Development of a radiomics-based model to predict occult liver metastases of pancreatic ductal adenocarcinoma: a multicenter study

被引:13
作者
Zhao, Ben [1 ]
Xia, Cong [1 ]
Xia, Tianyi [1 ]
Qiu, Yue [1 ]
Zhu, Liwen [1 ]
Cao, Buyue [1 ]
Gao, Yin [1 ]
Ge, Rongjun [2 ]
Cai, Wu [3 ]
Ding, Zhimin [4 ]
Yu, Qian [1 ]
Lu, Chunqiang [1 ]
Tang, Tianyu [1 ]
Wang, Yuancheng [1 ]
Song, Yang [5 ]
Long, Xueying [6 ]
Ye, Jing [7 ]
Lu, Dong [8 ]
Ju, Shenghong [1 ,9 ]
机构
[1] Southeast Univ, Sch Med, Zhongda Hosp, Dept Radiol,Jiangsu Key Lab Mol & Funct Imaging, Nanjing, Jiangsu, Peoples R China
[2] Southeast Univ, Sch Instrument Sci & Engn, Nanjing, Peoples R China
[3] Soochow Univ, Affiliated Hosp 2, Dept Radiol, Suzhou, Peoples R China
[4] Yijishan Hosp, Wannan Med Coll, Dept Radiol, Wuhu, Peoples R China
[5] MR Sci Mkt Siemens Healthineers, Shanghai, Peoples R China
[6] Cent South Univ, Xiangya Hosp, Dept Radiol, Changsha, Peoples R China
[7] Northern Jiangsu Peoples Hosp, Dept Radiol, Yangzhou, Peoples R China
[8] Univ Sci & Technol China, Affiliated Hosp 1, Dept Radiol, Hefei, Peoples R China
[9] Southeast Univ, Zhongda Hosp, Sch Med, Dept Radiol,Jiangsu Key Lab Mol & Funct Imaging, 87 Ding Jia Qiao Rd, Nanjing 210009, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
computed tomography; occult liver metastases; pancreatic ductal adenocarcinoma; prognosis; radiomics; STATEMENT; CANCER;
D O I
10.1097/JS9.0000000000000908
中图分类号
R61 [外科手术学];
学科分类号
摘要
Background: Undetectable occult liver metastases block the long-term survival of pancreatic ductal adenocarcinoma (PDAC). This study aimed to develop a radiomics-based model to predict occult liver metastases and assess its prognostic capacity for survival. Materials and methods: Patients who underwent surgical resection and were pathologically proven with PDAC were recruited retrospectively from five tertiary hospitals between January 2015 and December 2020. Radiomics features were extracted from tumors, and the radiomics-based model was developed in the training cohort using LASSO-logistic regression. The model's performance was assessed in the internal and external validation cohorts using the area under the receiver operating curve (AUC). Subsequently, the association of the model's risk stratification with progression-free survival (PFS) and overall survival (OS) was then statistically examined using Cox regression analysis and the log-rank test. Results: A total of 438 patients [mean (SD) age, 62.0 (10.0) years; 255 (58.2%) male] were divided into the training cohort (n=235), internal validation cohort (n=100), and external validation cohort (n=103). The radiomics-based model yielded an AUC of 0.73 (95% CI: 0.66-0.80), 0.72 (95% CI: 0.62-0.80), and 0.71 (95% CI: 0.61-0.80) in the training, internal validation, and external validation cohorts, respectively, which were higher than the preoperative clinical model. The model's risk stratification was an independent predictor of PFS (all P <0.05) and OS (all P <0.05). Furthermore, patients in the high-risk group stratified by the model consistently had a significantly shorter PFS and OS at each TNM stage (all P <0.05). Conclusion: The proposed radiomics-based model provided a promising tool to predict occult liver metastases and had a great significance in prognosis.
引用
收藏
页码:740 / 749
页数:10
相关论文
共 33 条
[1]   Pancreatic Ductal Adenocarcinoma Radiology Reporting Template: Consensus Statement of the Society of Abdominal Radiology and the American Pancreatic Association [J].
Al-Hawary, Mahmoud M. ;
Francis, Isaac R. ;
Chari, Suresh T. ;
Fishman, Elliot K. ;
Hough, David M. ;
Lu, David S. ;
Macari, Michael ;
Megibow, Alec J. ;
Miller, Frank H. ;
Mortele, Koenraad J. ;
Merchant, Nipun B. ;
Minter, Rebecca M. ;
Tamm, Eric P. ;
Sahani, Dushyant V. ;
Simeone, Diane M. .
GASTROENTEROLOGY, 2014, 146 (01) :291-+
[2]  
[Anonymous], 2017, PHYSIOL BEHAV, V176, P139, DOI DOI 10.1016/J.PHYSBEH.2017.03.040
[3]   Characterizing indeterminate liver lesions in patients with localized pancreatic cancer at the time of diagnosis [J].
Bhalla, Manav ;
Aldakkak, Mohammed ;
Kulkarni, Naveen M. ;
O'Connor, Stacy D. ;
Griffin, Michael O., Jr. ;
Christians, Kathleen K. ;
Evans, Douglas B. ;
Tsai, Susan ;
Tolat, Parag P. .
ABDOMINAL RADIOLOGY, 2018, 43 (02) :351-363
[4]  
Bossuyt PM, 2015, BMJ-BRIT MED J, V351, DOI [10.1136/bmj.h5527, 10.1148/radiol.2015151516, 10.1373/clinchem.2015.246280]
[5]   Precision Oncology in Surgery Patient Selection for Operable Pancreatic Cancer [J].
Dreyer, Stephan B. ;
Pinese, Mark ;
Jamieson, Nigel B. ;
Scarlett, Christopher J. ;
Colvin, Emily K. ;
Pajic, Marina ;
Johns, Amber L. ;
Humphris, Jeremy L. ;
Wu, Jianmin ;
Cowley, Mark J. ;
Chou, Angela ;
Nagrial, Adnan M. ;
Chantrill, Lorraine ;
Chin, Venessa T. ;
Jones, Marc D. ;
Moran-Jones, Kim ;
Carter, Christopher Ross ;
Dickson, Euan J. ;
Samra, Jaswinder S. ;
Merrett, Neil D. ;
Gill, Anthony J. ;
Kench, James G. ;
Duthie, Fraser ;
Miller, David K. ;
Cooke, Susanna ;
Aust, Daniela ;
Knosel, Thomas ;
Rummele, Petra ;
Grutzmann, Robert ;
Pilarsky, Christian ;
Nam Q Nguyen ;
Musgrove, Elizabeth A. ;
Bailey, Peter J. ;
McKay, Colin J. ;
Biankin, Andrew, V ;
Chang, David K. .
ANNALS OF SURGERY, 2020, 272 (02) :366-376
[6]   Radiomics: Images Are More than Pictures, They Are Data [J].
Gillies, Robert J. ;
Kinahan, Paul E. ;
Hricak, Hedvig .
RADIOLOGY, 2016, 278 (02) :563-577
[7]   Patterns, Timing, and Predictors of Recurrence Following Pancreatectomy for Pancreatic Ductal Adenocarcinoma [J].
Groot, Vincent P. ;
Rezaee, Neda ;
Wu, Wenchuan ;
Cameron, John L. ;
Fishman, Elliot K. ;
Hruban, Ralph H. ;
Weiss, Matthew J. ;
Zheng, Lei ;
Wolfgang, Christopher L. ;
He, Jin .
ANNALS OF SURGERY, 2018, 267 (05) :936-945
[8]   Neoadjuvant therapy for pancreatic cancer [J].
Gugenheim, Jean ;
Crovetto, Anna ;
Petrucciani, Niccolo .
UPDATES IN SURGERY, 2022, 74 (01) :35-42
[9]   Improvement of surgical results for pancreatic cancer [J].
Hartwig, Werner ;
Werner, Jens ;
Jaeger, Dirk ;
Debus, Juergen ;
Buechler, Markus W. .
LANCET ONCOLOGY, 2013, 14 (11) :E476-E485
[10]   Circulating tumor DNA as a predictive marker for occult metastases in pancreatic cancer patients with radiographically non-metastatic disease [J].
Hata, Tatsuo ;
Mizuma, Masamichi ;
Iseki, Masahiro ;
Takadate, Tatsuyuki ;
Ishida, Masaharu ;
Nakagawa, Kei ;
Hayashi, Hiroki ;
Morikawa, Takanori ;
Motoi, Fuyuhiko ;
Unno, Michiaki .
JOURNAL OF HEPATO-BILIARY-PANCREATIC SCIENCES, 2021, 28 (08) :648-658