{"id":3012,"date":"2025-10-10T23:42:19","date_gmt":"2025-10-10T21:42:19","guid":{"rendered":"https:\/\/portale2.unime.it\/ai-healthlab\/?p=3012"},"modified":"2025-10-15T12:14:25","modified_gmt":"2025-10-15T10:14:25","slug":"recognition-of-artifacts-in-mris","status":"publish","type":"post","link":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/","title":{"rendered":"Recognition of Artifacts in MRIs"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"3012\" class=\"elementor elementor-3012\">\n\t\t\t\t<div class=\"elementor-element elementor-element-7fad0cb e-flex e-con-boxed e-con e-parent\" data-id=\"7fad0cb\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-5683664a elementor-widget elementor-widget-text-editor\" data-id=\"5683664a\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p>\nLarge medical imaging datasets are becoming standard, but a crucial challenge remains: ensuring that every MRI scan is of sufficient quality, without artifacts that could compromise subsequent analyses or the diagnostic pathway.\n<\/p>\n<p><b>Motivations &amp; Objectives<\/b><\/p>\n<ul>\n<li>Automate MRI image quality control, reducing manual work and subjective bias.<\/li>\n<li>Overcome the scarcity of real artifact data through synthetic data augmentation, enabled by MRI physics-based simulators.<\/li>\n<li>Provide fast, efficient, and reliable tools to support high-throughput clinical pipelines.<\/li>\n<\/ul>\n<p><b>Methods<\/b><\/p>\n<ul>\n<li>Artifact generators inspired by the physics of magnetic resonance imaging (MRI) to simulate errors, distortions, and noise on brain images.<\/li>\n<li>Extraction of abstract and engineered features, able to compactly describe images and facilitate artifact classification.<\/li>\n<li>Automatic feature selection specific to each type of artifact, achieving maximum discriminative power for multisite\/multiscanner detection.<\/li>\n<li>Robust SVM classifiers, trained on selected features, to automatically identify nine types of MRI artifacts.<\/li>\n<\/ul>\n<p><b>Novelty &amp; Contributions<\/b><\/p>\n<ul>\n<li>Physical artifact generators to greatly expand datasets, making manual collection of rare cases less essential.<\/li>\n<li>Definition and validation of a large pool of features for the detection of nine classes of artifacts in structural MRI.<\/li>\n<li>Feature selection module specific for artifact\u2014\u201cclass by class\u201d optimization.<\/li>\n<\/ul>\n<p><b>Results &amp; Validation<\/b><\/p>\n<ul>\n<li>Performance evaluated on mixed databases (synthetic artifacts and clinical trial on multiple sclerosis with expert labels): up to +12.5 percentage points increase in accuracy, F1, F2, precision, and recall compared to conventional methods.<\/li>\n<li>Computationally light pipeline: &lt;1 second per scan, ideal for real-time implementation in clinical departments and large biobanks.<\/li>\n<\/ul>\n<h3><br><\/h3><h3>Related Scientific Articles<\/h3>\n<ul>\n<li>\n    An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training<br>\n    <a href=\"https:\/\/arxiv.org\/abs\/2206.03359\">(arXiv preprint arXiv:2206.03359, 2022)<\/a><br>\n    <a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/38000256\/\">PubMed<\/a><br>\n    <br>    <b>Authors:<\/b> Daniele Ravi, Frederik Barkhof, Daniel C. Alexander, Lemuel Puglisi, Geoffrey JM Parker, Arman Eshaghi (for ADNI)\n  <\/li>\n<\/ul>\n<h3><br><\/h3><h3>Code Repository<\/h3>\n<ul>\n<li>\n    Automatic Quality Control (artifact generator, SVM, feature selection):<br>\n    <a href=\"https:\/\/github.com\/daniravi\/automatic-quality-control\">daniravi\/automatic-quality-control<\/a><br>\n    <br>Main components: <code>src\/qcs\/artefacts\/<\/code> (artifact generators), <code>src\/qcs\/feature_extraction.py<\/code> (features), <code>src\/qcs\/feature_selection.py<\/code>\n  <\/li>\n<\/ul>\n<h3><br><\/h3><h3>Team &amp; Authors<\/h3>\n<ul>\n<li><a href=\"https:\/\/github.com\/daniravi\">Daniele Rav\u00ec<\/a> (PI, artifact simulator and SVM pipeline development)<\/li>\n<li><a href=\"https:\/\/github.com\/LemuelPuglisi\">Lemuel Puglisi<\/a> (Feature engineering, QSA code contributions)<\/li>\n<li>Frederik Barkhof, Daniel C. Alexander, Geoffrey JM Parker, Arman Eshaghi<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Large medical imaging datasets are becoming standard, but a crucial challenge remains: ensuring that every MRI scan is of sufficient quality, without artifacts that could compromise subsequent analyses or the diagnostic pathway. Motivations &amp; Objectives Automate MRI image quality control, reducing manual work and subjective bias. Overcome the scarcity of real artifact data through synthetic&hellip; <a class=\"more-link\" href=\"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/\">Continua a leggere <span class=\"screen-reader-text\">Recognition of Artifacts in MRIs<\/span><\/a><\/p>\n","protected":false},"author":94,"featured_media":2119,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[34],"tags":[],"class_list":["post-3012","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-eng-en","entry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Recognition of Artifacts in MRIs - AI-HealthLab<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Recognition of Artifacts in MRIs - AI-HealthLab\" \/>\n<meta property=\"og:description\" content=\"Large medical imaging datasets are becoming standard, but a crucial challenge remains: ensuring that every MRI scan is of sufficient quality, without artifacts that could compromise subsequent analyses or the diagnostic pathway. Motivations &amp; Objectives Automate MRI image quality control, reducing manual work and subjective bias. Overcome the scarcity of real artifact data through synthetic&hellip; Continua a leggere Recognition of Artifacts in MRIs\" \/>\n<meta property=\"og:url\" content=\"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/\" \/>\n<meta property=\"og:site_name\" content=\"AI-HealthLab\" \/>\n<meta property=\"article:published_time\" content=\"2025-10-10T21:42:19+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-10-15T10:14:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1434\" \/>\n\t<meta property=\"og:image:height\" content=\"1056\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"dravi\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"dravi\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/\"},\"author\":{\"name\":\"dravi\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#\\\/schema\\\/person\\\/d0bae234160fa13008ca10037ea1f672\"},\"headline\":\"Recognition of Artifacts in MRIs\",\"datePublished\":\"2025-10-10T21:42:19+00:00\",\"dateModified\":\"2025-10-15T10:14:25+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/\"},\"wordCount\":330,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/wp-content\\\/uploads\\\/sites\\\/94\\\/2025\\\/10\\\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg\",\"articleSection\":[\"NEWS eng\"],\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/\",\"url\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/\",\"name\":\"Recognition of Artifacts in MRIs - AI-HealthLab\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/wp-content\\\/uploads\\\/sites\\\/94\\\/2025\\\/10\\\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg\",\"datePublished\":\"2025-10-10T21:42:19+00:00\",\"dateModified\":\"2025-10-15T10:14:25+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#primaryimage\",\"url\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/wp-content\\\/uploads\\\/sites\\\/94\\\/2025\\\/10\\\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg\",\"contentUrl\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/wp-content\\\/uploads\\\/sites\\\/94\\\/2025\\\/10\\\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg\",\"width\":1434,\"height\":1056},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/en\\\/recognition-of-artifacts-in-mris\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Recognition of Artifacts in MRIs\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#website\",\"url\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/\",\"name\":\"AI-HealthLab\",\"description\":\"From AI to Care: Innovation for Health\",\"publisher\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#organization\",\"name\":\"AI-HealthLab\",\"url\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/wp-content\\\/uploads\\\/sites\\\/94\\\/2025\\\/10\\\/generated-image-9.png\",\"contentUrl\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/wp-content\\\/uploads\\\/sites\\\/94\\\/2025\\\/10\\\/generated-image-9.png\",\"width\":1024,\"height\":1024,\"caption\":\"AI-HealthLab\"},\"image\":{\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/#\\\/schema\\\/person\\\/d0bae234160fa13008ca10037ea1f672\",\"name\":\"dravi\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1abeb59312fe73568f1b0858fca41fbddc458fc64da57ee303e00578d4af5b35?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1abeb59312fe73568f1b0858fca41fbddc458fc64da57ee303e00578d4af5b35?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/1abeb59312fe73568f1b0858fca41fbddc458fc64da57ee303e00578d4af5b35?s=96&d=mm&r=g\",\"caption\":\"dravi\"},\"url\":\"https:\\\/\\\/portale2.unime.it\\\/ai-healthlab\\\/author\\\/dravi\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Recognition of Artifacts in MRIs - AI-HealthLab","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:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/","og_locale":"it_IT","og_type":"article","og_title":"Recognition of Artifacts in MRIs - AI-HealthLab","og_description":"Large medical imaging datasets are becoming standard, but a crucial challenge remains: ensuring that every MRI scan is of sufficient quality, without artifacts that could compromise subsequent analyses or the diagnostic pathway. Motivations &amp; Objectives Automate MRI image quality control, reducing manual work and subjective bias. Overcome the scarcity of real artifact data through synthetic&hellip; Continua a leggere Recognition of Artifacts in MRIs","og_url":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/","og_site_name":"AI-HealthLab","article_published_time":"2025-10-10T21:42:19+00:00","article_modified_time":"2025-10-15T10:14:25+00:00","og_image":[{"width":1434,"height":1056,"url":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg","type":"image\/jpeg"}],"author":"dravi","twitter_card":"summary_large_image","twitter_misc":{"Scritto da":"dravi","Tempo di lettura stimato":"2 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#article","isPartOf":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/"},"author":{"name":"dravi","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#\/schema\/person\/d0bae234160fa13008ca10037ea1f672"},"headline":"Recognition of Artifacts in MRIs","datePublished":"2025-10-10T21:42:19+00:00","dateModified":"2025-10-15T10:14:25+00:00","mainEntityOfPage":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/"},"wordCount":330,"commentCount":0,"publisher":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#organization"},"image":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#primaryimage"},"thumbnailUrl":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg","articleSection":["NEWS eng"],"inLanguage":"it-IT","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/","url":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/","name":"Recognition of Artifacts in MRIs - AI-HealthLab","isPartOf":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#website"},"primaryImageOfPage":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#primaryimage"},"image":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#primaryimage"},"thumbnailUrl":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg","datePublished":"2025-10-10T21:42:19+00:00","dateModified":"2025-10-15T10:14:25+00:00","breadcrumb":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#primaryimage","url":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg","contentUrl":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/3d93c8_270002f4ef5d42f18276965e4caee35dmv2.jpg","width":1434,"height":1056},{"@type":"BreadcrumbList","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/en\/recognition-of-artifacts-in-mris\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/portale2.unime.it\/ai-healthlab\/"},{"@type":"ListItem","position":2,"name":"Recognition of Artifacts in MRIs"}]},{"@type":"WebSite","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#website","url":"https:\/\/portale2.unime.it\/ai-healthlab\/","name":"AI-HealthLab","description":"From AI to Care: Innovation for Health","publisher":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/portale2.unime.it\/ai-healthlab\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"it-IT"},{"@type":"Organization","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#organization","name":"AI-HealthLab","url":"https:\/\/portale2.unime.it\/ai-healthlab\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#\/schema\/logo\/image\/","url":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/generated-image-9.png","contentUrl":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-content\/uploads\/sites\/94\/2025\/10\/generated-image-9.png","width":1024,"height":1024,"caption":"AI-HealthLab"},"image":{"@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/portale2.unime.it\/ai-healthlab\/#\/schema\/person\/d0bae234160fa13008ca10037ea1f672","name":"dravi","image":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/secure.gravatar.com\/avatar\/1abeb59312fe73568f1b0858fca41fbddc458fc64da57ee303e00578d4af5b35?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/1abeb59312fe73568f1b0858fca41fbddc458fc64da57ee303e00578d4af5b35?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1abeb59312fe73568f1b0858fca41fbddc458fc64da57ee303e00578d4af5b35?s=96&d=mm&r=g","caption":"dravi"},"url":"https:\/\/portale2.unime.it\/ai-healthlab\/author\/dravi\/"}]}},"_links":{"self":[{"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/posts\/3012","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/users\/94"}],"replies":[{"embeddable":true,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/comments?post=3012"}],"version-history":[{"count":5,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/posts\/3012\/revisions"}],"predecessor-version":[{"id":3197,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/posts\/3012\/revisions\/3197"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/media\/2119"}],"wp:attachment":[{"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/media?parent=3012"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/categories?post=3012"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/portale2.unime.it\/ai-healthlab\/wp-json\/wp\/v2\/tags?post=3012"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}