Evaluation of AI for prostate cancer detection in biparametric-MRI screening population data

作者
Fredrik Langkilde,Magnus Gren,Jonas Wallström,Stefan Kuczera,Stephan E. Maier
出处
期刊:European Radiology [Springer Science+Business Media]
被引量:1
标识
DOI:10.1007/s00330-025-12198-5
摘要

Abstract Objective The goal of this study was to curate a prostate MRI dataset from a screening population and to train and evaluate a deep-learning segmentation method on the same data. Materials and methods An artificial intelligence (AI) system, based on a deep-learning-based segmentation model (nnU-Net method), was trained and evaluated with MRI data from a prostate cancer screening population (G2-trial). The goal of the AI was to detect clinically significant prostate cancer (csPC), defined as International Society of Urological Pathology (ISUP) grade 2 or higher. The AI system was compared to the performance of radiologists using PI-RADS v2 evaluation metrics. Histopathology was used as the reference standard in the dataset. To better verify negative cases, 288 men were subject to systematic biopsies regardless of MRI findings, and all men had at least 3 years of follow-up. Results A total of 1354 MRI examinations in 1254 men with a median age of 58 years (range 50–63 years) were randomly divided into a training set (1086 examinations) and a test set (268 examinations). The resulting area under the receiver operating characteristic curve (AUROC) was 0.83 (95% CI 0.73–0.92) for the AI system; however, with significantly lower specificity at matched sensitivity levels compared to radiologists. Conclusion A prostate MRI dataset from a screening population with histological confirmation was curated and evaluated with AI. The neural network trained and tested on this data produced lower specificities than the radiologists. Key Points Question Does an AI system trained in a screening cohort perform as well as radiologists? Findings An AI trained on screening data achieved an AUROC of 0.83 (95% CI 0.73–0.92) with lower specificity at the same sensitivity levels as radiologists. Clinical relevance An AI system trained in a screening population has lower specificity than radiologists using PI-RADS v2. Graphical Abstract
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
1秒前
星辰发布了新的文献求助30
1秒前
深情安青的应助被狮山教授采纳,获得30
1秒前
jzmulyl发布了新的文献求助10
1秒前
123发布了新的文献求助10
2秒前
培P完成签到,获得积分10
2秒前
Pei完成签到,获得积分10
2秒前
黑粉头头发布了新的文献求助10
2秒前
coooler发布了新的文献求助10
3秒前
一味地丶逞强完成签到,获得积分10
3秒前
FashionBoy的应助被黄123huang_采纳,获得10
3秒前
何松发布了新的文献求助10
3秒前
旋转门发布了新的文献求助50
3秒前
3秒前
Mr_老旭完成签到,获得积分10
4秒前
4秒前
4秒前
ddd完成签到 ,获得积分10
4秒前
爆米花的应助被王井彦采纳,获得10
4秒前
完美世界的应助被韩野采纳,获得10
4秒前
威alisa发布了新的文献求助10
5秒前
5秒前
5秒前
5秒前
5秒前
企鹅发布了新的文献求助10
5秒前
6秒前
6秒前
隐形思天完成签到 ,获得积分10
6秒前
活力橘子完成签到,获得积分10
6秒前
搜集达人的应助被博nn采纳,获得10
6秒前
6秒前
YUAN发布了新的文献求助10
7秒前
anan完成签到,获得积分10
8秒前
8秒前
8秒前
Jennie发布了新的文献求助30
8秒前
coisini发布了新的文献求助10
9秒前
求知完成签到,获得积分10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8162621
求助须知:如何正确求助?哪些是违规求助? 9556889
关于积分的说明 21737583
捐赠科研通 7753002
什么是DOI,文献DOI怎么找? 3427836
关于科研通互助平台的介绍 2552719
邀请新用户注册赠送积分活动 2472507