Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography

doi:10.7150/thno.49671

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography
	Mu, Wei 1,2; Liu, Chang 7; Gao, Feng 6; Qi, Yafei 5; Lu, Hong 4; Liu, Zaiyi 3; Zhang, Xianyi 7; Cai, Xiaoli 7; Ji, Ruo Yun 7; Hou, Yang 7
刊名	THERANOSTICS
	2020
卷号	10 期号:21 页码:9779-9788
关键词	Pancreatic fistula fistula risk score pancreatoduodenectomy computed tomography (CT) deep learning
ISSN号	1838-7640
DOI	10.7150/thno.49671
通讯作者	Shi, Yu(shiy@sj-hospital.org)
英文摘要	Rationale: Clinically relevant postoperative pancreatic fistula (CR-POPF) is among the most formidable complications after pancreatoduodenectomy (PD), heightening morbidity/mortality rates. Fistula Risk Score (FRS) is a well-developed predictor, but it is an intraoperative predictor and quantifies >50% patients as intermediate risk. Therefore, an accurate and easy-to-use preoperative index is desired. Herein, we test the hypothesis that quantitative analysis of contrast-enhanced computed tomography (CE-CT) with deep learning could predict CR-POPFs. Methods: A group of 513 patients underwent pancreatico-enteric anastomosis after PD at three institutions between 2006 and 2019 was retrospectively collected, and formed a training (70%) and a validation dataset (30%) randomly. A convolutional neural network was trained and generated a deep-learning score (DLS) to identify the patients with higher risk of CR-POPF preoperatively using CE-CT images, which was further externally tested in a prospective cohort collected from August 2018 to June 2019 at the fourth institution. The biological underpinnings of DLS were assessed using histomorphological data by multivariate linear regression analysis. Results: CR-POPFs developed in 95 patients (16.3%) in total. Compared to FRS, the DLS offered significantly greater predictability in training (AUC:0.85 [95% CI, 0.80-0.90] vs. 0.78 [95% CI, 0.72-0.84]; P= 0.03), validation (0.81 [95% CI, 0.72-0.89] vs. 0.76 [95% CI, 0.66-0.84], P = 0.05) and test (0.89 [95% CI, 0.79-0.96] vs. 0.73 [95% CI, 0.61-0.83], P < 0.001) cohorts. Especially in the challenging patients of intermediate risk (FRS: 3-6), the DLS showed significantly higher accuracy (training: 79.9% vs. 61.5% [P = 0.005]; validation: 70.3% vs. 56.3% [P = 0.04]; test: 92.1% vs. 65.8% [P = 0.013]). Additionally, DLS was independently associated with pancreatic fibrosis (coefficients: -0.167), main pancreatic duct (coefficients: -0.445) and remnant volume (coefficients: 0.138) in multivariate linear regression analysis (r(2) = 0.512, P < 0.001). The user satisfaction score in the test cohort was 4 out of 5. Conclusions: Preoperative CT based deep-learning model provides a promising novel method for predicting CR-POPF occurrences after PD, especially at intermediate FRS risk level. This has a potential to be integrated into radiologic reporting system or incorporated into surgical planning software to accommodate the preferences of surgeons to optimize preoperative strategies, intraoperative decision-making, and even postoperative care.
资助项目	National Natural Science Foundation of China[81771802] ; National Natural Science Foundation of China[81771893] ; fundamental research funds for the central universities
WOS关键词	BODY-MASS INDEX ; RISK SCORE ; VOLUME ; CT ; VALIDATION ; RESECTION ; FIBROSIS ; HEAD
WOS研究方向	Research & Experimental Medicine
语种	英语
出版者	IVYSPRING INT PUBL
WOS记录号	WOS:000559294500009
资助机构	National Natural Science Foundation of China ; fundamental research funds for the central universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40419]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Shi, Yu
作者单位	1.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med, Beijing, Peoples R China 2.Chinese Acad Sci, Key Lab Mol Imaging, Beijing 100190, Peoples R China 3.Guangdong Acad Med Sci, Guangdong Gen Hosp, Dept Radiol, 106 Zhongshan Er Rd, Guangzhou 510080, Peoples R China 4.Tianjin Med Univ Canc Inst & Hosp, Dept Radiol, Natl Clin Res Ctr Canc, Key Lab Canc Prevent & Therapy, Tianjin, Peoples R China 5.China Med Univ, Dept Pathol, Shengjing Hosp, Shenyang, Peoples R China 6.China Med Univ, Dept Pancreatothyroid Surg, Shengjing Hosp, Shenyang, Peoples R China 7.China Med Univ, Shengjing Hosp, Dept Radiol, 36 Sanhao St, Shenyang 110004, Peoples R China
推荐引用方式 GB/T 7714	Mu, Wei,Liu, Chang,Gao, Feng,et al. Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography[J]. THERANOSTICS,2020,10(21):9779-9788.
APA	Mu, Wei.,Liu, Chang.,Gao, Feng.,Qi, Yafei.,Lu, Hong.,...&Shi, Yu.(2020).Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography.THERANOSTICS,10(21),9779-9788.
MLA	Mu, Wei,et al."Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography".THERANOSTICS 10.21(2020):9779-9788.