Loading…

Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience

To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. Neuroradiologists reviewed 770 CTA images and reported the presence or...

Full description

Saved in:
Bibliographic Details
Published in:World neurosurgery 2024-08, Vol.188, p.e59-e63
Main Authors: De Toledo, Otavio F., Gutierrez-Aguirre, Salvador F., Lara-Velazquez, Montserrat, Qureshi, Adnan I., Camp, Wendy, Erazu, Fernanda, Benalia, Victor H.C., Aghaebrahim, Amin, Sauvageau, Eric, Hanel, Ricardo A.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c237t-91a4bb62a8e38b899711eab6be0c9b9f45bb86145b8a9535b691d3c2ebe4d86e3
container_end_page e63
container_issue
container_start_page e59
container_title World neurosurgery
container_volume 188
creator De Toledo, Otavio F.
Gutierrez-Aguirre, Salvador F.
Lara-Velazquez, Montserrat
Qureshi, Adnan I.
Camp, Wendy
Erazu, Fernanda
Benalia, Victor H.C.
Aghaebrahim, Amin
Sauvageau, Eric
Hanel, Ricardo A.
description To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. Neuroradiologists reviewed 770 CTA images and reported the presence or absence of saccular aneurysms. Subsequently, the images were analyzed by AI software. If the software suspected an aneurysm, it flagged the corresponding image. In cases where there was a mismatch between the radiologist’s report and the AI findings, an expert neurosurgeon evaluated CTA images providing a definitive conclusion on the presence or absence of an aneurysm. AI software flagged 33 cases as potential aneurysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, while in the same group, radiologists identified aneurysms in 28 CTA images. Compared with the radiologist’s report, AI performance had a sensitivity of 36%, specificity of 97.6%, and negative predictive value of 96.2%. There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosurgeon confirmed that 7 of the 17 images showed an aneurysm. In 28 images considered negative by AI, radiologists indicated aneurysms; 17 of those confirmed by the neurosurgeon. AI has the potential to increase the diagnosis of unruptured intracranial aneurysms. However, it must be used as an adjacent tool within the standard of care due to limited applicability in real-world settings.
doi_str_mv 10.1016/j.wneu.2024.05.015
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3054433425</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S187887502400768X</els_id><sourcerecordid>3054433425</sourcerecordid><originalsourceid>FETCH-LOGICAL-c237t-91a4bb62a8e38b899711eab6be0c9b9f45bb86145b8a9535b691d3c2ebe4d86e3</originalsourceid><addsrcrecordid>eNp9kEFPGzEQha2qFUTAH-ih8rGXbO31etdb9RKFUJAicWg5W7Z3tnWaXadjJ8C_x0uAI3N5I_m9J89HyGfOCs54_W1T3I-wL0pWVgWTBePyA5lx1ai5aur249su2Sm5iHHD8gheqUackFORRcpazgjeRaChpwtMvvfOmy29GRNst_4PjA7or9Cne4NAU6CXkMCl6R2NQzNO5kX-BD7GIX6nC7oMww7hL4zRH3I0YfgHdAm5D-nqYQfop85z8qk32wgXL3pG7q5Wv5fX8_Xtz5vlYj13pWjSvOWmsrYujQKhrGrbhnMwtrbAXGvbvpLWqppnUaaVQtq65Z1wJVioOlWDOCNfj707DP_3EJMefHT5NDNC2EctmKwqIapSZmt5tDoMMSL0eod-MPioOdMTbr3RE2494dZM6ow7h7689O_tAN1b5BVuNvw4GiBfefCAOrpnAp3HDFJ3wb_X_wSXupKP</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3054433425</pqid></control><display><type>article</type><title>Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience</title><source>ScienceDirect Freedom Collection</source><creator>De Toledo, Otavio F. ; Gutierrez-Aguirre, Salvador F. ; Lara-Velazquez, Montserrat ; Qureshi, Adnan I. ; Camp, Wendy ; Erazu, Fernanda ; Benalia, Victor H.C. ; Aghaebrahim, Amin ; Sauvageau, Eric ; Hanel, Ricardo A.</creator><creatorcontrib>De Toledo, Otavio F. ; Gutierrez-Aguirre, Salvador F. ; Lara-Velazquez, Montserrat ; Qureshi, Adnan I. ; Camp, Wendy ; Erazu, Fernanda ; Benalia, Victor H.C. ; Aghaebrahim, Amin ; Sauvageau, Eric ; Hanel, Ricardo A.</creatorcontrib><description>To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. Neuroradiologists reviewed 770 CTA images and reported the presence or absence of saccular aneurysms. Subsequently, the images were analyzed by AI software. If the software suspected an aneurysm, it flagged the corresponding image. In cases where there was a mismatch between the radiologist’s report and the AI findings, an expert neurosurgeon evaluated CTA images providing a definitive conclusion on the presence or absence of an aneurysm. AI software flagged 33 cases as potential aneurysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, while in the same group, radiologists identified aneurysms in 28 CTA images. Compared with the radiologist’s report, AI performance had a sensitivity of 36%, specificity of 97.6%, and negative predictive value of 96.2%. There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosurgeon confirmed that 7 of the 17 images showed an aneurysm. In 28 images considered negative by AI, radiologists indicated aneurysms; 17 of those confirmed by the neurosurgeon. AI has the potential to increase the diagnosis of unruptured intracranial aneurysms. However, it must be used as an adjacent tool within the standard of care due to limited applicability in real-world settings.</description><identifier>ISSN: 1878-8750</identifier><identifier>ISSN: 1878-8769</identifier><identifier>EISSN: 1878-8769</identifier><identifier>DOI: 10.1016/j.wneu.2024.05.015</identifier><identifier>PMID: 38735565</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>Aneurysm ; Artificial intelligence ; stroke</subject><ispartof>World neurosurgery, 2024-08, Vol.188, p.e59-e63</ispartof><rights>2024 Elsevier Inc.</rights><rights>Copyright © 2024 Elsevier Inc. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c237t-91a4bb62a8e38b899711eab6be0c9b9f45bb86145b8a9535b691d3c2ebe4d86e3</cites><orcidid>0009-0008-9847-2685 ; 0000-0003-3085-7411 ; 0000-0002-4687-8308 ; 0000-0002-1797-5627</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38735565$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>De Toledo, Otavio F.</creatorcontrib><creatorcontrib>Gutierrez-Aguirre, Salvador F.</creatorcontrib><creatorcontrib>Lara-Velazquez, Montserrat</creatorcontrib><creatorcontrib>Qureshi, Adnan I.</creatorcontrib><creatorcontrib>Camp, Wendy</creatorcontrib><creatorcontrib>Erazu, Fernanda</creatorcontrib><creatorcontrib>Benalia, Victor H.C.</creatorcontrib><creatorcontrib>Aghaebrahim, Amin</creatorcontrib><creatorcontrib>Sauvageau, Eric</creatorcontrib><creatorcontrib>Hanel, Ricardo A.</creatorcontrib><title>Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience</title><title>World neurosurgery</title><addtitle>World Neurosurg</addtitle><description>To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. Neuroradiologists reviewed 770 CTA images and reported the presence or absence of saccular aneurysms. Subsequently, the images were analyzed by AI software. If the software suspected an aneurysm, it flagged the corresponding image. In cases where there was a mismatch between the radiologist’s report and the AI findings, an expert neurosurgeon evaluated CTA images providing a definitive conclusion on the presence or absence of an aneurysm. AI software flagged 33 cases as potential aneurysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, while in the same group, radiologists identified aneurysms in 28 CTA images. Compared with the radiologist’s report, AI performance had a sensitivity of 36%, specificity of 97.6%, and negative predictive value of 96.2%. There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosurgeon confirmed that 7 of the 17 images showed an aneurysm. In 28 images considered negative by AI, radiologists indicated aneurysms; 17 of those confirmed by the neurosurgeon. AI has the potential to increase the diagnosis of unruptured intracranial aneurysms. However, it must be used as an adjacent tool within the standard of care due to limited applicability in real-world settings.</description><subject>Aneurysm</subject><subject>Artificial intelligence</subject><subject>stroke</subject><issn>1878-8750</issn><issn>1878-8769</issn><issn>1878-8769</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kEFPGzEQha2qFUTAH-ih8rGXbO31etdb9RKFUJAicWg5W7Z3tnWaXadjJ8C_x0uAI3N5I_m9J89HyGfOCs54_W1T3I-wL0pWVgWTBePyA5lx1ai5aur249su2Sm5iHHD8gheqUackFORRcpazgjeRaChpwtMvvfOmy29GRNst_4PjA7or9Cne4NAU6CXkMCl6R2NQzNO5kX-BD7GIX6nC7oMww7hL4zRH3I0YfgHdAm5D-nqYQfop85z8qk32wgXL3pG7q5Wv5fX8_Xtz5vlYj13pWjSvOWmsrYujQKhrGrbhnMwtrbAXGvbvpLWqppnUaaVQtq65Z1wJVioOlWDOCNfj707DP_3EJMefHT5NDNC2EctmKwqIapSZmt5tDoMMSL0eod-MPioOdMTbr3RE2494dZM6ow7h7689O_tAN1b5BVuNvw4GiBfefCAOrpnAp3HDFJ3wb_X_wSXupKP</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>De Toledo, Otavio F.</creator><creator>Gutierrez-Aguirre, Salvador F.</creator><creator>Lara-Velazquez, Montserrat</creator><creator>Qureshi, Adnan I.</creator><creator>Camp, Wendy</creator><creator>Erazu, Fernanda</creator><creator>Benalia, Victor H.C.</creator><creator>Aghaebrahim, Amin</creator><creator>Sauvageau, Eric</creator><creator>Hanel, Ricardo A.</creator><general>Elsevier Inc</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0009-0008-9847-2685</orcidid><orcidid>https://orcid.org/0000-0003-3085-7411</orcidid><orcidid>https://orcid.org/0000-0002-4687-8308</orcidid><orcidid>https://orcid.org/0000-0002-1797-5627</orcidid></search><sort><creationdate>20240801</creationdate><title>Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience</title><author>De Toledo, Otavio F. ; Gutierrez-Aguirre, Salvador F. ; Lara-Velazquez, Montserrat ; Qureshi, Adnan I. ; Camp, Wendy ; Erazu, Fernanda ; Benalia, Victor H.C. ; Aghaebrahim, Amin ; Sauvageau, Eric ; Hanel, Ricardo A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c237t-91a4bb62a8e38b899711eab6be0c9b9f45bb86145b8a9535b691d3c2ebe4d86e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Aneurysm</topic><topic>Artificial intelligence</topic><topic>stroke</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>De Toledo, Otavio F.</creatorcontrib><creatorcontrib>Gutierrez-Aguirre, Salvador F.</creatorcontrib><creatorcontrib>Lara-Velazquez, Montserrat</creatorcontrib><creatorcontrib>Qureshi, Adnan I.</creatorcontrib><creatorcontrib>Camp, Wendy</creatorcontrib><creatorcontrib>Erazu, Fernanda</creatorcontrib><creatorcontrib>Benalia, Victor H.C.</creatorcontrib><creatorcontrib>Aghaebrahim, Amin</creatorcontrib><creatorcontrib>Sauvageau, Eric</creatorcontrib><creatorcontrib>Hanel, Ricardo A.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>World neurosurgery</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>De Toledo, Otavio F.</au><au>Gutierrez-Aguirre, Salvador F.</au><au>Lara-Velazquez, Montserrat</au><au>Qureshi, Adnan I.</au><au>Camp, Wendy</au><au>Erazu, Fernanda</au><au>Benalia, Victor H.C.</au><au>Aghaebrahim, Amin</au><au>Sauvageau, Eric</au><au>Hanel, Ricardo A.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience</atitle><jtitle>World neurosurgery</jtitle><addtitle>World Neurosurg</addtitle><date>2024-08-01</date><risdate>2024</risdate><volume>188</volume><spage>e59</spage><epage>e63</epage><pages>e59-e63</pages><issn>1878-8750</issn><issn>1878-8769</issn><eissn>1878-8769</eissn><abstract>To evaluate variability in aneurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. Neuroradiologists reviewed 770 CTA images and reported the presence or absence of saccular aneurysms. Subsequently, the images were analyzed by AI software. If the software suspected an aneurysm, it flagged the corresponding image. In cases where there was a mismatch between the radiologist’s report and the AI findings, an expert neurosurgeon evaluated CTA images providing a definitive conclusion on the presence or absence of an aneurysm. AI software flagged 33 cases as potential aneurysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, while in the same group, radiologists identified aneurysms in 28 CTA images. Compared with the radiologist’s report, AI performance had a sensitivity of 36%, specificity of 97.6%, and negative predictive value of 96.2%. There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosurgeon confirmed that 7 of the 17 images showed an aneurysm. In 28 images considered negative by AI, radiologists indicated aneurysms; 17 of those confirmed by the neurosurgeon. AI has the potential to increase the diagnosis of unruptured intracranial aneurysms. However, it must be used as an adjacent tool within the standard of care due to limited applicability in real-world settings.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>38735565</pmid><doi>10.1016/j.wneu.2024.05.015</doi><orcidid>https://orcid.org/0009-0008-9847-2685</orcidid><orcidid>https://orcid.org/0000-0003-3085-7411</orcidid><orcidid>https://orcid.org/0000-0002-4687-8308</orcidid><orcidid>https://orcid.org/0000-0002-1797-5627</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1878-8750
ispartof World neurosurgery, 2024-08, Vol.188, p.e59-e63
issn 1878-8750
1878-8769
1878-8769
language eng
recordid cdi_proquest_miscellaneous_3054433425
source ScienceDirect Freedom Collection
subjects Aneurysm
Artificial intelligence
stroke
title Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehensive Stroke Center Experience
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T21%3A02%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Use%20of%20Artificial%20Intelligence%20Software%20to%20Detect%20Intracranial%20Aneurysms:%20A%20Comprehensive%20Stroke%20Center%20Experience&rft.jtitle=World%20neurosurgery&rft.au=De%20Toledo,%20Otavio%20F.&rft.date=2024-08-01&rft.volume=188&rft.spage=e59&rft.epage=e63&rft.pages=e59-e63&rft.issn=1878-8750&rft.eissn=1878-8769&rft_id=info:doi/10.1016/j.wneu.2024.05.015&rft_dat=%3Cproquest_cross%3E3054433425%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c237t-91a4bb62a8e38b899711eab6be0c9b9f45bb86145b8a9535b691d3c2ebe4d86e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3054433425&rft_id=info:pmid/38735565&rfr_iscdi=true