CASIA OpenIR  > 中国科学院分子影像重点实验室
Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning: A Multi-Center and Prospective Validation Study
Wei, Jingwei1,2; Jiang, Hanyu3; Zeng, Mengsu4,5; Wang, Meiyun6,7; Niu, Meng8; Gu, Dongsheng1,2; Chong, Huanhuan4,5; Zhang, Yanyan9; Fu, Fangfang6,7; Zhou, Mu10; Chen, Jie3; Lyv, Fudong11; Wei, Hong3; Bashir, Mustafa R.12; Song, Bin3; Li, Hongjun9,13; Tian, Jie1,2,14,15
Source PublicationCANCERS
2021-05-01
Volume13Issue:10Pages:19
Abstract

Simple Summary Microvascular invasion (MVI) is an independent risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). Preoperative knowledge of MVI would assist with tailored surgical strategy making to prolong patient survival. Previous radiological studies proved the role of noninvasive medical imaging in MVI prediction. However, hitherto, deep learning methods remained unexplored for this clinical task. As an end-to-end self-learning strategy, deep learning may not only achieve improved prediction accuracy, but may also visualize high-risk areas of invasion by generating attention maps. In this multicenter study, we developed deep learning models to perform MVI preoperative assessments using two imaging modalities-computed tomography (CT) and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI). A head-to-head prospective validation was conducted to verify the validity of deep learning models and achieve a comparison between CT and EOB-MRI for MVI assessment. The findings put forward a better understanding of MVI preoperative prediction in HCC management. Microvascular invasion (MVI) is a critical risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). Preknowledge of MVI would assist tailored surgery planning in HCC management. In this multicenter study, we aimed to explore the validity of deep learning (DL) in MVI prediction using two imaging modalities-contrast-enhanced computed tomography (CE-CT) and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI). A total of 750 HCCs were enrolled from five Chinese tertiary hospitals. Retrospective CE-CT (n = 306, collected between March, 2013 and July, 2019) and EOB-MRI (n = 329, collected between March, 2012 and March, 2019) data were used to train two DL models, respectively. Prospective external validation (n = 115, collected between July, 2015 and February, 2018) was performed to assess the developed models. Furthermore, DL-based attention maps were utilized to visualize high-risk MVI regions. Our findings revealed that the EOB-MRI-based DL model achieved superior prediction outcome to the CE-CT-based DL model (area under receiver operating characteristics curve (AUC): 0.812 vs. 0.736, p = 0.038; sensitivity: 70.4% vs. 57.4%, p = 0.015; specificity: 80.3% vs. 86.9%, p = 0.052). DL attention maps could visualize peritumoral high-risk areas with genuine histopathologic confirmation. Both DL models could stratify high and low-risk groups regarding progression free survival and overall survival (p < 0.05). Thus, DL can be an efficient tool for MVI prediction, and EOB-MRI was proven to be the modality with advantage for MVI assessment than CE-CT.

Keywordhepatocellular carcinoma microvascular invasion magnetic resonance imaging computed tomography deep learning
DOI10.3390/cancers13102368
WOS KeywordPREOPERATIVE PREDICTION ; RECURRENCE ; RESECTION ; NOMOGRAM ; RISK
Indexed BySCI
Language英语
Funding ProjectMinistry of Science and Technology of China[2017YFA0205200] ; National Natural Science Foundation of China[82001917] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81527805] ; Chinese Academy of Sciences[GJJSTD20170004] ; Chinese Academy of Sciences[QYZDJ-SSW-JSC005] ; Beijing Municipal Science and Technology Commission[Z161100002616022] ; Beijing Municipal Science and Technology Commission[Z171100000117023]
Funding OrganizationMinistry of Science and Technology of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Beijing Municipal Science and Technology Commission
WOS Research AreaOncology
WOS SubjectOncology
WOS IDWOS:000654719300001
PublisherMDPI
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/44649
Collection中国科学院分子影像重点实验室
Corresponding AuthorLi, Hongjun; Tian, Jie
Affiliation1.Chinese Acad Sci, Inst Automat, Key Lab Mol Imaging, Beijing 100190, Peoples R China
2.Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China
3.Sichuan Univ, West China Hosp, Dept Radiol, Chengdu 610041, Peoples R China
4.Fudan Univ, Zhongshan Hosp, Dept Radiol, Shanghai 200032, Peoples R China
5.Shanghai Inst Med Imaging, Shanghai 200032, Peoples R China
6.Henan Prov Peoples Hosp, Dept Med Imaging, Zhengzhou 450003, Peoples R China
7.Zhengzhou Univ, Peoples Hosp, Dept Med Imaging, Zhengzhou 450003, Peoples R China
8.China Med Univ, Affiliated Hosp 1, Dept Intervent Radiol, Shenyang 110000, Peoples R China
9.Capital Med Univ, Beijing Youan Hosp, Dept Radiol, Beijing 100069, Peoples R China
10.SenseBrain Res, Santa Clara, CA 95131 USA
11.Capital Med Univ, Beijing Youan Hosp, Dept Pathol, Beijing 100069, Peoples R China
12.Duke Univ, Med Ctr, Dept Radiol, Durham, NC 27710 USA
13.Beihang Univ, Sch Bioengn, Beijing 100191, Peoples R China
14.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med, Beijing 100191, Peoples R China
15.Xidian Univ, Sch Life Sci & Technol, Minist Educ, Engn Res Ctr Mol & Neuro Imaging, Xian 710126, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences;  Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences;  Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wei, Jingwei,Jiang, Hanyu,Zeng, Mengsu,et al. Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning: A Multi-Center and Prospective Validation Study[J]. CANCERS,2021,13(10):19.
APA Wei, Jingwei.,Jiang, Hanyu.,Zeng, Mengsu.,Wang, Meiyun.,Niu, Meng.,...&Tian, Jie.(2021).Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning: A Multi-Center and Prospective Validation Study.CANCERS,13(10),19.
MLA Wei, Jingwei,et al."Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning: A Multi-Center and Prospective Validation Study".CANCERS 13.10(2021):19.
Files in This Item: Download All
File Name/Size DocType Version Access License
Prediction of Microv(2568KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wei, Jingwei]'s Articles
[Jiang, Hanyu]'s Articles
[Zeng, Mengsu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wei, Jingwei]'s Articles
[Jiang, Hanyu]'s Articles
[Zeng, Mengsu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wei, Jingwei]'s Articles
[Jiang, Hanyu]'s Articles
[Zeng, Mengsu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning A Multi-Center and Prospective Validation Study.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.