Radiologist-like artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy

doi:10.7150/thno.48706

	Radiologist-like artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy
	Shao, Lizhi 1,2; Yan, Ye 3; Liu, Zhenyu2,9,12 ; Ye, Xiongjun 4; Xia, Haizhui 3; Zhu, Xuehua 3; Zhang, Yuting 3; Zhang, Zhiying 3; Chen, Huiying 5; He, Wei 5; Liu, Cheng 3; Lu, Min 6; Huang, Yi 3; Ma, Lulin 3; Sun, Kai 2,8; Zhou, Xuezhi 2,8; Yang, Guanyu 1,7; Lu, Jian 3; Tian, Jie 2,8,10,11
发表期刊	THERANOSTICS
ISSN	1838-7640
	2020
卷号	10 期号:22 页码:10200-10212
通讯作者	Yang, Guanyu(yang.list@seu.edu.cn) ; Lu, Jian(lujian@bjmu.edu.cn) ; Tian, Jie(jie.tian@ia.ac.cn)
摘要	Rationale: To reduce upgrading and downgrading between needle biopsy (NB) and radical prostatectomy (RP) by predicting patient-level Gleason grade groups (GGs) of RP to avoid over-and under-treatment. Methods: In this study, we retrospectively enrolled 575 patients from two medical institutions. All patients received prebiopsy magnetic resonance (MR) examinations, and pathological evaluations of NB and RP were available. A total of 12,708 slices of original male pelvic MR images (T2-weighted sequences with fat suppression, T2WI-FS) containing 5405 slices of prostate tissue, and 2,753 tumor annotations (only T2WI-FS were annotated using RP pathological sections as ground truth) were analyzed for the prediction of patient-level RP GGs. We present a prostate cancer (PCa) framework, PCa-GGNet, that mimics radiologist behavior based on deep reinforcement learning (DRL). We developed and validated it using a multi-center format. Results: Accuracy (ACC) of our model outweighed NB results (0.815 [95% confidence interval (CI): 0.773-0.857] vs. 0.437 [95% CI: 0.335-0.539]). The PCa-GGNet scored higher (kappa value: 0.761) than NB (kappa value: 0.289). Our model significantly reduced the upgrading rate by 27.9% (P < 0.001) and downgrading rate by 6.4% (P = 0.029). Conclusions: DRL using MRI can be applied to the prediction of patient-level RP GGs to reduce upgrading and downgrading from biopsy, potentially improving the clinical benefits of prostate cancer oncologic controls.
关键词	prostate cancer Gleason grade groups deep reinforcement learning prostate cancer grading magnetic resonance imaging
DOI	10.7150/thno.48706
关键词[WOS]	GLEASON SCORE ; TARGETED BIOPSY ; CANCER ; CLASSIFICATION ; OPPORTUNITIES ; CONCORDANCE ; VALIDATION ; DIAGNOSIS ; FEATURES ; SYSTEM
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[81922040] ; National Natural Science Foundation of China[61871004] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81527805] ; National Natural Science Foundation of China[31571001] ; National Natural Science Foundation of China[61828101] ; National Key Research and Development Program of China[2018YFC0115900] ; Beijing Natural Science Foundation[7182109] ; National Key R&D Program of China[2017YFA0205200] ; Chinese Academy of Sciences[XDB32030200] ; Chinese Academy of Sciences[XDB01030200] ; Chinese Academy of Sciences[QYZDJ-SSW-JSC005] ; Youth Innovation Promotion Association CAS[2019136] ; Key Research and Development Project of Jiangsu Province[BE2018749] ; Southeast University-Nanjing Medical University Cooperative Research Project[2242019K3DN08]
项目资助者	National Natural Science Foundation of China ; National Key Research and Development Program of China ; Beijing Natural Science Foundation ; National Key R&D Program of China ; Chinese Academy of Sciences ; Youth Innovation Promotion Association CAS ; Key Research and Development Project of Jiangsu Province ; Southeast University-Nanjing Medical University Cooperative Research Project
WOS研究方向	Research & Experimental Medicine
WOS类目	Medicine, Research & Experimental
WOS记录号	WOS:000596762400001
出版者	IVYSPRING INT PUBL
七大方向——子方向分类	医学影像处理与分析
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42732
专题	中国科学院分子影像重点实验室
通讯作者	Yang, Guanyu; Lu, Jian; Tian, Jie
作者单位	1.Southeast Univ, Sch Comp Sci & Engn, Nanjing 211189, Peoples R China 2.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing Key Lab Mol Imaging,State Key Lab Managem, Beijing 100190, Peoples R China 3.Peking Univ Third Hosp, Dept Urol, Beijing, Peoples R China 4.Peking Univ Peoples Hosp, Urol & Lithotripsy Ctr, Beijing, Peoples R China 5.Peking Univ Third Hosp, Dept Radiol, Beijing, Peoples R China 6.Peking Univ Third Hosp, Dept Pathol, Beijing, Peoples R China 7.Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, LIST, Nanjing, Peoples R China 8.Xidian Univ, Sch Life Sci & Technol, Minist Educ, Engn Res Ctr Mol & Neuro Imaging, Xian, Peoples R China 9.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China 10.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med & Engn, Beijing, Peoples R China 11.Beihang Univ, Minist Ind & Informat Technol, Key Lab Big Data Based Precis Med, Beijing, Peoples R China 12.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100080, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Shao, Lizhi,Yan, Ye,Liu, Zhenyu,et al. Radiologist-like artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy[J]. THERANOSTICS,2020,10(22):10200-10212.
APA	Shao, Lizhi.,Yan, Ye.,Liu, Zhenyu.,Ye, Xiongjun.,Xia, Haizhui.,...&Tian, Jie.(2020).Radiologist-like artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy.THERANOSTICS,10(22),10200-10212.
MLA	Shao, Lizhi,et al."Radiologist-like artificial intelligence for grade group prediction of radical prostatectomy for reducing upgrading and downgrading from biopsy".THERANOSTICS 10.22(2020):10200-10212.