Application of an artificial intelligence ensemble for detection of important secondary findings on lung ventilation and perfusion SPECT-CT.

Autor: Smith C; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: smitcart@musc.edu., Nance S; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: nances@musc.edu., Chamberlin JH; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: chamberj@musc.edu., Maisuria D; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: maisuria@musc.edu., O'Doherty J; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America; Siemens Healthineers, 40 Liberty Boulevard, Malvern, PA 19355, United States of America. Electronic address: odoherty@musc.edu., Baruah D; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: baruah@musc.edu., Schoepf UJ; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: schoepf@musc.edu., Szemes AV; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: vargaasz@musc.edu., Elojeimy S; Division of Nuclear Medicine, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: elojeim@musc.edu., Kabakus IM; Division of CardioThoracic Radiology, Department of Radiology and Radiological Science, Medical University of South Carolina, 96 Jonathan Lucas Street, Suite 210, MSC 323, Charleston, SC 29425, United States of America. Electronic address: kabakus@musc.edu.
Jazyk: angličtina
Zdroj: Clinical imaging [Clin Imaging] 2023 Aug; Vol. 100, pp. 24-29. Date of Electronic Publication: 2023 May 02.
DOI: 10.1016/j.clinimag.2023.04.015
Abstrakt: Rationale: Single-photon-emission-computerized-tomography/computed-tomography(SPECT/CT) is commonly used for pulmonary disease. Scant work has been done to determine ability of AI for secondary findings using low-dose-CT(LDCT) attenuation correction series of SPECT/CT.
Methods: 120 patients with ventilation-perfusion-SPECT/CT from 9/1/21-5/1/22 were included in this retrospective study. AI-RAD companion(VA10A,Siemens-Healthineers, Erlangen, Germany), an ensemble of deep-convolutional-neural-networks was evaluated for the detection of pulmonary nodules, coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss. Accuracy, sensitivity, specificity was measured for the outcomes. Inter-rater reliability were measured. Inter-rater reliability was measured using the intraclass correlation coefficient (ICC) by comparing the number of nodules identified by the AI to radiologist.
Results: Overall per-nodule accuracy, sensitivity, and specificity for detection of lung nodules were 0.678(95%CI 0.615-0.732), 0.956(95%CI 0.900-0.985), and 0.456(95%CI 0.376-0.543), respectively, with an intraclass correlation coefficient (ICC) between AI and radiologist of 0.78(95%CI 0.71-0.83). Overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.939(95%CI 0.878-0.975), 0.974(95%CI 0.925-0.995), and 0.857(95%CI 0.781-0.915), respectively. Sensitivity for coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.898(95%CI 0.778-0.966), 1 (95%CI 0.958-1), and 1 (95%CI 0.961-1), respectively. Specificity for coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.969(95% CI 0.893-0.996), 0.897 (95% CI 0.726-0.978), and 0.346 (95% CI 0.172-0.557), respectively.
Conclusion: AI ensemble was accurate for coronary artery calcium and aortic ectasia/aneurysm, while sensitive for aortic ectasia/aneurysm, lung nodules and vertebral height loss on LDCT attenuation correction series of SPECT/CT.
Competing Interests: Declaration of competing interest I confirm that all authors of this manuscript have declared any financial or personal relationships that could be viewed as potential sources of bias. We have disclosed any relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. We have also declared any potential conflicts of interest that could be perceived as influencing the content of the manuscript. We assure you that the research presented in this manuscript has been conducted in an impartial and objective manner, and the findings have not been influenced by any conflicting interests. Ismail M. Kabakus MD PhD received institutional research support and/or personal fees from Circle, Elucid Bioimaging, and Siemens. Uwe Joseph Schoepf MD received institutional research support and/or personal fees from Bayer, Bracco, Elucid Bioimaging, Guerbet, HeartFlow, Keya Medical, and Siemens. Akos-Varga Szemes MD PhD received institutional research support and/or personal fees from Elucid Bioimaging and Siemens.Jim O’Doherty PhD was an employee of Siemens Medical Solutions USA, Inc.
(Copyright © 2023 Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: