Assessing the role of an artificial intelligence assessment tool for thoracic aorta diameter on routine chest CT

John Graby; Maredudd Harris; Calum Jones; Harry Waring; Stephen Lyen; Benjamin J. Hudson; Jonathan Carl Luis Rodrigues

doi:10.1259/bjr.20220853

Assessing the role of an artificial intelligence assessment tool for thoracic aorta diameter on routine chest CT

John Graby, Maredudd Harris, Calum Jones, Harry Waring, Stephen Lyen, Benjamin J. Hudson, Jonathan Carl Luis Rodrigues

Department for Health

Royal United Hospitals Bath NHS Foundation Trust

Research output: Contribution to journal › Article › peer-review

7 Downloads (Pure)

Abstract

OBJECTIVE: To assess the diagnostic accuracy and clinical impact of automated artificial intelligence (AI) measurement of thoracic aorta diameter on routine chest CT. METHODS: A single-centre retrospective study involving three cohorts. 210 consecutive ECG-gated CT aorta scans (mean age 75 ± 13) underwent automated analysis (AI-Rad Companion Chest CT, Siemens) and were compared to a reference standard of specialist cardiothoracic radiologists for accuracy measuring aortic diameter. A repeated measures analysis tested reporting consistency in a second cohort (29 patients, mean age 61 ± 17) of immediate sequential pre-contrast and contrast CT aorta acquisitions. Potential clinical impact was assessed in a third cohort of 197 routine CT chests (mean age 66 ± 15) to document potential clinical impact. RESULTS: AI analysis produced a full report in 387/436 (89%) and a partial report in 421/436 (97%). Manual vs AI agreement was good to excellent (ICC 0.76-0.92). Repeated measures analysis of expert and AI reports for the ascending aorta were moderate to good (ICC 0.57-0.88). AI diagnostic performance crossed the threshold for maximally accepted limits of agreement (>5 mm) at the aortic root on ECG-gated CTs. AI newly identified aortic dilatation in 27% of patients on routine thoracic imaging with a specificity of 99% and sensitivity of 77%. CONCLUSION: AI has good agreement with expert readers at the mid-ascending aorta and has high specificity, but low sensitivity, at detecting dilated aortas on non-dedicated chest CTs. ADVANCES IN KNOWLEDGE: An AI tool may improve the detection of previously unknown thoracic aorta dilatation on chest CTs vs current routine reporting.

Original language	English
Article number	20220853
Number of pages	11
Journal	The British journal of radiology
Volume	96
Issue number	1151
Early online date	26 Jul 2023
DOIs	https://doi.org/10.1259/bjr.20220853
Publication status	Published - 1 Nov 2023

Bibliographical note

Funding Information:
Dr Rodrigues and Dr Graby report personal fees from Sanofi, and Dr Rodrigues personal fees from NHSX, HeartFlow-Physicians’ services, and is co-founder and partner for Heart & Lung health, all outside of this submitted work. Our institution (the Royal United Hospitals Bath NHS Foundation Trust) is a European reference centre for Siemens Healthineers CT scanners and Siemens AI-Rad Companion was provided free of charge for the study but the study was conducted independently to Siemens Healthineers.

Publisher Copyright:
© 2023 The Authors.

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

Access to Document

10.1259/bjr.20220853

AI_assessment_of_the_aorta_updated_manuscript_clean_with_figure_in-line
© 2023 The Authors. Published by the British Institute of Radiology.
Accepted author manuscript, 563 KB

Cite this

@article{99c8b49ad6124e2295a53151c7e5d919,

title = "Assessing the role of an artificial intelligence assessment tool for thoracic aorta diameter on routine chest CT",

abstract = "OBJECTIVE: To assess the diagnostic accuracy and clinical impact of automated artificial intelligence (AI) measurement of thoracic aorta diameter on routine chest CT. METHODS: A single-centre retrospective study involving three cohorts. 210 consecutive ECG-gated CT aorta scans (mean age 75 ± 13) underwent automated analysis (AI-Rad Companion Chest CT, Siemens) and were compared to a reference standard of specialist cardiothoracic radiologists for accuracy measuring aortic diameter. A repeated measures analysis tested reporting consistency in a second cohort (29 patients, mean age 61 ± 17) of immediate sequential pre-contrast and contrast CT aorta acquisitions. Potential clinical impact was assessed in a third cohort of 197 routine CT chests (mean age 66 ± 15) to document potential clinical impact. RESULTS: AI analysis produced a full report in 387/436 (89%) and a partial report in 421/436 (97%). Manual vs AI agreement was good to excellent (ICC 0.76-0.92). Repeated measures analysis of expert and AI reports for the ascending aorta were moderate to good (ICC 0.57-0.88). AI diagnostic performance crossed the threshold for maximally accepted limits of agreement (>5 mm) at the aortic root on ECG-gated CTs. AI newly identified aortic dilatation in 27% of patients on routine thoracic imaging with a specificity of 99% and sensitivity of 77%. CONCLUSION: AI has good agreement with expert readers at the mid-ascending aorta and has high specificity, but low sensitivity, at detecting dilated aortas on non-dedicated chest CTs. ADVANCES IN KNOWLEDGE: An AI tool may improve the detection of previously unknown thoracic aorta dilatation on chest CTs vs current routine reporting.",

author = "John Graby and Maredudd Harris and Calum Jones and Harry Waring and Stephen Lyen and Hudson, {Benjamin J.} and Rodrigues, {Jonathan Carl Luis}",

note = "Funding Information: Dr Rodrigues and Dr Graby report personal fees from Sanofi, and Dr Rodrigues personal fees from NHSX, HeartFlow-Physicians{\textquoteright} services, and is co-founder and partner for Heart & Lung health, all outside of this submitted work. Our institution (the Royal United Hospitals Bath NHS Foundation Trust) is a European reference centre for Siemens Healthineers CT scanners and Siemens AI-Rad Companion was provided free of charge for the study but the study was conducted independently to Siemens Healthineers. Publisher Copyright: {\textcopyright} 2023 The Authors.",

year = "2023",

month = nov,

day = "1",

doi = "10.1259/bjr.20220853",

language = "English",

volume = "96",

journal = "The British journal of radiology",

issn = "0007-1285",

publisher = "British Institute of Radiology",

number = "1151",

}

TY - JOUR

T1 - Assessing the role of an artificial intelligence assessment tool for thoracic aorta diameter on routine chest CT

AU - Graby, John

AU - Harris, Maredudd

AU - Jones, Calum

AU - Waring, Harry

AU - Lyen, Stephen

AU - Hudson, Benjamin J.

AU - Rodrigues, Jonathan Carl Luis

N1 - Funding Information: Dr Rodrigues and Dr Graby report personal fees from Sanofi, and Dr Rodrigues personal fees from NHSX, HeartFlow-Physicians’ services, and is co-founder and partner for Heart & Lung health, all outside of this submitted work. Our institution (the Royal United Hospitals Bath NHS Foundation Trust) is a European reference centre for Siemens Healthineers CT scanners and Siemens AI-Rad Companion was provided free of charge for the study but the study was conducted independently to Siemens Healthineers. Publisher Copyright: © 2023 The Authors.

PY - 2023/11/1

Y1 - 2023/11/1

N2 - OBJECTIVE: To assess the diagnostic accuracy and clinical impact of automated artificial intelligence (AI) measurement of thoracic aorta diameter on routine chest CT. METHODS: A single-centre retrospective study involving three cohorts. 210 consecutive ECG-gated CT aorta scans (mean age 75 ± 13) underwent automated analysis (AI-Rad Companion Chest CT, Siemens) and were compared to a reference standard of specialist cardiothoracic radiologists for accuracy measuring aortic diameter. A repeated measures analysis tested reporting consistency in a second cohort (29 patients, mean age 61 ± 17) of immediate sequential pre-contrast and contrast CT aorta acquisitions. Potential clinical impact was assessed in a third cohort of 197 routine CT chests (mean age 66 ± 15) to document potential clinical impact. RESULTS: AI analysis produced a full report in 387/436 (89%) and a partial report in 421/436 (97%). Manual vs AI agreement was good to excellent (ICC 0.76-0.92). Repeated measures analysis of expert and AI reports for the ascending aorta were moderate to good (ICC 0.57-0.88). AI diagnostic performance crossed the threshold for maximally accepted limits of agreement (>5 mm) at the aortic root on ECG-gated CTs. AI newly identified aortic dilatation in 27% of patients on routine thoracic imaging with a specificity of 99% and sensitivity of 77%. CONCLUSION: AI has good agreement with expert readers at the mid-ascending aorta and has high specificity, but low sensitivity, at detecting dilated aortas on non-dedicated chest CTs. ADVANCES IN KNOWLEDGE: An AI tool may improve the detection of previously unknown thoracic aorta dilatation on chest CTs vs current routine reporting.

AB - OBJECTIVE: To assess the diagnostic accuracy and clinical impact of automated artificial intelligence (AI) measurement of thoracic aorta diameter on routine chest CT. METHODS: A single-centre retrospective study involving three cohorts. 210 consecutive ECG-gated CT aorta scans (mean age 75 ± 13) underwent automated analysis (AI-Rad Companion Chest CT, Siemens) and were compared to a reference standard of specialist cardiothoracic radiologists for accuracy measuring aortic diameter. A repeated measures analysis tested reporting consistency in a second cohort (29 patients, mean age 61 ± 17) of immediate sequential pre-contrast and contrast CT aorta acquisitions. Potential clinical impact was assessed in a third cohort of 197 routine CT chests (mean age 66 ± 15) to document potential clinical impact. RESULTS: AI analysis produced a full report in 387/436 (89%) and a partial report in 421/436 (97%). Manual vs AI agreement was good to excellent (ICC 0.76-0.92). Repeated measures analysis of expert and AI reports for the ascending aorta were moderate to good (ICC 0.57-0.88). AI diagnostic performance crossed the threshold for maximally accepted limits of agreement (>5 mm) at the aortic root on ECG-gated CTs. AI newly identified aortic dilatation in 27% of patients on routine thoracic imaging with a specificity of 99% and sensitivity of 77%. CONCLUSION: AI has good agreement with expert readers at the mid-ascending aorta and has high specificity, but low sensitivity, at detecting dilated aortas on non-dedicated chest CTs. ADVANCES IN KNOWLEDGE: An AI tool may improve the detection of previously unknown thoracic aorta dilatation on chest CTs vs current routine reporting.

UR - http://www.scopus.com/inward/record.url?scp=85175356258&partnerID=8YFLogxK

U2 - 10.1259/bjr.20220853

DO - 10.1259/bjr.20220853

M3 - Article

C2 - 37335231

AN - SCOPUS:85175356258

SN - 0007-1285

VL - 96

JO - The British journal of radiology

JF - The British journal of radiology

IS - 1151

M1 - 20220853

ER -

Assessing the role of an artificial intelligence assessment tool for thoracic aorta diameter on routine chest CT

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this