I L Štepán-Buksakowska1, J M Accurso2, F E Diehn3, J Huston3, T J Kaufmann3, P H Luetmer3, C P Wood3, X Yang4, D J Blezek4, R Carter5, C Hagen5, D Hořínek6, A Hejčl7, M Roček8, B J Erickson9. 1. From the Department of Radiology (I.L.Š.-B., F.E.D., J.H., T.J.K., P.H.L., C.P.W., B.J.E.) International Clinical Research Center (I.L.Š.-B., D.H., A.H.), St. Anne's University Hospital Brno, Brno, Czech Republic Department of Radiology (I.L.Š.-B., M.R.), Second Faculty of Medicine, Charles University and University Hospital Motol, Prague, Czech Republic. 2. Department of Radiology (J.M.A.), Mayo Clinic, Jacksonville, Florida. 3. From the Department of Radiology (I.L.Š.-B., F.E.D., J.H., T.J.K., P.H.L., C.P.W., B.J.E.). 4. Department of Information Services (X.Y., D.J.B.), Mayo Clinic, Rochester, Minnesota. 5. Division of Biomedical Statistics and Informatics (R.C., C.H.). 6. International Clinical Research Center (I.L.Š.-B., D.H., A.H.), St. Anne's University Hospital Brno, Brno, Czech Republic Department of Neurosurgery (D.H., A.H.), Masaryk Hospital, Ústí nad Labem, Czech Republic Department of Neurosurgery (D.H.), Central Military Hospital, Prague, Czech Republic. 7. International Clinical Research Center (I.L.Š.-B., D.H., A.H.), St. Anne's University Hospital Brno, Brno, Czech Republic Department of Neurosurgery (D.H., A.H.), Masaryk Hospital, Ústí nad Labem, Czech Republic. 8. Department of Radiology (I.L.Š.-B., M.R.), Second Faculty of Medicine, Charles University and University Hospital Motol, Prague, Czech Republic. 9. From the Department of Radiology (I.L.Š.-B., F.E.D., J.H., T.J.K., P.H.L., C.P.W., B.J.E.) bje@mayo.edu.
Abstract
BACKGROUND AND PURPOSE: 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. MATERIALS AND METHODS: 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. RESULTS: 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. CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.
BACKGROUND AND PURPOSE: 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. MATERIALS AND METHODS: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. RESULTS: 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. CONCLUSIONS: In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.
Authors: Bharathi Dasan Jagadeesan; Josser E Delgado Almandoz; Yasha Kadkhodayan; Colin P Derdeyn; Dewitte T Cross; Michael R Chicoine; Keith M Rich; Gregory J Zipfel; Ralph G Dacey; Christopher J Moran Journal: J Neurointerv Surg Date: 2013-03-28 Impact factor: 5.836
Authors: M H Schönfeld; V Schlotfeldt; N D Forkert; E Goebell; M Groth; E Vettorazzi; Y D Cho; M H Han; H-S Kang; J Fiehler Journal: Clin Neuroradiol Date: 2014-08-27 Impact factor: 3.649
Authors: S Miki; N Hayashi; Y Masutani; Y Nomura; T Yoshikawa; S Hanaoka; M Nemoto; K Ohtomo Journal: AJNR Am J Neuroradiol Date: 2016-02-18 Impact factor: 3.825