{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T12:08:55Z","timestamp":1793275735751,"version":"4.5.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009379","name":"Interdisziplin\u00e4res Zentrum f\u00fcr Klinische Forschung, Universit\u00e4tsklinikum W\u00fcrzburg","doi-asserted-by":"publisher","award":["Z-3BC\/17"],"award-info":[{"award-number":["Z-3BC\/17"]}],"id":[{"id":"10.13039\/501100009379","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011699","name":"Siemens Healthineers","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/501100011699","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Insights Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To evaluate the performance of an optimized deep-learning-based algorithm (AI) for the detection and subtyping of intracranial hemorrhage (ICH) in non-contrast cranial CT (cCT).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>CCTs performed between 2020 and 2022 were processed using a pre-trained 3D-neural-AI to detect ICH. The current version was compared to the initial version (ICH) and the radiological report (ICH, subtypes) regarding diagnostic accuracy. A consensus of the radiological report and an additional reading by a radiologist (7 years of experience) served as the ground truth. We investigated the AI-generated confidence score as a threshold for clinical usage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In the total cohort of 2960 cCTs (ICH prevalence 10.5%), the current AI prototype detected ICH with high sensitivity (93.9%) and specificity (96.1%). This resulted in an accuracy of 95.9% and a negative predictive value (NPV) of 99.3%, including 12 ICH-positive cases that were initially missed by the interpreting radiologists. Subtyping results were comparable between the AI and the radiologists. In the cohort processed with both prototypes (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009996), the results of the current AI were slightly lower (sensitivity 88.3%; accuracy 94.4%; NPV 98.6%), yet it still outperformed those of the initial version (sensitivity 77.7%, accuracy 95.5%, NPV 97.4%), resulting in eight fewer false negatives and eleven additional true positives. A confidence score of 60% was considered a useful threshold, resulting in a significant increase of AUC (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.018).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The current AI algorithm achieves high diagnostic accuracy and negative predictive value. Combining AI-driven analysis with radiologists\u2019 expertise may improve the overall performance and reduce the number of missed ICHs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Critical relevance statement<\/jats:title>\n                    <jats:p>The dual use of AI as a control and triage tool can reduce radiology workload. Our results show AI reliably supports standardized exams with diagnostic quality comparable to radiologists, while transparent output enhances clinical acceptance and integration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Potentially life-threatening intracranial hemorrhages are time-critical and need accurate detection on non-contrast cranial CT.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The optimized algorithm achieved high diagnostic accuracy for ICH detection similar to radiologists.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The combination of radiologists and AI may improve the efficiency and diagnostic quality of ICH detection.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s13244-026-02249-w","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T10:48:36Z","timestamp":1773744516000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Diagnostic performance and confidence of an optimized deep-learning algorithm for the detection of intracranial hemorrhages"],"prefix":"10.1186","volume":"17","author":[{"given":"Franziska","family":"Tombach","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristina","family":"Krompa\u00df","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan-Lucca","family":"Hennes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Weber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan-Peter","family":"Grunz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henner","family":"Huflage","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thorsten Alexander","family":"Bley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julius Frederik","family":"Heidenreich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2565-8111","authenticated-orcid":false,"given":"Philipp","family":"Gruschwitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"2249_CR1","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/s11883-012-0252-1","volume":"14","author":"MA Ikram","year":"2012","unstructured":"Ikram MA, Wieberdink RG, Koudstaal PJ (2012) International epidemiology of intracerebral hemorrhage. Curr Atheroscler Rep 14:300\u2013306","journal-title":"Curr Atheroscler Rep"},{"key":"2249_CR2","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/S1474-4422(09)70340-0","volume":"9","author":"CJ van Asch","year":"2010","unstructured":"van Asch CJ, Luitse MJ, Rinkel GJ, van der Tweel I, Algra A, Klijn CJ (2010) Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: a systematic review and meta-analysis. Lancet Neurol 9:167\u2013176","journal-title":"Lancet Neurol"},{"key":"2249_CR3","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.1161\/STR.0000000000000069","volume":"46","author":"JC Hemphill 3rd","year":"2015","unstructured":"Hemphill JC 3rd, Greenberg SM, Anderson CS et al (2015) Guidelines for the management of spontaneous intracerebral hemorrhage: a guideline for healthcare professionals from the American Heart Association\/American Stroke Association. Stroke 46:2032\u20132060","journal-title":"Stroke"},{"key":"2249_CR4","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1016\/j.acra.2018.07.001","volume":"26","author":"AL Chetlen","year":"2019","unstructured":"Chetlen AL, Chan TL, Ballard DH et al (2019) Addressing burnout in radiologists. Acad Radiol 26:526\u2013533","journal-title":"Acad Radiol"},{"key":"2249_CR5","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1186\/s13244-020-00925-z","volume":"11","author":"RJM Bruls","year":"2020","unstructured":"Bruls RJM, Kwee RM (2020) Workload for radiologists during on-call hours: dramatic increase in the past 15 years. Insights Imaging 11:121","journal-title":"Insights Imaging"},{"key":"2249_CR6","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/j.jacr.2010.03.004","volume":"7","author":"EA Krupinski","year":"2010","unstructured":"Krupinski EA, Berbaum KS, Caldwell RT, Schartz KM, Kim J (2010) Long radiology workdays reduce detection and accommodation accuracy. J Am Coll Radiol 7:698\u2013704","journal-title":"J Am Coll Radiol"},{"key":"2249_CR7","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1148\/radiol.2021203486","volume":"298","author":"J Vosshenrich","year":"2021","unstructured":"Vosshenrich J, Brantner P, Cyriac J, Boll DT, Merkle EM, Heye T (2021) Quantifying radiology resident fatigue: analysis of preliminary reports. Radiology 298:632\u2013639","journal-title":"Radiology"},{"key":"2249_CR8","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s13244-025-01926-6","volume":"16","author":"AP Brady","year":"2025","unstructured":"Brady AP, Loewe C, Brkljacic B et al (2025) Guidelines and recommendations for radiologist staffing, education and training. Insights Imaging 16:57","journal-title":"Insights Imaging"},{"key":"2249_CR9","doi-asserted-by":"publisher","first-page":"2246","DOI":"10.1007\/s00330-021-08352-4","volume":"32","author":"N Schmitt","year":"2022","unstructured":"Schmitt N, Mokli Y, Weyland CS et al (2022) Automated detection and segmentation of intracranial hemorrhage suspect hyperdensities in non-contrast-enhanced CT scans of acute stroke patients. Eur Radiol 32:2246\u20132254","journal-title":"Eur Radiol"},{"key":"2249_CR10","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210168","volume":"4","author":"M Seyam","year":"2022","unstructured":"Seyam M, Weikert T, Sauter A, Brehm A, Psychogios MN, Blackham KA (2022) Utilization of artificial intelligence-based intracranial hemorrhage detection on emergent noncontrast CT images in clinical workflow. Radiol Artif Intell 4:e210168","journal-title":"Radiol Artif Intell"},{"key":"2249_CR11","doi-asserted-by":"crossref","unstructured":"Kiefer J, Kopp M, Ruettinger T et al (2023) Diagnostic accuracy and performance analysis of a scanner-integrated artificial intelligence model for the detection of intracranial hemorrhages in a traumatology emergency department. Bioengineering 10:1362","DOI":"10.3390\/bioengineering10121362"},{"key":"2249_CR12","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210115","volume":"4","author":"E Gibson","year":"2022","unstructured":"Gibson E, Georgescu B, Ceccaldi P et al (2022) Artificial intelligence with statistical confidence scores for detection of acute or subacute hemorrhage on noncontrast CT head scans. Radiol Artif Intell 4:210115","journal-title":"Radiol Artif Intell"},{"key":"2249_CR13","doi-asserted-by":"publisher","first-page":"100005","DOI":"10.1016\/j.neuri.2021.100005","volume":"1","author":"P Gruschwitz","year":"2021","unstructured":"Gruschwitz P, Grunz J, Kuhl P et al (2021) Performance testing of a novel deep learning algorithm for the detection of intracranial hemorrhage and first trial under clinical conditions. Neurosci Inform 1:100005","journal-title":"Neurosci Inform"},{"key":"2249_CR14","doi-asserted-by":"publisher","first-page":"e15154","DOI":"10.2196\/15154","volume":"22","author":"O Asan","year":"2020","unstructured":"Asan O, Bayrak AE, Choudhury A (2020) Artificial intelligence and human trust in healthcare: focus on clinicians. J Med Internet Res 22:e15154","journal-title":"J Med Internet Res"},{"key":"2249_CR15","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1109\/TPAMI.2017.2782687","volume":"41","author":"FC Ghesu","year":"2019","unstructured":"Ghesu FC, Georgescu B, Zheng Y et al (2019) Multi-scale deep reinforcement learning for real-time 3D-landmark detection in CT scans. IEEE Trans Pattern Anal Mach Intell 41:176\u2013189","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2249_CR16","doi-asserted-by":"publisher","unstructured":"Descoteaux M, Maier-Hein L, Franz A, Jannin P, Collins L, Duchesne S (2017) In: Proceedings of the 20th international conference on medical image computing and computer-assisted intervention (MICCAI) 2017, Quebec City, 11\u201313 September 2017, Part I. https:\/\/doi.org\/10.1007\/978-3-319-66182-7","DOI":"10.1007\/978-3-319-66182-7"},{"key":"2249_CR17","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1007\/s00234-025-03560-x","volume":"67","author":"DW Kang","year":"2025","unstructured":"Kang DW, Kim M, Park GH et al (2025) Deep learning-assisted detection of intracranial hemorrhage: validation and impact on reader performance. Neuroradiology 67:1511\u20131519","journal-title":"Neuroradiology"},{"key":"2249_CR18","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1007\/s11547-024-01867-y","volume":"129","author":"T D\u2019Angelo","year":"2024","unstructured":"D\u2019Angelo T, Bucolo GM, Kamareddine T et al (2024) Accuracy and time efficiency of a novel deep learning algorithm for intracranial hemorrhage detection in CT Scans. Radiol Med 129:1499\u20131506","journal-title":"Radiol Med"},{"key":"2249_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-01317-3","volume":"15","author":"SN Ahmed","year":"2025","unstructured":"Ahmed SN, Prakasam P (2025) Intracranial hemorrhage segmentation and classification framework in computer tomography images using deep learning techniques. Sci Rep 15:17151","journal-title":"Sci Rep"},{"key":"2249_CR20","volume":"4","author":"JM Hillis","year":"2024","unstructured":"Hillis JM, Bizzo BC, Newbury-Chaet I et al (2024) Evaluation of an artificial intelligence model for identification of intracranial hemorrhage subtypes on computed tomography of the head. Stroke Vasc Interv Neurol 4:e001223","journal-title":"Stroke Vasc Interv Neurol"},{"key":"2249_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2021.102785","volume":"32","author":"X Wang","year":"2021","unstructured":"Wang X, Shen T, Yang S et al (2021) A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans. Neuroimage Clin 32:102785","journal-title":"Neuroimage Clin"},{"key":"2249_CR22","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1016\/j.jacr.2017.12.019","volume":"15","author":"TN Hanna","year":"2018","unstructured":"Hanna TN, Zygmont ME, Peterson R et al (2018) The effects of fatigue from overnight shifts on radiology search patterns and diagnostic performance. J Am Coll Radiol 15:1709\u20131716","journal-title":"J Am Coll Radiol"},{"key":"2249_CR23","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1007\/s00062-023-01291-1","volume":"33","author":"S Agarwal","year":"2023","unstructured":"Agarwal S, Wood D, Grzeda M et al (2023) Systematic review of artificial intelligence for abnormality detection in high-volume neuroimaging and subgroup meta-analysis for intracranial hemorrhage detection. Clin Neuroradiol 33:943\u2013956","journal-title":"Clin Neuroradiol"},{"key":"2249_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3941\/jrcr.v13i8.3633","volume":"13","author":"C Saade","year":"2019","unstructured":"Saade C, Najem E, Asmar K, Salman R, El Achkar B, Naffaa L (2019) Intracranial calcifications on CT: an updated review. J Radiol Case Rep 13:1\u201318","journal-title":"J Radiol Case Rep"},{"key":"2249_CR25","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1161\/STR.0b013e3182587839","volume":"43","author":"ES Connolly Jr","year":"2012","unstructured":"Connolly ES Jr, Rabinstein AA, Carhuapoma JR et al (2012) Guidelines for the management of aneurysmal subarachnoid hemorrhage: a guideline for healthcare professionals from the American Heart Association\/American Stroke Association. Stroke 43:1711\u20131737","journal-title":"Stroke"}],"container-title":["Insights into Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-026-02249-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13244-026-02249-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13244-026-02249-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:02:39Z","timestamp":1773788559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13244-026-02249-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2249"],"URL":"https:\/\/doi.org\/10.1186\/s13244-026-02249-w","relation":{},"ISSN":["1869-4101"],"issn-type":[{"value":"1869-4101","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"10 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The institutional review board (Ethic Committee of the University of W\u00fcrzburg; protocol number: 20230919 02) approved the retrospective data analysis.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The Ethics Committee waived the requirement for informed consent for anonymized processing of image data by the AI.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The institute has a research partnership with Siemens Healthineers. As part of this partnership, two versions of the algorithm were made available for examination. Study design, data collection, analysis, and publication were carried out in accordance with good scientific practices, with no involvement from the developer. T.A.B. and J.P.G. received speaker honoraria from Siemens Healthineers outside of the presented work. J.P.G. is a member of the Scientific Editorial Board of\n                      Insights into Imaging\n                      (section: Cardiovascular) and, as such, did not participate in the selection or review processes for this article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"73"}}