A multicenter study of artificial intelligence-aided software for detecting visible clinically significant prostate cancer on mpMRI

Background AI-based software may improve the performance of radiologists when detecting clinically significant prostate cancer (csPCa). This study aims to compare the performance of radiologists in detecting MRI-visible csPCa on MRI with and without AI-based software. Materials and methods In total,...

Full description

Saved in:
Bibliographic Details
Published in:Insights into imaging 2023-04, Vol.14 (1), p.72-72, Article 72
Main Authors: Sun, Zhaonan, Wang, Kexin, Kong, Zixuan, Xing, Zhangli, Chen, Yuntian, Luo, Ning, Yu, Yang, Song, Bin, Wu, Pengsheng, Wang, Xiangpeng, Zhang, Xiaodong, Wang, Xiaoying
Format: Article
Language:English
Subjects:
Artificial intelligence
Clinical significance
Computer-assisted
Data collection
Deep learning
Diagnosis
Diagnostic Radiology
Imaging
Internal Medicine
Interventional Radiology
Magnetic resonance imaging
Mean
Medical diagnosis
Medicine
Medicine & Public Health
Neuroradiology
Original
Original Article
Performance enhancement
Prostate cancer
Prostatic neoplasms
Radiology
Reading
Software
Ultrasound
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background AI-based software may improve the performance of radiologists when detecting clinically significant prostate cancer (csPCa). This study aims to compare the performance of radiologists in detecting MRI-visible csPCa on MRI with and without AI-based software. Materials and methods In total, 480 multiparametric MRI (mpMRI) images were retrospectively collected from eleven different MR devices, with 349 csPCa lesions in 180 (37.5%) cases. The csPCa areas were annotated based on pathology. Sixteen radiologists from four hospitals participated in reading. Each radiologist was randomly assigned to 30 cases and diagnosed twice. Half cases were interpreted without AI, and the other half were interpreted with AI. After four weeks, the cases were read again in switched mode. The mean diagnostic performance was compared using sensitivity and specificity on lesion level and patient level. The median reading time and diagnostic confidence were assessed. Results On lesion level, AI-aided improved the sensitivity from 40.1% to 59.0% (18.9% increased; 95% confidence interval (CI) [11.5, 26.1]; p  
ISSN:1869-4101
1869-4101
DOI:10.1186/s13244-023-01421-w