{"id":19537,"date":"2026-09-24T05:07:39","date_gmt":"2026-09-24T08:07:39","guid":{"rendered":"https:\/\/rtmedical.com.br\/tmp-en-1790237258616\/"},"modified":"2026-09-24T05:07:45","modified_gmt":"2026-09-24T08:07:45","slug":"ai-aria-mri-alzheimers-ajr","status":"publish","type":"post","link":"https:\/\/rtmedical.com.br\/en\/ai-aria-mri-alzheimers-ajr\/","title":{"rendered":"AJR Panel Backs AI for ARIA Detection on Brain MRI"},"content":{"rendered":"

AI tools that detect ARIA on brain MRI<\/strong> in patients receiving anti-amyloid therapy for Alzheimer disease now have enough evidence behind them for clinical use, as long as the radiologist keeps ownership of the report. That is the conclusion of a multidisciplinary panel of neuroradiologists and Alzheimer disease clinicians, published September 16 in the American Journal of Roentgenology<\/em> (AJR). The group recommends conditional<\/strong> implementation: AI as clinical decision support, with the specialist validating every finding in what the authors call a radiologist-in-the-loop framework.<\/p>\n

\"Axial
Every patient on an anti-amyloid antibody goes through several surveillance MRIs in the first year, and that is where AI steps in as a second reader.<\/figcaption><\/figure>\n

Who wrote it and what the panel recommends<\/h2>\n

The paper, an expert opinion article (DOI 10.2214\/AJR.26.35514<\/a>), brings together leading names in dementia neuroimaging: Jeffrey Petrella and P. Murali Doraiswamy (Duke), Frederik Barkhof (UCL and Amsterdam UMC), Tammie Benzinger (Mallinckrodt Institute, Washington University), Petrice Cogswell (Mayo Clinic), Ana Franceschi (Northwell), Marwan Sabbagh (Barrow Neurological Institute), Stephen Salloway (Brown) and Greg Zaharchuk (Stanford). They reviewed how much evidence exists to move these systems into routine practice, how to integrate them safely, and what remains unknown.<\/p>\n

The key points, based on the paper’s abstract and ITN’s coverage:<\/p>\n

Higher sensitivity.<\/strong> Reader performance studies show that AI assistance raises sensitivity by roughly 16 percentage points for ARIA-E<\/strong> and 10 points for ARIA-H<\/strong>, while reducing interreader variability. Slightly lower specificity.<\/strong> The drop ranges from 3 to 9 percentage points; the panel judged that avoiding missed or delayed ARIA outweighs the extra work of reviewing false positives. Radiologist accountability.<\/strong> The final read belongs to the physician, who must check AI output against the full examination and clinical context. Heterogeneous products.<\/strong> The commercial tools named \u2014 icometrix icobrain aria, cortechs.ai NeuroQuant Lesion Surveillance, Neurophet AQUA AD Plus and Qynapse QyScore \u2014 differ substantially in FDA clearance status, technical capabilities and validation evidence. Safeguards.<\/strong> Standardized acquisition protocols, local validation, radiologist training, ongoing quality audits and participation in real-world registries such as ALZ-NET and InRAD.<\/p>\n

Where the 16 and 10 points come from<\/h2>\n

The figures match the largest reader study published on the topic so far: Sima and colleagues in JAMA Network Open<\/a> (2024), a study run by icometrix with Biogen. Sixteen board-certified radiologists read 199 retrospective cases \u2014 each a baseline and a post-dosing MRI from the aducanumab trials PRIME, EMERGE and ENGAGE \u2014 with and without icobrain aria. Sensitivity rose from 71% to 87% for ARIA-E and from 69% to 79% for ARIA-H, while specificity stayed above 80% for both. Assisted area under the curve was 0.87 for ARIA-E and 0.83 for ARIA-H.<\/p>\n

The design matters: trial cases with relatively controlled acquisition protocols, and only 2 of the 16 readers were neuroradiologists. The gain tends to be largest for readers who do not see ARIA every day \u2014 which is both the argument for the tool and a limit on extrapolating the result to specialized centers.<\/p>\n

Why ARIA is a volume problem<\/h2>\n

Lecanemab and donanemab, monoclonal antibodies against amyloid beta, slow cognitive decline in early Alzheimer disease to a clinically meaningful degree. The trade-off is ARIA in two forms. ARIA-E<\/strong> is vasogenic edema or sulcal effusion, seen as FLAIR hyperintensity. ARIA-H<\/strong> covers microhemorrhages and superficial siderosis, identified on susceptibility-weighted sequences (T2* GRE or SWI). Most episodes are asymptomatic and occur in the first months of treatment, with higher risk in APOE \u03b54 homozygotes.<\/p>\n

That is why the drug labels require a baseline MRI and scheduled surveillance MRIs before specific early infusions, plus imaging whenever symptoms appear. Radiographic severity \u2014 defined by the extent of edema or the microhemorrhage count \u2014 drives the decision to pause, resume or stop therapy. This is a comparative read with direct therapeutic consequences, not an incidental finding.<\/p>\n

The panel estimated that if 10% of U.S. patients with mild cognitive impairment or early Alzheimer dementia are treated, monitoring would generate 7 to 8 million additional MRI exams<\/strong>. That volume, combined with how subtle punctate microhemorrhages and small sulcal effusions can be, is the classic recipe for fatigue, interreader variability and missed findings \u2014 exactly where detection and longitudinal quantification algorithms tend to pay off.<\/p>\n

What changes for imaging departments<\/h2>\n

The recommendation is not simply “buy software.” The panel sets preconditions that depend on each site. First, protocol: without standardized FLAIR and susceptibility sequences between baseline and follow-up, no algorithm compares well \u2014 and neither does the radiologist. Second, local validation, because performance on clinical trial data does not guarantee performance on a given site’s scanner fleet. Third, auditing: tracking agreement between AI and final report, false-positive rates and missed cases over time.<\/p>\n

The move tracks the regulatory trend. Radiology accounts for most AI-enabled devices authorized by the FDA, as we reported in Radiology Holds 76% of FDA AI Authorizations<\/a>. Dementia neuroimaging is also going through a biomarker expansion, from the FDA approval of Lantheus’ tau PET agent<\/a> to MRI techniques such as MR-AIV, which maps brain fluid flow with AI<\/a>.<\/p>\n

For Brazil and Latin America, the discussion is timely. With donanemab registered by Brazil’s regulator Anvisa in 2025, centers starting to treat patients will need a reliable surveillance MRI workflow, often outside dedicated neuroradiology centers. That is precisely the setting where AI assistance showed the largest sensitivity gain. Local availability of these tools, their regulatory status and their validation on regional scanners and protocols still need to be checked case by case.<\/p>\n

Limitations and what remains to be proven<\/h2>\n

The panel itself acknowledges the gaps. Current evidence measures reading accuracy, not clinical outcomes: it is still unknown whether detecting more mild, asymptomatic ARIA changes patient trajectories or simply increases dose suspensions. Reader studies come mostly from trial data, often manufacturer-funded, and from aducanumab rather than the antibodies now in use. The loss of specificity, small in percentage terms, can add up at scale: across millions of exams, a few points mean a lot of alerts to review.<\/p>\n

That is why the paper calls for prospective studies on outcomes and long-term care, and for feeding registries such as ALZ-NET. “AI-assisted ARIA detection is likely to enhance patient safety when used as clinical decision support within a radiologist-in-the-loop framework,” the authors conclude. Until outcome data arrive, the recommendation is pragmatic: use it, but measure it.<\/p>\n

Source:<\/strong> ITN (Imaging Technology News)<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

An AJR expert panel supports AI decision support for ARIA on MRI during anti-amyloid therapy: +16 points sensitivity for ARIA-E, radiologist in control.<\/p>\n","protected":false},"author":1,"featured_media":19485,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"ngg_post_thumbnail":0,"_rt_cluster":"","fifu_image_url":"","fifu_image_alt":"","footnotes":""},"categories":[102,100],"tags":[],"class_list":["post-19537","post","type-post","status-publish","format-standard","has-post-thumbnail","category-ai","category-radiology"],"aioseo_notices":[],"rt_seo":{"title":"","description":"An AJR expert panel supports AI decision support for ARIA on MRI during anti-amyloid therapy: +16 points sensitivity for ARIA-E, radiologist in control.","canonical":"","og_image":"","robots":"index,follow","schema_type":"Article","include_in_llms":true,"llms_label":"AI for ARIA detection on MRI during anti-amyloid therapy","llms_summary":"An AJR expert panel (Petrella, Barkhof, Benzinger et al., Sept 2026) supports conditional use of AI clinical decision support to detect ARIA-E and ARIA-H on MRI in patients on lecanemab\/donanemab, with a radiologist in the loop. Sensitivity +16 pp (ARIA-E) and +10 pp (ARIA-H), specificity -3 to -9 pp; 7-8 million extra US MRIs projected; tools include icobrain aria, NeuroQuant, Neurophet AQUA and QyScore.","faq_items":[],"video":[],"gtin":"","mpn":"","brand":"","aggregate_rating":[]},"_links":{"self":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/19537\/"}],"collection":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/"}],"about":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/types\/post\/"}],"author":[{"embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/users\/1\/"}],"replies":[{"embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/comments\/?post=19537"}],"version-history":[{"count":1,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/19537\/revisions\/"}],"predecessor-version":[{"id":19539,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/posts\/19537\/revisions\/19539\/"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/media\/19485\/"}],"wp:attachment":[{"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/media\/?parent=19537"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/categories\/?post=19537"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rtmedical.com.br\/en\/wp-json\/wp\/v2\/tags\/?post=19537"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}