Loading…
Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting
MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA i...
Saved in:
Published in: | American journal of neuroradiology : AJNR 2014-10, Vol.35 (10), p.1897-1902 |
---|---|
Main Authors: | , , , , , , , , , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73 |
---|---|
cites | cdi_FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73 |
container_end_page | 1902 |
container_issue | 10 |
container_start_page | 1897 |
container_title | American journal of neuroradiology : AJNR |
container_volume | 35 |
creator | Štepán-Buksakowska, I L Accurso, J M Diehn, F E Huston, J Kaufmann, T J Luetmer, P H Wood, C P Yang, X Blezek, D J Carter, R Hagen, C Hořínek, D Hejčl, A Roček, M Erickson, B J |
description | MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.
Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean = 3.12 mm, median = 2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.
For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F(1,47) = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.
In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm. |
doi_str_mv | 10.3174/ajnr.a3996 |
format | article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7966251</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1628240562</sourcerecordid><originalsourceid>FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73</originalsourceid><addsrcrecordid>eNqNkU1rFTEUhoMo9ra68QdIliJMzXcmG-FyUStUBOnCXThNztymzCTXZKbQf-9cWovuXJ3F-_DyHh5C3nB2LrlVH-A213OQzplnZMOdNJ3T7udzsmHc6c5w1p-Q09ZuGWPaWfGSnAjlhNJKbsjNrkyHZcbaQYoYaUywz6WlRtN0qOUOG404Y5hTybQMtE0wjjTluUKokBOMFDIu9b5Nja7Itx_bNaVAw5hyCmvccJ5T3r8iLwYYG75-vGfk6vOnq91Fd_n9y9fd9rILytq5M8iittYwqwcTh6CQ6UEzGQVeR-eEMCg4aqUGGY1jMHAdEYLjEIQEK8_Ix4faw3I9YQx4XDr6Q00T1HtfIPl_k5xu_L7ceeuMEZqvBe8eC2r5tWCb_ZRawHFc3yxL87xnvRG8N_-BGtELxbQRK_r-AQ21tFZxeFrEmT9K9EeJfnuUuMJv__7hCf1jTf4Gsi6bDg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1628240562</pqid></control><display><type>article</type><title>Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting</title><source>PubMed Central</source><creator>Štepán-Buksakowska, I L ; Accurso, J M ; Diehn, F E ; Huston, J ; Kaufmann, T J ; Luetmer, P H ; Wood, C P ; Yang, X ; Blezek, D J ; Carter, R ; Hagen, C ; Hořínek, D ; Hejčl, A ; Roček, M ; Erickson, B J</creator><creatorcontrib>Štepán-Buksakowska, I L ; Accurso, J M ; Diehn, F E ; Huston, J ; Kaufmann, T J ; Luetmer, P H ; Wood, C P ; Yang, X ; Blezek, D J ; Carter, R ; Hagen, C ; Hořínek, D ; Hejčl, A ; Roček, M ; Erickson, B J</creatorcontrib><description>MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.
Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean = 3.12 mm, median = 2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.
For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F(1,47) = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.
In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.</description><identifier>ISSN: 0195-6108</identifier><identifier>EISSN: 1936-959X</identifier><identifier>DOI: 10.3174/ajnr.a3996</identifier><identifier>PMID: 24924543</identifier><language>eng</language><publisher>United States: American Society of Neuroradiology</publisher><subject>Algorithms ; Brain ; Diagnosis, Computer-Assisted - methods ; Female ; Humans ; Intracranial Aneurysm - diagnostic imaging ; Magnetic Resonance Angiography - methods ; Male ; Radiography ; Retrospective Studies</subject><ispartof>American journal of neuroradiology : AJNR, 2014-10, Vol.35 (10), p.1897-1902</ispartof><rights>2014 by American Journal of Neuroradiology.</rights><rights>2014 by American Journal of Neuroradiology 2014 American Journal of Neuroradiology</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73</citedby><cites>FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7966251/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7966251/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/24924543$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Štepán-Buksakowska, I L</creatorcontrib><creatorcontrib>Accurso, J M</creatorcontrib><creatorcontrib>Diehn, F E</creatorcontrib><creatorcontrib>Huston, J</creatorcontrib><creatorcontrib>Kaufmann, T J</creatorcontrib><creatorcontrib>Luetmer, P H</creatorcontrib><creatorcontrib>Wood, C P</creatorcontrib><creatorcontrib>Yang, X</creatorcontrib><creatorcontrib>Blezek, D J</creatorcontrib><creatorcontrib>Carter, R</creatorcontrib><creatorcontrib>Hagen, C</creatorcontrib><creatorcontrib>Hořínek, D</creatorcontrib><creatorcontrib>Hejčl, A</creatorcontrib><creatorcontrib>Roček, M</creatorcontrib><creatorcontrib>Erickson, B J</creatorcontrib><title>Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting</title><title>American journal of neuroradiology : AJNR</title><addtitle>AJNR Am J Neuroradiol</addtitle><description>MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.
Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean = 3.12 mm, median = 2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.
For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F(1,47) = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.
In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.</description><subject>Algorithms</subject><subject>Brain</subject><subject>Diagnosis, Computer-Assisted - methods</subject><subject>Female</subject><subject>Humans</subject><subject>Intracranial Aneurysm - diagnostic imaging</subject><subject>Magnetic Resonance Angiography - methods</subject><subject>Male</subject><subject>Radiography</subject><subject>Retrospective Studies</subject><issn>0195-6108</issn><issn>1936-959X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNqNkU1rFTEUhoMo9ra68QdIliJMzXcmG-FyUStUBOnCXThNztymzCTXZKbQf-9cWovuXJ3F-_DyHh5C3nB2LrlVH-A213OQzplnZMOdNJ3T7udzsmHc6c5w1p-Q09ZuGWPaWfGSnAjlhNJKbsjNrkyHZcbaQYoYaUywz6WlRtN0qOUOG404Y5hTybQMtE0wjjTluUKokBOMFDIu9b5Nja7Itx_bNaVAw5hyCmvccJ5T3r8iLwYYG75-vGfk6vOnq91Fd_n9y9fd9rILytq5M8iittYwqwcTh6CQ6UEzGQVeR-eEMCg4aqUGGY1jMHAdEYLjEIQEK8_Ix4faw3I9YQx4XDr6Q00T1HtfIPl_k5xu_L7ceeuMEZqvBe8eC2r5tWCb_ZRawHFc3yxL87xnvRG8N_-BGtELxbQRK_r-AQ21tFZxeFrEmT9K9EeJfnuUuMJv__7hCf1jTf4Gsi6bDg</recordid><startdate>20141001</startdate><enddate>20141001</enddate><creator>Štepán-Buksakowska, I L</creator><creator>Accurso, J M</creator><creator>Diehn, F E</creator><creator>Huston, J</creator><creator>Kaufmann, T J</creator><creator>Luetmer, P H</creator><creator>Wood, C P</creator><creator>Yang, X</creator><creator>Blezek, D J</creator><creator>Carter, R</creator><creator>Hagen, C</creator><creator>Hořínek, D</creator><creator>Hejčl, A</creator><creator>Roček, M</creator><creator>Erickson, B J</creator><general>American Society of Neuroradiology</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>7TK</scope><scope>5PM</scope></search><sort><creationdate>20141001</creationdate><title>Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting</title><author>Štepán-Buksakowska, I L ; Accurso, J M ; Diehn, F E ; Huston, J ; Kaufmann, T J ; Luetmer, P H ; Wood, C P ; Yang, X ; Blezek, D J ; Carter, R ; Hagen, C ; Hořínek, D ; Hejčl, A ; Roček, M ; Erickson, B J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Algorithms</topic><topic>Brain</topic><topic>Diagnosis, Computer-Assisted - methods</topic><topic>Female</topic><topic>Humans</topic><topic>Intracranial Aneurysm - diagnostic imaging</topic><topic>Magnetic Resonance Angiography - methods</topic><topic>Male</topic><topic>Radiography</topic><topic>Retrospective Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Štepán-Buksakowska, I L</creatorcontrib><creatorcontrib>Accurso, J M</creatorcontrib><creatorcontrib>Diehn, F E</creatorcontrib><creatorcontrib>Huston, J</creatorcontrib><creatorcontrib>Kaufmann, T J</creatorcontrib><creatorcontrib>Luetmer, P H</creatorcontrib><creatorcontrib>Wood, C P</creatorcontrib><creatorcontrib>Yang, X</creatorcontrib><creatorcontrib>Blezek, D J</creatorcontrib><creatorcontrib>Carter, R</creatorcontrib><creatorcontrib>Hagen, C</creatorcontrib><creatorcontrib>Hořínek, D</creatorcontrib><creatorcontrib>Hejčl, A</creatorcontrib><creatorcontrib>Roček, M</creatorcontrib><creatorcontrib>Erickson, B J</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>Neurosciences Abstracts</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>American journal of neuroradiology : AJNR</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Štepán-Buksakowska, I L</au><au>Accurso, J M</au><au>Diehn, F E</au><au>Huston, J</au><au>Kaufmann, T J</au><au>Luetmer, P H</au><au>Wood, C P</au><au>Yang, X</au><au>Blezek, D J</au><au>Carter, R</au><au>Hagen, C</au><au>Hořínek, D</au><au>Hejčl, A</au><au>Roček, M</au><au>Erickson, B J</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting</atitle><jtitle>American journal of neuroradiology : AJNR</jtitle><addtitle>AJNR Am J Neuroradiol</addtitle><date>2014-10-01</date><risdate>2014</risdate><volume>35</volume><issue>10</issue><spage>1897</spage><epage>1902</epage><pages>1897-1902</pages><issn>0195-6108</issn><eissn>1936-959X</eissn><abstract>MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.
Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean = 3.12 mm, median = 2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.
For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F(1,47) = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.
In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.</abstract><cop>United States</cop><pub>American Society of Neuroradiology</pub><pmid>24924543</pmid><doi>10.3174/ajnr.a3996</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0195-6108 |
ispartof | American journal of neuroradiology : AJNR, 2014-10, Vol.35 (10), p.1897-1902 |
issn | 0195-6108 1936-959X |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7966251 |
source | PubMed Central |
subjects | Algorithms Brain Diagnosis, Computer-Assisted - methods Female Humans Intracranial Aneurysm - diagnostic imaging Magnetic Resonance Angiography - methods Male Radiography Retrospective Studies |
title | Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T10%3A50%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Computer-aided%20diagnosis%20improves%20detection%20of%20small%20intracranial%20aneurysms%20on%20MRA%20in%20a%20clinical%20setting&rft.jtitle=American%20journal%20of%20neuroradiology%20:%20AJNR&rft.au=%C5%A0tep%C3%A1n-Buksakowska,%20I%20L&rft.date=2014-10-01&rft.volume=35&rft.issue=10&rft.spage=1897&rft.epage=1902&rft.pages=1897-1902&rft.issn=0195-6108&rft.eissn=1936-959X&rft_id=info:doi/10.3174/ajnr.a3996&rft_dat=%3Cproquest_pubme%3E1628240562%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c477t-6e0d5776075f6dfc4e05f503d2ebd99226e21e544f3d690af15deac91ac23a73%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1628240562&rft_id=info:pmid/24924543&rfr_iscdi=true |