{"id":81,"date":"2018-03-14T20:48:48","date_gmt":"2018-03-14T20:48:48","guid":{"rendered":"http:\/\/gero.usc.edu\/labs\/irimialab\/?page_id=81"},"modified":"2026-04-21T23:12:19","modified_gmt":"2026-04-21T23:12:19","slug":"research","status":"publish","type":"page","link":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/","title":{"rendered":"Research"},"content":{"rendered":"<div class=\"wpb-content-wrapper\"><p>[vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;566&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text css=&#8221;&#8221;]<\/p>\n<h2><strong>Brain age<\/strong><\/h2>\n<p>[\/vc_column_text][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify\">In recent years, biological age has emerged as a useful metric for quantifying how an individual\u2019s brain deviates from typical aging trajectories. The difference between an individual\u2019s chronological age and predicted brain age, termed the brain age gap, is widely used as a marker of neurological injury, neurodegenerative disease, and disease risk. We develop and apply deep neural networks to estimate brain age from MRI data, considering both the overall pace of brain aging and regional variation in local brain age. These measures provide insight into atypical aging and have applications in assessing disease risk, including Alzheimer\u2019s disease, as well as tracking cognitive recovery following traumatic brain injury.<\/p>\n<ul>\n<li>\n<p class=\"c-article-title\" data-test=\"article-title\"><a href=\"https:\/\/www.pnas.org\/doi\/abs\/10.1073\/pnas.2413442122\">Deep learning to quantify the pace of brain aging in relation to neurocognitive changes<\/a><\/p>\n<\/li>\n<li>\n<p class=\"c-article-title\" data-test=\"article-title\"><a href=\"https:\/\/www.pnas.org\/doi\/10.1073\/pnas.2214634120\">Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment<\/a><\/p>\n<\/li>\n<\/ul>\n<p>[\/vc_column_text][\/vc_column][vc_column][vc_separator css=&#8221;&#8221;][\/vc_column][\/vc_row][vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;1615&#8243; img_size=&#8221;full&#8221; css=&#8221;&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text css=&#8221;&#8221;]<\/p>\n<h2><strong>Deep learning for neuroimaging and genetics<\/strong><\/h2>\n<p>[\/vc_column_text][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify\" data-pm-slice=\"1 1 []\">Artificial intelligence is one of the fastest growing fields in research and continues to expand rapidly across disciplines. Our lab develops explainable AI methods to analyze neuroimaging and genomic data, with the goal of advancing our understanding of healthy aging and neurodegenerative disease. Our models leverage cutting edge deep learning and multimodal data integration techniques to capture complex relationships between brain structure, genetics, cognition, and aging. Through these efforts, we aim to bridge computational innovation with clinical and neuroscientific applications, contributing both methodological advances and a deeper understanding of brain health across the lifespan.<\/p>\n<ul>\n<li data-start=\"759\" data-end=\"1033\"><a href=\"https:\/\/link.springer.com\/article\/10.1007\/s11357-025-02046-1\">Deep neural networks and genome-wide associations reveal the polygenic architecture of local brain aging<\/a><\/li>\n<li data-start=\"759\" data-end=\"1033\"><a class=\"gsc_a_at\" href=\"https:\/\/arxiv.org\/abs\/2601.10912\">Graph neural network reveals the local cortical morphology of brain aging in normal cognition and Alzheimer&#8217;s disease<\/a><\/li>\n<\/ul>\n<p>[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_separator css=&#8221;.vc_custom_1653015616527{padding-top: 25px !important;padding-bottom: 25px !important;}&#8221;][\/vc_column][\/vc_row][vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;515&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text]<\/p>\n<h2><b>Demyelination in health and disease<\/b><\/h2>\n<p>[\/vc_column_text][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify\">Myelin sheaths are fatty axonal coatings that are essential to the health and function of the brain and play a key role in both normal aging and disease. Cortical demyelination can occur in traumatic brain injury (TBI) and is also associated with broader neurodegenerative processes. The ratio <i>R<\/i> of <i>T1<\/i>&#8211; to <i>T2<\/i>-weighted magnetic resonance image intensities serves as a measure of relative myelin content in the cortex, which we can compute longitudinally across clinical cohorts. Using this approach, we map intracortical myelin and its changes over time, comparing patterns of demyelination after mTBI to those seen in typical aging to better understand central nervous system dysfunction and inform potential remyelination therapies.<\/p>\n<ul>\n<li>\n<p class=\"c-article-title\" data-test=\"article-title\"><a href=\"https:\/\/www.frontiersin.org\/journals\/neuroscience\/articles\/10.3389\/fnins.2022.905979\/full\">Vascular cognitive impairment after mild stroke: connectomic insights, neuroimaging, and knowledge translation<\/a><\/p>\n<\/li>\n<li>\n<p class=\"c-article-title\" data-test=\"article-title\"><a href=\"https:\/\/www.frontiersin.org\/journals\/neurology\/articles\/10.3389\/fneur.2022.854396\/full\">Mild traumatic brain injury results in significant and lasting cortical demyelination<\/a><\/p>\n<\/li>\n<\/ul>\n<p>[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_separator css=&#8221;.vc_custom_1653015616527{padding-top: 25px !important;padding-bottom: 25px !important;}&#8221;][\/vc_column][\/vc_row][vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;390&#8243; img_size=&#8221;full&#8221; css=&#8221;&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text]<\/p>\n<h2><b>Functional neuroanatomy of brain injury<\/b><\/h2>\n<p>[\/vc_column_text][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify\">Studying the functional neuroanatomy of mild traumatic brain injury (mTBI) is essential for understanding neurological and cognitive outcomes post-injury. The brain undergoes significant changes in functional connectivity (FC), quantified using functional magnetic resonance imaging (fMRI), after mTBI, and these alterations underlie persistent neural and cognitive effects that vary with age and sex. Our work focuses on post-traumatic FC changes across both acute and chronic stages of injury, mapping sex- and age-dependent patterns across cortical resting-state networks (RSNs) in a cohort of mTBI patients. Our findings indicate that male sex and older age at injury are associated with more pronounced FC alterations, which may contribute to post-traumatic cognitive deficits.<\/p>\n<ul>\n<li>\n<p class=\"c-article-title\" data-test=\"article-title\"><a href=\"https:\/\/www.liebertpub.com\/doi\/10.1089\/neu.2023.0509?url_ver=Z39.88-2003&amp;rfr_id=ori:rid:crossref.org&amp;rfr_dat=cr_pub%20%200pubmed\">Identification and connectomic profiling of concussion using bayesian machine learning<\/a><\/p>\n<\/li>\n<li>\n<p class=\"c-article-title\" data-test=\"article-title\"><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0010945223002885?via%3Dihub\">Prediction of cognitive outcome after mild traumatic brain injury from acute measures of communication within brain networks<\/a><\/p>\n<\/li>\n<\/ul>\n<p>[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_separator css=&#8221;.vc_custom_1653015616527{padding-top: 25px !important;padding-bottom: 25px !important;}&#8221;][\/vc_column][\/vc_row][vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;618&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text]<\/p>\n<h2><b>Atypical aging in non-industrial populations<\/b><\/h2>\n<p>[\/vc_column_text][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify\">Accelerated brain loss and atrophy can indicate increased risk of dementia. The indigenous forager-horticulturist Tsiman\u00e9 of lowland Bolivia show a decline in brain volume that is about 70% slower than that of Western populations. We generate automated segmentations of computed tomography (CT) brain scans from the Tsiman\u00e9 Health and Life History Project, enabling volumetric analysis of subcortical and cortical regions to compare brain development and atrophy with populations in developed countries. Because of their non-sedentary lifestyle and diet rich in fiber, vegetables, and lean meats, the Tsiman\u00e9 provide a unique opportunity to study the effects of modern lifestyles on brain health and aging.<\/p>\n<ul>\n<li><a href=\"https:\/\/academic.oup.com\/biomedgerontology\/article-abstract\/76\/12\/2147\/6280196\"><span style=\"font-weight: 400\">The indigenous South American Tsiman\u00e9 exhibit relatively modest decrease in brain volume with age despite high systemic inflammation<\/span><\/a><\/li>\n<li><a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/35262289\/\">Prevalence of dementia and mild cognitive impairment in indigenous Bolivian forager-horticulturalists<\/a><\/li>\n<\/ul>\n<p>[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_separator css=&#8221;.vc_custom_1653015616527{padding-top: 25px !important;padding-bottom: 25px !important;}&#8221;][\/vc_column][\/vc_row][vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;567&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text]<\/p>\n<h2><b>Structural connectomics in health and disease<\/b><\/h2>\n<p>[\/vc_column_text][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify\">Mild traumatic brain injury (mTBI) can lead to a range of cognitive and neurological effects that often persist despite normal findings on conventional magnetic resonance imaging (MRI). Damage to white matter, caused by diffuse axonal injury or secondary chemical processes such as excitotoxicity, may not be visible on these scans. Our team uses diffusion MRI (dMRI) and network theory to characterize brain networks in individuals with mTBI, exploring structural connectomics as an indicator of cognitive outcomes by extracting quantitative measures of brain connectivity. We aim to track changes in network organization and cognitive function over time in individuals with mTBI compared to healthy controls, using machine learning and statistical methods to evaluate the predictive value of these network metrics for recovery and decline.<\/p>\n<ul>\n<li>\n<p class=\"heading-title\"><a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/22305988\/\">Circular representation of human cortical networks for subject and population-level connectomic visualization<\/a><\/p>\n<\/li>\n<li>\n<p class=\"heading-title\"><a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/22616011\/\">Mapping connectivity damage in the case of Phineas Gage<\/a><\/p>\n<\/li>\n<\/ul>\n<p>[\/vc_column_text][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>[vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;566&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text css=&#8221;&#8221;] Brain age [\/vc_column_text][vc_column_text css=&#8221;&#8221;] In recent years, biological age has emerged as a useful metric for quantifying how an individual\u2019s brain deviates from typical aging trajectories. The difference between an individual\u2019s chronological age and predicted brain age, termed the brain age gap, is widely used as a marker of [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":567,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-full.php","meta":{"_acf_changed":false,"footnotes":""},"class_list":["post-81","page","type-page","status-publish","has-post-thumbnail","hentry"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Research - The Irimia Lab<\/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:\/\/gero.usc.edu\/labs\/irimialab\/research\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Research - The Irimia Lab\" \/>\n<meta property=\"og:description\" content=\"[vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;566&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text css=&#8221;&#8221;] Brain age [\/vc_column_text][vc_column_text css=&#8221;&#8221;] In recent years, biological age has emerged as a useful metric for quantifying how an individual\u2019s brain deviates from typical aging trajectories. The difference between an individual\u2019s chronological age and predicted brain age, termed the brain age gap, is widely used as a marker of [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/\" \/>\n<meta property=\"og:site_name\" content=\"The Irimia Lab\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-21T23:12:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/gero.usc.edu\/labs\/irimialab\/files\/2022\/05\/connectivity-tbi.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1378\" \/>\n\t<meta property=\"og:image:height\" content=\"862\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/\",\"url\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/\",\"name\":\"Research - The Irimia Lab\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/files\\\/2022\\\/05\\\/connectivity-tbi.png\",\"datePublished\":\"2018-03-14T20:48:48+00:00\",\"dateModified\":\"2026-04-21T23:12:19+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/#primaryimage\",\"url\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/files\\\/2022\\\/05\\\/connectivity-tbi.png\",\"contentUrl\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/files\\\/2022\\\/05\\\/connectivity-tbi.png\",\"width\":1378,\"height\":862,\"caption\":\"Brain diagram\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/research\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/#website\",\"url\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/\",\"name\":\"The Irimia Lab\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/gero.usc.edu\\\/labs\\\/irimialab\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Research - The Irimia Lab","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:\/\/gero.usc.edu\/labs\/irimialab\/research\/","og_locale":"en_US","og_type":"article","og_title":"Research - The Irimia Lab","og_description":"[vc_row][vc_column width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;566&#8243; img_size=&#8221;full&#8221;][\/vc_column][vc_column width=&#8221;1\/2&#8243;][vc_column_text css=&#8221;&#8221;] Brain age [\/vc_column_text][vc_column_text css=&#8221;&#8221;] In recent years, biological age has emerged as a useful metric for quantifying how an individual\u2019s brain deviates from typical aging trajectories. The difference between an individual\u2019s chronological age and predicted brain age, termed the brain age gap, is widely used as a marker of [&hellip;]","og_url":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/","og_site_name":"The Irimia Lab","article_modified_time":"2026-04-21T23:12:19+00:00","og_image":[{"width":1378,"height":862,"url":"https:\/\/gero.usc.edu\/labs\/irimialab\/files\/2022\/05\/connectivity-tbi.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/","url":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/","name":"Research - The Irimia Lab","isPartOf":{"@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/#website"},"primaryImageOfPage":{"@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/#primaryimage"},"image":{"@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/#primaryimage"},"thumbnailUrl":"https:\/\/gero.usc.edu\/labs\/irimialab\/files\/2022\/05\/connectivity-tbi.png","datePublished":"2018-03-14T20:48:48+00:00","dateModified":"2026-04-21T23:12:19+00:00","breadcrumb":{"@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/gero.usc.edu\/labs\/irimialab\/research\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/#primaryimage","url":"https:\/\/gero.usc.edu\/labs\/irimialab\/files\/2022\/05\/connectivity-tbi.png","contentUrl":"https:\/\/gero.usc.edu\/labs\/irimialab\/files\/2022\/05\/connectivity-tbi.png","width":1378,"height":862,"caption":"Brain diagram"},{"@type":"BreadcrumbList","@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/research\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/gero.usc.edu\/labs\/irimialab\/"},{"@type":"ListItem","position":2,"name":"Research"}]},{"@type":"WebSite","@id":"https:\/\/gero.usc.edu\/labs\/irimialab\/#website","url":"https:\/\/gero.usc.edu\/labs\/irimialab\/","name":"The Irimia Lab","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/gero.usc.edu\/labs\/irimialab\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/pages\/81","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/comments?post=81"}],"version-history":[{"count":20,"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/pages\/81\/revisions"}],"predecessor-version":[{"id":1884,"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/pages\/81\/revisions\/1884"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/media\/567"}],"wp:attachment":[{"href":"https:\/\/gero.usc.edu\/labs\/irimialab\/wp-json\/wp\/v2\/media?parent=81"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}