亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Deep Learning Whole‐Gland and Zonal Prostate Segmentation on a Public MRI Dataset

分割 人工智能 计算机科学 前列腺 磁共振成像 数据集 模式识别(心理学) 医学 放射科 癌症 内科学
作者
Renato Cuocolo,Albert Comelli,Alessandro Stefano,Viviana Benfante,Navdeep Dahiya,Arnaldo Stanzione,Anna Castaldo,Davide Raffaele De Lucia,Anthony Yezzi,Massimo Imbriaco
出处
期刊:Journal of Magnetic Resonance Imaging [Wiley]
卷期号:54 (2): 452-459 被引量:73
标识
DOI:10.1002/jmri.27585
摘要

Background Prostate volume, as determined by magnetic resonance imaging (MRI), is a useful biomarker both for distinguishing between benign and malignant pathology and can be used either alone or combined with other parameters such as prostate‐specific antigen. Purpose This study compared different deep learning methods for whole‐gland and zonal prostate segmentation. Study Type Retrospective. Population A total of 204 patients (train/test = 99/105) from the PROSTATEx public dataset. Field strength/Sequence A 3 T, TSE T 2 ‐weighted. Assessment Four operators performed manual segmentation of the whole‐gland, central zone + anterior stroma + transition zone (TZ), and peripheral zone (PZ). U‐net, efficient neural network (ENet), and efficient residual factorized ConvNet (ERFNet) were trained and tuned on the training data through 5‐fold cross‐validation to segment the whole gland and TZ separately, while PZ automated masks were obtained by the subtraction of the first two. Statistical Tests Networks were evaluated on the test set using various accuracy metrics, including the Dice similarity coefficient (DSC). Model DSC was compared in both the training and test sets using the analysis of variance test (ANOVA) and post hoc tests. Parameter number, disk size, training, and inference times determined network computational complexity and were also used to assess the model performance differences. A P < 0.05 was selected to indicate the statistical significance. Results The best DSC ( P < 0.05) in the test set was achieved by ENet: 91% ± 4% for the whole gland, 87% ± 5% for the TZ, and 71% ± 8% for the PZ. U‐net and ERFNet obtained, respectively, 88% ± 6% and 87% ± 6% for the whole gland, 86% ± 7% and 84% ± 7% for the TZ, and 70% ± 8% and 65 ± 8% for the PZ. Training and inference time were lowest for ENet. Data Conclusion Deep learning networks can accurately segment the prostate using T 2 ‐weighted images. Evidence Level 4 Technical Efficacy Stage 2

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
坦率的语芙完成签到,获得积分10
4秒前
提米橘发布了新的文献求助10
22秒前
NattyPoe发布了新的文献求助10
23秒前
FashionBoy应助sanages采纳,获得10
27秒前
量子星尘发布了新的文献求助10
27秒前
29秒前
叶渊舟发布了新的文献求助10
34秒前
Criminology34举报小冰棍求助涉嫌违规
38秒前
小成完成签到 ,获得积分10
44秒前
orixero应助科研通管家采纳,获得10
45秒前
Owen应助科研通管家采纳,获得10
45秒前
田様应助科研通管家采纳,获得10
45秒前
科研通AI2S应助科研通管家采纳,获得10
45秒前
叶渊舟完成签到,获得积分10
47秒前
千里草完成签到,获得积分10
55秒前
熊猫完成签到 ,获得积分10
1分钟前
1分钟前
小管完成签到,获得积分10
1分钟前
黄佳怡发布了新的文献求助10
1分钟前
提米橘发布了新的文献求助10
1分钟前
Cherry完成签到,获得积分10
1分钟前
科研通AI2S应助mtg采纳,获得10
1分钟前
1分钟前
1分钟前
我是老大应助冒险寻羊采纳,获得10
1分钟前
竹捷发布了新的文献求助10
1分钟前
akin发布了新的文献求助10
1分钟前
斯文败类应助竹捷采纳,获得10
1分钟前
Linden_bd完成签到 ,获得积分10
1分钟前
2分钟前
2分钟前
FashionBoy应助机智的莫茗采纳,获得10
2分钟前
冒险寻羊发布了新的文献求助10
2分钟前
wanci应助冒险寻羊采纳,获得10
2分钟前
2分钟前
提米橘发布了新的文献求助10
2分钟前
雨月残心完成签到,获得积分10
2分钟前
所所应助科研通管家采纳,获得10
2分钟前
Owen应助科研通管家采纳,获得10
2分钟前
科研通AI2S应助科研通管家采纳,获得10
2分钟前
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
Handbook of pharmaceutical excipients, Ninth edition 5000
Aerospace Standards Index - 2026 ASIN2026 3000
Relation between chemical structure and local anesthetic action: tertiary alkylamine derivatives of diphenylhydantoin 1000
Signals, Systems, and Signal Processing 610
Discrete-Time Signals and Systems 610
Principles of town planning : translating concepts to applications 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 纳米技术 有机化学 物理 生物化学 化学工程 计算机科学 复合材料 内科学 催化作用 光电子学 物理化学 电极 冶金 遗传学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 6066090
求助须知:如何正确求助?哪些是违规求助? 7898366
关于积分的说明 16322626
捐赠科研通 5208252
什么是DOI,文献DOI怎么找? 2786256
邀请新用户注册赠送积分活动 1768979
关于科研通互助平台的介绍 1647792