Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study
(2024) In The Lancet Oncology 25(7). p.879-887- Abstract
- Background: Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging—Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale. Methods: In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or... (More)
- Background: Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging—Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale. Methods: In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or greater cancers using a retrospective cohort of 10 207 MRI examinations from 9129 patients. Of these examinations, 9207 cases from three centres (11 sites) based in the Netherlands were used for training and tuning, and 1000 cases from four centres (12 sites) based in the Netherlands and Norway were used for testing. In parallel, we facilitated a multireader, multicase observer study with 62 radiologists (45 centres in 20 countries; median 7 [IQR 5–10] years of experience in reading prostate MRI) using PI-RADS (2.1) on 400 paired MRI examinations from the testing cohort. Primary endpoints were the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) of the AI system in comparison with that of all readers using PI-RADS (2.1) and in comparison with that of the historical radiology readings made during multidisciplinary routine practice (ie, the standard of care with the aid of patient history and peer consultation). Histopathology and at least 3 years (median 5 [IQR 4–6] years) of follow-up were used to establish the reference standard. The statistical analysis plan was prespecified with a primary hypothesis of non-inferiority (considering a margin of 0·05) and a secondary hypothesis of superiority towards the AI system, if non-inferiority was confirmed. This study was registered at ClinicalTrials.gov, NCT05489341. Findings: Of the 10 207 examinations included from Jan 1, 2012, through Dec 31, 2021, 2440 cases had histologically confirmed Gleason grade group 2 or greater prostate cancer. In the subset of 400 testing cases in which the AI system was compared with the radiologists participating in the reader study, the AI system showed a statistically superior and non-inferior AUROC of 0·91 (95% CI 0·87–0·94; p (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/41b4d2d1-8cb9-4c31-9efd-e207a23db7fc
- author
- Saha, A. ; Bjartell, A. LU and Huisman, Henkjan
- author collaboration
- organization
- publishing date
- 2024
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- accuracy, appendix, Article, artificial intelligence, biochemical recurrence, cancer diagnosis, cancer research, cancer screening, cohort analysis, controlled study, data mining, diagnostic accuracy, digital rectal examination, echography, electronic health record, follow up, Gleason score, health care quality, histopathology, human, image quality, intelligence, machine learning, major clinical study, male, medical student, multiparametric magnetic resonance imaging, nuclear magnetic resonance imaging, point of care testing, predictive value, prevalence, prostate biopsy, prostate cancer, prostate imaging reporting and data system, prostate volume, prostatectomy, radiologist, receiver operating characteristic, retrospective study, Schistosoma mansoni, sensitivity and specificity, training, transrectal ultrasonography, vaccination, workload
- in
- The Lancet Oncology
- volume
- 25
- issue
- 7
- pages
- 9 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:85196560193
- ISSN
- 1470-2045
- DOI
- 10.1016/S1470-2045(24)00220-1
- language
- English
- LU publication?
- yes
- id
- 41b4d2d1-8cb9-4c31-9efd-e207a23db7fc
- date added to LUP
- 2024-08-29 15:53:18
- date last changed
- 2024-08-30 07:58:32
@article{41b4d2d1-8cb9-4c31-9efd-e207a23db7fc,
abstract = {{Background: Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging—Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale. Methods: In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or greater cancers using a retrospective cohort of 10 207 MRI examinations from 9129 patients. Of these examinations, 9207 cases from three centres (11 sites) based in the Netherlands were used for training and tuning, and 1000 cases from four centres (12 sites) based in the Netherlands and Norway were used for testing. In parallel, we facilitated a multireader, multicase observer study with 62 radiologists (45 centres in 20 countries; median 7 [IQR 5–10] years of experience in reading prostate MRI) using PI-RADS (2.1) on 400 paired MRI examinations from the testing cohort. Primary endpoints were the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) of the AI system in comparison with that of all readers using PI-RADS (2.1) and in comparison with that of the historical radiology readings made during multidisciplinary routine practice (ie, the standard of care with the aid of patient history and peer consultation). Histopathology and at least 3 years (median 5 [IQR 4–6] years) of follow-up were used to establish the reference standard. The statistical analysis plan was prespecified with a primary hypothesis of non-inferiority (considering a margin of 0·05) and a secondary hypothesis of superiority towards the AI system, if non-inferiority was confirmed. This study was registered at ClinicalTrials.gov, NCT05489341. Findings: Of the 10 207 examinations included from Jan 1, 2012, through Dec 31, 2021, 2440 cases had histologically confirmed Gleason grade group 2 or greater prostate cancer. In the subset of 400 testing cases in which the AI system was compared with the radiologists participating in the reader study, the AI system showed a statistically superior and non-inferior AUROC of 0·91 (95% CI 0·87–0·94; p}},
author = {{Saha, A. and Bjartell, A. and Huisman, Henkjan}},
issn = {{1470-2045}},
keywords = {{accuracy; appendix; Article; artificial intelligence; biochemical recurrence; cancer diagnosis; cancer research; cancer screening; cohort analysis; controlled study; data mining; diagnostic accuracy; digital rectal examination; echography; electronic health record; follow up; Gleason score; health care quality; histopathology; human; image quality; intelligence; machine learning; major clinical study; male; medical student; multiparametric magnetic resonance imaging; nuclear magnetic resonance imaging; point of care testing; predictive value; prevalence; prostate biopsy; prostate cancer; prostate imaging reporting and data system; prostate volume; prostatectomy; radiologist; receiver operating characteristic; retrospective study; Schistosoma mansoni; sensitivity and specificity; training; transrectal ultrasonography; vaccination; workload}},
language = {{eng}},
number = {{7}},
pages = {{879--887}},
publisher = {{Elsevier}},
series = {{The Lancet Oncology}},
title = {{Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study}},
url = {{http://dx.doi.org/10.1016/S1470-2045(24)00220-1}},
doi = {{10.1016/S1470-2045(24)00220-1}},
volume = {{25}},
year = {{2024}},
}