{"id":1097,"date":"2026-07-18T04:17:50","date_gmt":"2026-07-18T04:17:50","guid":{"rendered":"https:\/\/valutednews.com\/?p=1097"},"modified":"2026-07-18T04:17:50","modified_gmt":"2026-07-18T04:17:50","slug":"ai-tool-flags-six-acute-abdominal-emergencies-on-ct","status":"publish","type":"post","link":"https:\/\/valutednews.com\/?p=1097","title":{"rendered":"AI Tool Flags Six Acute Abdominal Emergencies on CT"},"content":{"rendered":"<div style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/img.medscapestatic.com\/vim\/live\/professional_assets\/medscape\/images\/thumbnail_library\/gty-260713-abdominal-ct-scan-800x450.jpg\" class=\"attachment-post-thumbnail size-post-thumbnail wp-post-image\" alt=\"AI Tool Flags Six Acute Abdominal Emergencies on CT\" title=\"AI Tool Flags Six Acute Abdominal Emergencies on CT\" \/><\/div><p><\/p>\n<div id=\"article-body_2026a1000nwm\">\n<div>\n<h2>TOPLINE<\/h2>\n<p>An AI system identified six acute abdominal emergencies on CT scans using a multiwindow Hounsfield unit (HU) encoding approach and localised the detected pathology to the clinically appropriate abdominal region with 99.5% accuracy, a study showed.<\/p>\n<h2>METHODOLOGY<\/h2>\n<ul>\n<li data-list-item-id=\"e7028b4c26f4f11d42fc54b7dd7c1eff9\">Researchers developed and retrospectively analysed a deep learning system trained and internally validated on a patient-level split of a teleradiology dataset comprising 1274 patients with 42,922 bounding box annotations.<\/li>\n<li data-list-item-id=\"ec502deb6d2bdc800cc678f9e5e0e4ce7\">Each CT slice was encoded into three diagnostic HU windows mapped to separate image channels (centre\/width in HU): soft tissue (50\/400), bone\/stone (500\/1600), and angio\/liver (60\/150).<\/li>\n<li data-list-item-id=\"e6ef4f8f248c1958f08ad829c7312ad93\">A &#8220;YOLOv11-Large&#8221; model with an added stride-4 head was trained at a high resolution of 1280 \u00d7 1280 pixels to preserve fine soft tissue details, evaluating the area under the receiver operating characteristic curve (AUROC) and macro F1 scores.<\/li>\n<li data-list-item-id=\"ed5751fb1b268e30b7a9760f049a81da7\">The model was trained to detect six acute abdominal emergencies: <a href=\"https:\/\/emedicine.medscape.com\/article\/1979501-overview\" class=\"cl_ref_article\">abdominal aortic aneurysm<\/a>, <a href=\"https:\/\/emedicine.medscape.com\/article\/181364-overview\" class=\"cl_ref_article\">acute pancreatitis<\/a>, <a href=\"https:\/\/emedicine.medscape.com\/article\/171886-overview\" class=\"cl_ref_article\">acute cholecystitis<\/a>, kidney and ureter stones, acute <a href=\"https:\/\/emedicine.medscape.com\/article\/173388-overview\" class=\"cl_ref_article\">diverticulitis<\/a>, and <a href=\"https:\/\/emedicine.medscape.com\/article\/773895-overview\" class=\"cl_ref_article\">acute appendicitis<\/a>.<\/li>\n<li data-list-item-id=\"eb323f92a218a4d8a95a56734077ba58e\">The researchers mapped anatomic localisations to a clinical nine-region abdominal grid and validated the system using a radiologist-adjudicated 280-patient Stanford Merlin cohort.<\/li>\n<\/ul>\n<h2>TAKEAWAY<\/h2>\n<ul>\n<li data-list-item-id=\"e06643df0998739f7b60e15d85717e318\">The system achieved a high macro AUROC of 0.941 across all six conditions, with abdominal aortic aneurysm achieving the highest at 0.998 and acute appendicitis achieving the lowest at 0.880; the macro F1 score was 76.1%.<\/li>\n<li data-list-item-id=\"e962c1b1e268beb113fa28e83ed11e6ca\">On external validation, all the six classes maintained an AUROC \u2265 0.80, and macro F1 was 0.545 at unmodified thresholds, increasing to 0.648 after site-specific recalibration.<\/li>\n<li data-list-item-id=\"e3d5b943cbe5573461bbfbe3f41102ef4\">Anatomic localisation to the correct abdominal region was 99.5% accurate among detected cases and 90.9% accurate when factoring in missed detections (199\/219 patient-pathology pairs).<\/li>\n<li data-list-item-id=\"e5affc29faa31a5e2b92e321de222dd84\">Among 80 target-negative patients, the specificity was 86.2%, with 11 patients incorrectly flagged for at least one acute finding, representing a 13.8% per-patient false-positive rate.<\/li>\n<\/ul>\n<h2>IN PRACTICE<\/h2>\n<p>&#8220;[The study] findings suggest that a region-aware multi-pathology CT triage system may provide clinically interpretable decision support, although prospective validation integrated with a picture archiving and communication system (PACS) remains necessary before clinical use,&#8221; the authors wrote.<\/p>\n<p>They added that the tool&#8217;s &#8220;layered output is important for emergency CT triage because the radiologist needs both an indication that an abnormality may be present and a rapid sense of where to look and how the finding relates to the clinical presentation.&#8221;<\/p>\n<h2>SOURCE<\/h2>\n<p>The study was led by Hasan Mete Erdo\u011fan, Budapest University of Technology and Economics, Budapest, Hungary. It was <a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02084-x\" rel=\"nofollow\" target=\"_blank\">published online<\/a> on July 08, 2026, in the <em>Journal of Imaging Informatics in Medicine<\/em>.<\/p>\n<h2>LIMITATIONS<\/h2>\n<p>The internal dataset was obtained from a single national teleradiology network. Retrospective external validation was performed using a single US dataset, and external adjudication was performed by a single radiologist. Furthermore, this study was limited by the absence of external bounding box annotations, the unavailability of contrast phase metadata, a two-dimensional per-slice detector design, and the lack of multireader radiologist comparisons.<\/p>\n<h2>DISCLOSURES<\/h2>\n<p>This research did not receive any external funding. Open access funding was provided by the Budapest University of Technology and Economics. The authors reported having no conflicts of interest.<\/p>\n<p><em>This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication.<\/em><\/p>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>TOPLINE An AI system identified six acute abdominal emergencies on CT scans using a multiwindow Hounsfield unit (HU) encoding approach and localised the detected pathology to the clinically appropriate abdominal region with 99.5% accuracy, a study showed. METHODOLOGY Researchers developed and retrospectively analysed a deep learning system trained and internally validated on a patient-level split&#8230;<\/p>\n","protected":false},"author":1,"featured_media":1098,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/img.medscapestatic.com\/vim\/live\/professional_assets\/medscape\/images\/thumbnail_library\/gty-260713-abdominal-ct-scan-800x450.jpg","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[2220,2219,2221,2218,2217],"class_list":["post-1097","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-health","tag-abdominal","tag-acute","tag-emergencies","tag-flags","tag-tool"],"_links":{"self":[{"href":"https:\/\/valutednews.com\/index.php?rest_route=\/wp\/v2\/posts\/1097","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/valutednews.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/valutednews.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/valutednews.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/valutednews.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1097"}],"version-history":[{"count":0,"href":"https:\/\/valutednews.com\/index.php?rest_route=\/wp\/v2\/posts\/1097\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/valutednews.com\/index.php?rest_route=\/wp\/v2\/media\/1098"}],"wp:attachment":[{"href":"https:\/\/valutednews.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1097"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/valutednews.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1097"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/valutednews.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1097"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}