deep learning enables fast and dense single-molecule localization with high accuracy<\/a><em>. Nature Methods<\/em>, 03 September 2021. DOI: 10.1038\/s41592-021-01236-x<\/p>\n\n\n\n<p class=\"vf-text--body vf-text-body--5\">Gritti N, Lim JL <em>et al.<\/em> (2021). <a href=\"https:\/\/journals.biologists.com\/dev\/article\/148\/18\/dev199611\/272032\/MOrgAna-accessible-quantitative-analysis-of\">MOrgAna: accessible quantitative analysis of organoids with machine learning<\/a><em>. Development, <\/em>8 September 2021. DOI: 10.1242\/dev.199611<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n\n\n<style>\n    <\/style>\n\n<section id=\"wp-block-1\">\n  <div class=\"vf-card-container  | vf-u-fullbleed  \n  | vf-u-background-color-ui--grey--light \">\n          <div class=\"vf-section-header | vf-u-margin__bottom--600\">\n        <h2 class=\"vf-section-header__heading\" >\n            <\/h2>\n              <\/div>\n      \n\n<div class=\"embl-grid\"><div class=\"\"><!--[vf\/content]-->\n<div class=\"vf-content\">\n\n<h3 class=\"wp-block-heading\"><a href=\"https:\/\/www.embl.org\/about\/info\/annual-report\/\">Back to Annual report<\/a><\/h3>\n\n<\/div>\n<\/div>\n\n\n<div class=\"\"><!--[vf\/content]-->\n<div class=\"vf-content\">\n\n<article class=\"vf-card vf-card--brand vf-card--bordered vf-u-margin__bottom--800\" default>\n  <img decoding=\"async\" width=\"1000\" height=\"600\" src=\"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/bone-marrow.jpeg\" class=\"vf-card__image\" alt=\"\" loading=\"lazy\" itemprop=\"image\" srcset=\"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/bone-marrow.jpeg 1000w, https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/bone-marrow-300x180.jpeg 300w, https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/05\/bone-marrow-768x461.jpeg 768w\" sizes=\"auto, (max-width: 1000px) 100vw, 1000px\" \/>\n  <div class=\"vf-card__content | vf-stack vf-stack--400\">\n          <h3 class=\"vf-card__heading\">\n                  <a class=\"vf-card__link\" href=\"https:\/\/www.embl.org\/about\/info\/annual-report\/ar2021\/delving-deeper-into-the-human-genome\" target=\"\">\n        \n        Next Story\n                  <svg aria-hidden=\"true\" class=\"vf-card__heading__icon | vf-icon vf-icon-arrow--inline-end\" width=\"1em\" height=\"1em\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\">\n            <path d=\"M0 12c0 6.627 5.373 12 12 12s12-5.373 12-12S18.627 0 12 0C5.376.008.008 5.376 0 12zm13.707-5.209l4.5 4.5a1 1 0 010 1.414l-4.5 4.5a1 1 0 01-1.414-1.414l2.366-2.367a.25.25 0 00-.177-.424H6a1 1 0 010-2h8.482a.25.25 0 00.177-.427l-2.366-2.368a1 1 0 011.414-1.414z\" fill=\"currentColor\" fill-rule=\"nonzero\"><\/path>\n          <\/svg>\n        <\/a>\n              <\/h3>\n    \n          <p class=\"vf-card__subheading\">Delving deeper into the human genome<\/p>\n    \n          <p class=\"vf-card__text\"><span style=\"font-weight: 400;\">EMBL research and tools advance understanding of genetic underpinnings of human disease.<\/span><\/p>\n      <\/div>\n<\/article>\n\n<\/div>\n<\/div>\n\n\n<div class=\"\"><!--[vf\/content]-->\n<div class=\"vf-content\">\n\n<article class=\"vf-card vf-card--brand vf-card--bordered vf-u-margin__bottom--800\" default>\n      <img decoding=\"async\" src=\"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-content\/uploads\/2022\/06\/AR2021_PDF_mock-up_AdobeStock_182004081.jpg\" class=\"vf-card__image\" alt=\"\" loading=\"lazy\" itemprop=\"image\">\n  \n  <div class=\"vf-card__content | vf-stack vf-stack--400\">\n          <h3 class=\"vf-card__heading\">\n                  <a class=\"vf-card__link\" href=\"https:\/\/www.embl.org\/documents\/document\/annual-report-2021\/\" target=\"_blank\">\n        \n        Download the annual report summary \n                  <svg aria-hidden=\"true\" class=\"vf-card__heading__icon | vf-icon vf-icon-arrow--inline-end\" width=\"1em\" height=\"1em\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\">\n            <path d=\"M0 12c0 6.627 5.373 12 12 12s12-5.373 12-12S18.627 0 12 0C5.376.008.008 5.376 0 12zm13.707-5.209l4.5 4.5a1 1 0 010 1.414l-4.5 4.5a1 1 0 01-1.414-1.414l2.366-2.367a.25.25 0 00-.177-.424H6a1 1 0 010-2h8.482a.25.25 0 00.177-.427l-2.366-2.368a1 1 0 011.414-1.414z\" fill=\"currentColor\" fill-rule=\"nonzero\"><\/path>\n          <\/svg>\n        <\/a>\n              <\/h3>\n    \n    \n          <p class=\"vf-card__text\">A snapshot of EMBL 2021 facts and figures<\/p>\n      <\/div>\n<\/article>\n\n<\/div>\n<\/div>\n<\/div>\n\n\n        <\/div>\n<\/section>","protected":false},"excerpt":{"rendered":"","protected":false},"author":6,"featured_media":0,"parent":38,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"vf_template_subpage.php","meta":{"_acf_changed":false,"footnotes":""},"embl_taxonomy":[],"class_list":["post-770","page","type-page","status-publish","hentry"],"acf":[],"embl_taxonomy_terms":[],"_links":{"self":[{"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/pages\/770","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/comments?post=770"}],"version-history":[{"count":50,"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/pages\/770\/revisions"}],"predecessor-version":[{"id":3608,"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/pages\/770\/revisions\/3608"}],"up":[{"embeddable":true,"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/pages\/38"}],"wp:attachment":[{"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/media?parent=770"}],"wp:term":[{"taxonomy":"embl_taxonomy","embeddable":true,"href":"https:\/\/www.embl.org\/about\/info\/annual-report\/wp-json\/wp\/v2\/embl_taxonomy?post=770"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}