{"id":6027,"date":"2025-11-13T14:21:37","date_gmt":"2025-11-13T03:21:37","guid":{"rendered":"https:\/\/harrison.ai\/?p=6027"},"modified":"2026-02-23T20:18:31","modified_gmt":"2026-02-23T09:18:31","slug":"harrison-rad-1-is-open","status":"publish","type":"post","link":"https:\/\/harrison.ai\/harrison-rad-1-is-open\/","title":{"rendered":"Harrison.rad.1 is Open: Test, Challenge and Explore Our Radiology Foundation Model Today"},"content":{"rendered":"    <section id=\"heading-link-color-block_85a73b4c255e30ad529ac281e0f8f5b0\" class=\"case-block case-block--space pb-0 padding-sm  bg-white text-\" >\n        <div class=\"container  container--alt\">\n            <div class=\"case__holder\">\n                                    <div class=\"case__left\">\n                        <div class=\"case__card bg-navy text-white\">\n                            <h2 class=\"h4 ls-0\" data-aos=\"fade-up\">Experience Harrison.rad.1 today.<\/h2>                            <div class=\"text b2\" data-aos=\"fade-up\"><p>Explore what&#8217;s possible when foundation models are purpose-built for radiology.<\/p>\n<\/div>                                                            <div class=\"case__btn\" data-aos=\"fade-up\">\n                                    <a class=\"btn text-white font-rules btn--secondary\" href=\"https:\/\/chat.harrison.ai\/\" target=\"_blank\">Access now <span class=\"icon-arrow-right-up\"><\/span><\/a>\n                                <\/div>\n                                                    <\/div>\n                    <\/div>\n                    <div class=\"case__right\">\n                        <div class=\"case__img\"><img decoding=\"async\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-460x294.png\" class=\"attachment-medium size-medium\" alt=\"\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-460x294.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-1024x655.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-768x491.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm.png 1381w\" sizes=\"(max-width: 460px) 100vw, 460px\" \/><\/div>                    <\/div>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"news-content-2-block-block_95dbc3e7662f3cc05531ccf5ee63b0ae\" class=\"content-block content-block--alt padding-sm none text-\" >\n        <div class=\"container  container--tab\">\n            <div class=\"content b1 detail\" data-aos=\"fade-up\">\n                                <p>With increasing challenges from rising imaging volumes, workforce shortages and growing complexity of medical images, specialised capabilities from foundation models have the potential to accelerate development of tools to scale global healthcare.<\/p>\n<p>Dr. Jarrel Seah, Harrison.ai Chief Medical &amp; AI Officer, poses a question at Launch Day 2025:<\/p>\n<p>\u201cWhat if, instead of building individual algorithms for every finding, every X-ray modality, every clinical question, we built one foundation model that could understand all of these?&#8221;<\/p>\n<p>That model is Harrison.rad.1.<\/p>\n<p>Watch this exclusive Launch Day 2025 clip, as Dr. Seah walks through Harrison.rad.1\u2019s performance in real-world challenges, and demonstrates the radiology LLM in action.<\/p>\n<p>&nbsp;<\/p>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"news-media-block-block_ee3167206b5ceb081a95514152cd9635\" class=\"graphic-block   text-graphic-block--alt video-block\" >\n        <div class=\"container  container-fluid\">\n                            <div class=\"location__decor hide-sm\">\n                    <span class=\"pixel-decor pixel-decor-single\" style=\"background-color: rgba(255, 255, 255, 1)\"><\/span>\n                    <span class=\"pixel-decor-multiple\">\n                        <span class=\"pixel-decor\" style=\"background-color: rgba(255, 255, 255, 1)\"><\/span>\n                        <span class=\"pixel-decor\" style=\"background-color: rgba(9, 114, 241, 1)\"><\/span>\n                    <\/span>\n                    <span class=\"pixel-decor pixel-decor-single\" style=\"background-color: rgba(112, 212, 252, 1)\"><\/span>\n                <\/div>\n                                    \n                                    <div class=\"video__holder\" data-aos=\"fade-up\" data-video>\n                        <a href=\"#\" class=\"video__link\" data-video-link>\n                            <div class=\"image-placeholder\">\n                                <img decoding=\"async\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-Launch-Day-Video-Thumbnail.png\" class=\"attachment-full size-full\" alt=\"\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-Launch-Day-Video-Thumbnail.png 1784w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-Launch-Day-Video-Thumbnail-460x257.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-Launch-Day-Video-Thumbnail-1024x572.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-Launch-Day-Video-Thumbnail-768x429.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-Launch-Day-Video-Thumbnail-1536x858.png 1536w\" sizes=\"(max-width: 1784px) 100vw, 1784px\" \/>                            <\/div>\n                            <svg fill=\"currentColor\" class=\"play\" version=\"1.1\" id=\"Layer_1\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" x=\"0px\" y=\"0px\"\n                                viewBox=\"0 0 60 67.9\" style=\"enable-background:new 0 0 60 67.9;\" xml:space=\"preserve\">\n                            <g>\n                                <path d=\"M8,8l44,25.9l-6.6,3.9L8,59.9C8,59.9,8,8.9,8,8 M8,0C6.6,0,5.3,0.4,4,1.1C1.5,2.5,0,5.1,0,8v51.9c0,2.9,1.5,5.5,4,6.9\n                                    c1.2,0.7,2.6,1.1,4,1.1c1.4,0,2.8-0.4,4.1-1.1l37.4-22.1l6.6-3.9c2.4-1.4,3.9-4.1,3.9-6.9c0-2.8-1.5-5.5-3.9-6.9l-44-25.9\n                                    C10.8,0.4,9.4,0,8,0L8,0z\"\/>\n                            <\/g>\n                            <\/svg>\n\n                            <iframe loading=\"lazy\"\n                                src=\"https:\/\/player.vimeo.com\/video\/1136409886\"\n                                width=\"640\"\n                                height=\"360\"\n                                frameborder=\"0\"\n                                allow=\"autoplay; fullscreen; picture-in-picture\"\n                                allowfullscreen>\n                            <\/iframe>\n                        <\/a>\n                    <\/div>\n                                            <!-- <\/div> -->\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"news-content-2-block-block_b8a20d48b36b7d6512d9c30360e66860\" class=\"content-block content-block--alt py-0 padding-sm py-0 text-\" >\n        <div class=\"container  container--tab\">\n            <div class=\"content b1 detail\" data-aos=\"fade-up\">\n                                                                <div class=\"section-small-text\">\n                    <p><em>Disclaimer: <\/em><em>Harrison.rad.1 is available for research use only. It is not intended for clinical use, which includes directly or indirectly in the diagnosis of disease or other conditions, or in the cure, mitigation, monitoring, treatment, or prevention of disease.<\/em><\/p>\n                <\/div>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"heading-link-color-block_55f855cdc9db2cd07d59c28249f5242f\" class=\"case-block case-block--space pb-0 padding-sm  bg-white text-\" >\n        <div class=\"container  container--alt\">\n            <div class=\"case__holder\">\n                                    <div class=\"case__left\">\n                        <div class=\"case__card bg-navy text-white\">\n                            <h2 class=\"h4 ls-0\" data-aos=\"fade-up\">Demo Harrison.rad.1 with us.<\/h2>                                                                                        <div class=\"case__btn\" data-aos=\"fade-up\">\n                                    <a class=\"btn text-white font-rules btn--secondary\" href=\"https:\/\/harrison.ai\/sales-enquiry\/\" target=\"_blank\">Book a demo <span class=\"icon-arrow-right-up\"><\/span><\/a>\n                                <\/div>\n                                                    <\/div>\n                    <\/div>\n                    <div class=\"case__right\">\n                        <div class=\"case__img\"><img decoding=\"async\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-460x294.png\" class=\"attachment-medium size-medium\" alt=\"\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-460x294.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-1024x655.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-768x491.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm.png 1381w\" sizes=\"(max-width: 460px) 100vw, 460px\" \/><\/div>                    <\/div>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"news-content-2-block-block_e1d3e7d561a54e6bd02730feb984075e\" class=\"content-block content-block--alt py-0 padding-sm py-0 text-\" >\n        <div class=\"container  container--tab\">\n            <div class=\"content b1 detail\" data-aos=\"fade-up\">\n                                <p>&nbsp;<\/p>\n<h5><strong>Putting Harrison.rad.1 to the Test<\/strong><\/h5>\n<p>\u201cFoundation models need to be tested, not just promised,\u201d Dr. Jarrel Seah highlighted.<\/p>\n<p>When we introduced it, we benchmarked it to some common industry standards. Harrison.rad.1 achieved a score of 51.40 on the FRCR 2B Rapids exam, the same credentialing exam taken by radiologists in the UK. Jarrel noted, \u201cThat exceeds the average performance of human radiologists retaking that exam within a year of passing.\u201d<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-6053\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/FRCR-Rapids-2B-Score.png\" alt=\"\" width=\"1781\" height=\"996\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/FRCR-Rapids-2B-Score.png 1781w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/FRCR-Rapids-2B-Score-460x257.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/FRCR-Rapids-2B-Score-1024x573.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/FRCR-Rapids-2B-Score-768x429.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/FRCR-Rapids-2B-Score-1536x859.png 1536w\" sizes=\"auto, (max-width: 1781px) 100vw, 1781px\" \/><\/p>\n<p>But real-world results matter most.<\/p>\n<p>In May 2025, Mass General Brigham AI Arena and the American College of Radiology ran an <a href=\"https:\/\/healthcareaichallenge.org\/ai-results\/\" target=\"_blank\" rel=\"noopener\">independent challenge<\/a> at the ACR Annual Meeting.<\/p>\n<p>The question: could board-certified radiologists tell the difference between AI-generated and human-written reports?<\/p>\n<ul>\n<li>113 radiologist<\/li>\n<li>2,840 blinded evaluations<\/li>\n<\/ul>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-6034 size-full\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-AI-Challenge-e1763014958616.png\" alt=\"\" width=\"1870\" height=\"760\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-AI-Challenge-e1763014958616.png 1870w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-AI-Challenge-e1763014958616-460x187.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-AI-Challenge-e1763014958616-1024x416.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-AI-Challenge-e1763014958616-768x312.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Rad.1-AI-Challenge-e1763014958616-1536x624.png 1536w\" sizes=\"auto, (max-width: 1870px) 100vw, 1870px\" \/><\/p>\n<p>The results: reports powered by Harrison.rad.1 achieved a 65.4% acceptability rate, compared to 79.6% for radiologist-written reports.<\/p>\n<p>Reflecting on the real-world challenge, Jarrel noted, \u201cMass General Brigham AI Arena said that these results show that draft reporting AI is improving at breakneck speed and is closer than ever to meaningfully enhancing radiologist efficiency.\u201d<img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-6035 size-full\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/MGB-AI-Challenge-Results-e1763026857622.png\" alt=\"\" width=\"1774\" height=\"880\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/MGB-AI-Challenge-Results-e1763026857622.png 1774w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/MGB-AI-Challenge-Results-e1763026857622-460x228.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/MGB-AI-Challenge-Results-e1763026857622-1024x508.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/MGB-AI-Challenge-Results-e1763026857622-768x381.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/MGB-AI-Challenge-Results-e1763026857622-1536x762.png 1536w\" sizes=\"auto, (max-width: 1774px) 100vw, 1774px\" \/><\/p>\n<h5><strong>Why Harrison.rad.1 Performs So Well<\/strong><\/h5>\n<p>The key lies in the data. <a href=\"https:\/\/harrison.ai\/radiology-foundation-model\/\">Harrison.rad.1<\/a> is built on millions of DICOM images, radiologist annotations, and structured reports spanning all X-ray modalities.<\/p>\n<p>Jarrel explained, \u201cWhy does Harrison.rad.1 perform at this level? Well, it comes down to comprehensive training data. This model leverages the same high-quality radiology data sets that power our Harrison.ai clinical decision support tools.\u201d<\/p>\n<p>&#8220;The most comprehensive detection algorithms on the market are now powering, the most promising foundation model for radiology reporting. And that&#8217;s not a coincidence,&#8221; Jarrel added.<\/p>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"news-content-2-block-block_cb5271feee43845caf0c5a831590ae17\" class=\"content-block content-block--alt pt-0 padding-md pt-0 text-\" >\n        <div class=\"container  container--tab\">\n            <div class=\"content b1 detail\" data-aos=\"fade-up\">\n                                <h5><strong>See It in Action: Collaborate, Validate, Innovate<\/strong><\/h5>\n<p>\u201cWe believe the field advances fastest when researchers can validate, test, and push these models forward,\u201d Jarrel explained. That\u2019s why Harrison.rad.1 is now available for:<\/p>\n<ul>\n<li>Benchmarking and validation studies<\/li>\n<li>Clinical trials and workflow integration testing<\/li>\n<li>Safety and reliability research<\/li>\n<\/ul>\n<p>\u201cIf you\u2019re working on radiology AI benchmarks, multimodal foundation models, or clinical validation studies, we want to work with you,\u201d Jarrel added.<\/p>\n<p>Harrison.rad.1 is available today. \u201cTry it, test it, challenge it. Help us make it better,\u201d said Jarrel.<\/p>\n<p><a href=\"https:\/\/harrison.ai\/events\/rsna-2025\/\" target=\"_blank\" rel=\"noopener\">Book a demo<\/a> with our team at RSNA to see Harrison.rad.1 in action.<\/p>\n<p>&nbsp;<\/p>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n    <section id=\"heading-link-color-block_4b4d950c7138f8a6cbe9aa126ab0ad0d\" class=\"case-block case-block--space py-0 padding-sm  bg-white text-\" >\n        <div class=\"container  container--alt\">\n            <div class=\"case__holder\">\n                                    <div class=\"case__left\">\n                        <div class=\"case__card bg-navy text-white\">\n                            <h2 class=\"h4 ls-0\" data-aos=\"fade-up\">Experience Harrison.rad.1.<\/h2>                            <div class=\"text b2\" data-aos=\"fade-up\"><p>Explore what&#8217;s possible when foundation models are purpose-built for radiology.<\/p>\n<\/div>                                                            <div class=\"case__btn\" data-aos=\"fade-up\">\n                                    <a class=\"btn text-white font-rules btn--secondary\" href=\"https:\/\/chat.harrison.ai\/\" target=\"_blank\">Access now <span class=\"icon-arrow-right-up\"><\/span><\/a>\n                                <\/div>\n                                                    <\/div>\n                    <\/div>\n                    <div class=\"case__right\">\n                        <div class=\"case__img\"><img decoding=\"async\" src=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-460x294.png\" class=\"attachment-medium size-medium\" alt=\"\" srcset=\"https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-460x294.png 460w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-1024x655.png 1024w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm-768x491.png 768w, https:\/\/harrison.ai\/wp-content\/uploads\/2025\/11\/Screenshot-2025-11-13-at-5.15.42-pm.png 1381w\" sizes=\"(max-width: 460px) 100vw, 460px\" \/><\/div>                    <\/div>\n                \n            <\/div>\n        <\/div>\n    <\/section>\n\n\n\n\n\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":7,"featured_media":5863,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[45,30],"tags":[],"region":[],"product":[],"class_list":["post-6027","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blogs","category-webinar"],"acf":[],"_links":{"self":[{"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/posts\/6027","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/comments?post=6027"}],"version-history":[{"count":60,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/posts\/6027\/revisions"}],"predecessor-version":[{"id":6277,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/posts\/6027\/revisions\/6277"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/media\/5863"}],"wp:attachment":[{"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/media?parent=6027"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/categories?post=6027"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/tags?post=6027"},{"taxonomy":"region","embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/region?post=6027"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/harrison.ai\/wp-json\/wp\/v2\/product?post=6027"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}