Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization

Background and Objectives: Acute aortic dissection (AD) is a life-threatening condition in which early detection can significantly improve patient outcomes and survival. This study evaluates the clinical benefits of integrating a deep learning (DL)-based application for the automated detection and p...

Full description

Saved in:
Bibliographic Details
Main Authors: Martina Cotena, Angela Ayobi, Colin Zuchowski, Jacqueline C. Junn, Brent D. Weinberg, Peter D. Chang, Daniel S. Chow, Jennifer E. Soun, Mar Roca-Sogorb, Yasmina Chaibi, Sarah Quenet
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/23/2689
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261205199880192
author Martina Cotena
Angela Ayobi
Colin Zuchowski
Jacqueline C. Junn
Brent D. Weinberg
Peter D. Chang
Daniel S. Chow
Jennifer E. Soun
Mar Roca-Sogorb
Yasmina Chaibi
Sarah Quenet
author_facet Martina Cotena
Angela Ayobi
Colin Zuchowski
Jacqueline C. Junn
Brent D. Weinberg
Peter D. Chang
Daniel S. Chow
Jennifer E. Soun
Mar Roca-Sogorb
Yasmina Chaibi
Sarah Quenet
author_sort Martina Cotena
collection DOAJ
description Background and Objectives: Acute aortic dissection (AD) is a life-threatening condition in which early detection can significantly improve patient outcomes and survival. This study evaluates the clinical benefits of integrating a deep learning (DL)-based application for the automated detection and prioritization of AD on chest CT angiographies (CTAs) with a focus on the reduction in the scan-to-assessment time (STAT) and interpretation time (IT). Materials and Methods: This retrospective Multi-Reader Multi-Case (MRMC) study compared AD detection with and without artificial intelligence (AI) assistance. The ground truth was established by two U.S. board-certified radiologists, while three additional expert radiologists served as readers. Each reader assessed the same CTAs in two phases: assessment unaided by AI assistance (pre-AI arm) and, after a 1-month washout period, assessment aided by device outputs (post-AI arm). STAT and IT metrics were compared between the two arms. Results: This study included 285 CTAs (95 per reader, per arm) with a mean patient age of 58.5 years ±14.7 (SD), of which 52% were male and 37% had a prevalence of AD. AI assistance significantly reduced the STAT for detecting 33 true positive AD cases from 15.84 min (95% CI: 13.37–18.31 min) without AI to 5.07 min (95% CI: 4.23–5.91 min) with AI, representing a 68% reduction (<i>p</i> < 0.01). The IT also reduced significantly from 21.22 s (95% CI: 19.87–22.58 s) without AI to 14.17 s (95% CI: 13.39–14.95 s) with AI (<i>p</i> < 0.05). Conclusions: The integration of a DL-based algorithm for AD detection on chest CTAs significantly reduces both the STAT and IT. By prioritizing urgent cases, the AI-assisted approach outperforms the standard First-In, First-Out (FIFO) workflow.
format Article
id doaj-art-3fc66435a3eb49a3a7604b37b2ed9555
institution OA Journals
issn 2075-4418
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-3fc66435a3eb49a3a7604b37b2ed95552025-08-20T01:55:28ZengMDPI AGDiagnostics2075-44182024-11-011423268910.3390/diagnostics14232689Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and PrioritizationMartina Cotena0Angela Ayobi1Colin Zuchowski2Jacqueline C. Junn3Brent D. Weinberg4Peter D. Chang5Daniel S. Chow6Jennifer E. Soun7Mar Roca-Sogorb8Yasmina Chaibi9Sarah Quenet10Avicenna.AI, 375 Avenue du Mistral, 13600 La Ciotat, FranceAvicenna.AI, 375 Avenue du Mistral, 13600 La Ciotat, FranceDepartment of Radiology and Imaging Sciences, Emory University School of Medicine, 1364 Clifton Road Northeast, Suite BG20, Atlanta, GA 30322, USADepartment of Radiology and Imaging Sciences, Emory University School of Medicine, 1364 Clifton Road Northeast, Suite BG20, Atlanta, GA 30322, USADepartment of Radiology and Imaging Sciences, Emory University School of Medicine, 1364 Clifton Road Northeast, Suite BG20, Atlanta, GA 30322, USADepartment of Radiological Sciences, University of California Irvine, Irvine, CA 92697, USADepartment of Radiological Sciences, University of California Irvine, Irvine, CA 92697, USADepartment of Radiological Sciences, University of California Irvine, Irvine, CA 92697, USAAvicenna.AI, 375 Avenue du Mistral, 13600 La Ciotat, FranceAvicenna.AI, 375 Avenue du Mistral, 13600 La Ciotat, FranceAvicenna.AI, 375 Avenue du Mistral, 13600 La Ciotat, FranceBackground and Objectives: Acute aortic dissection (AD) is a life-threatening condition in which early detection can significantly improve patient outcomes and survival. This study evaluates the clinical benefits of integrating a deep learning (DL)-based application for the automated detection and prioritization of AD on chest CT angiographies (CTAs) with a focus on the reduction in the scan-to-assessment time (STAT) and interpretation time (IT). Materials and Methods: This retrospective Multi-Reader Multi-Case (MRMC) study compared AD detection with and without artificial intelligence (AI) assistance. The ground truth was established by two U.S. board-certified radiologists, while three additional expert radiologists served as readers. Each reader assessed the same CTAs in two phases: assessment unaided by AI assistance (pre-AI arm) and, after a 1-month washout period, assessment aided by device outputs (post-AI arm). STAT and IT metrics were compared between the two arms. Results: This study included 285 CTAs (95 per reader, per arm) with a mean patient age of 58.5 years ±14.7 (SD), of which 52% were male and 37% had a prevalence of AD. AI assistance significantly reduced the STAT for detecting 33 true positive AD cases from 15.84 min (95% CI: 13.37–18.31 min) without AI to 5.07 min (95% CI: 4.23–5.91 min) with AI, representing a 68% reduction (<i>p</i> < 0.01). The IT also reduced significantly from 21.22 s (95% CI: 19.87–22.58 s) without AI to 14.17 s (95% CI: 13.39–14.95 s) with AI (<i>p</i> < 0.05). Conclusions: The integration of a DL-based algorithm for AD detection on chest CTAs significantly reduces both the STAT and IT. By prioritizing urgent cases, the AI-assisted approach outperforms the standard First-In, First-Out (FIFO) workflow.https://www.mdpi.com/2075-4418/14/23/2689aortic dissectionautomated detectiondeep learningprioritized worklistemergency radiologymulti-reader multi-case study
spellingShingle Martina Cotena
Angela Ayobi
Colin Zuchowski
Jacqueline C. Junn
Brent D. Weinberg
Peter D. Chang
Daniel S. Chow
Jennifer E. Soun
Mar Roca-Sogorb
Yasmina Chaibi
Sarah Quenet
Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization
Diagnostics
aortic dissection
automated detection
deep learning
prioritized worklist
emergency radiology
multi-reader multi-case study
title Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization
title_full Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization
title_fullStr Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization
title_full_unstemmed Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization
title_short Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization
title_sort enhancing radiologist efficiency with ai a multi reader multi case study on aortic dissection detection and prioritization
topic aortic dissection
automated detection
deep learning
prioritized worklist
emergency radiology
multi-reader multi-case study
url https://www.mdpi.com/2075-4418/14/23/2689
work_keys_str_mv AT martinacotena enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT angelaayobi enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT colinzuchowski enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT jacquelinecjunn enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT brentdweinberg enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT peterdchang enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT danielschow enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT jenniferesoun enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT marrocasogorb enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT yasminachaibi enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization
AT sarahquenet enhancingradiologistefficiencywithaiamultireadermulticasestudyonaorticdissectiondetectionandprioritization