Radiomic feature reproducibility in contrast-enhanced CT of the pancreas is affected by variabilities in scan parameters and manual segmentation

被引:65
作者
Yamashita, Rikiya [1 ]
Perrin, Thomas [2 ]
Chakraborty, Jayasree [2 ]
Chou, Joanne F. [3 ]
Horvat, Natally [1 ]
Koszalka, Maura A. [2 ]
Midya, Abhishek [2 ]
Gonen, Mithat [3 ]
Allen, Peter [2 ]
Jarnagin, William R. [2 ]
Simpson, Amber L. [2 ]
Do, Richard K. G. [1 ]
机构
[1] Mem Sloan Kettering Canc Ctr, Dept Radiol, 1275 York Ave, New York, NY 10065 USA
[2] Mem Sloan Kettering Canc Ctr, Dept Surg, 1275 York Ave, New York, NY 10065 USA
[3] Mem Sloan Kettering Canc Ctr, Dept Epidemiol & Biostat, 1275 York Ave, New York, NY 10065 USA
基金
美国国家卫生研究院;
关键词
Reproducibility of results; Pancreatic ductal carcinoma; X-ray computed tomography; Radiomics; Texture analysis; TEXTURE ANALYSIS; CANCER; ASSOCIATION; INFORMATION; STABILITY; IMAGES;
D O I
10.1007/s00330-019-06381-8
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Objectives This study aims to measure the reproducibility of radiomic features in pancreatic parenchyma and ductal adenocarcinomas (PDAC) in patients who underwent consecutive contrast-enhanced computed tomography (CECT) scans. Methods In this IRB-approved and HIPAA-compliant retrospective study, 37 pairs of scans from 37 unique patients who underwent CECTs within a 2-week interval were included in the analysis of the reproducibility of features derived from pancreatic parenchyma, and a subset of 18 pairs of scans were further analyzed for the reproducibility of features derived from PDAC. In each patient, pancreatic parenchyma and pancreatic tumor (when present) were manually segmented by two radiologists independently. A total of 266 radiomic features were extracted from the pancreatic parenchyma and tumor region and also the volume and diameter of the tumor. The concordance correlation coefficient (CCC) was calculated to assess feature reproducibility for each patient in three scenarios: (1) different radiologists, same CECT; (2) same radiologist, different CECTs; and (3) different radiologists, different CECTs. Results Among pancreatic parenchyma-derived features, using a threshold of CCC > 0.90, 58/266 (21.8%) and 48/266 (18.1%) features met the threshold for scenario 1, 14/266 (5.3%) and 15/266 (5.6%) for scenario 2, and 14/266 (5.3%) and 10/266 (3.8%) for scenario 3. Among pancreatic tumor-derived features, 11/268 (4.1%) and 17/268 (6.3%) features met the threshold for scenario 1, 1/268 (0.4%) and 5/268 (1.9%) features met the threshold for scenario 2, and no features for scenario 3 met the threshold, respectively. Conclusions Variations between CECT scans affected radiomic feature reproducibility to a greater extent than variation in segmentation. A smaller number of pancreatic tumor-derived radiomic features were reproducible compared with pancreatic parenchyma-derived radiomic features under the same conditions.
引用
收藏
页码:195 / 205
页数:11
相关论文
共 50 条
[31]   Radiomic Nomogram for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Therapy in Breast Cancer: Predictive Value of Staging Contrast-enhanced CT [J].
Huang, Xiaomei ;
Mai, Jinhai ;
Huang, Yanqi ;
He, Lan ;
Chen, Xin ;
Wu, Xiaomei ;
Li, Yexing ;
Yang, Xiaojun ;
Dong, Mengyi ;
Huang, Jia ;
Zhang, Fang ;
Liang, Changhong ;
Liu, Zaiyi .
CLINICAL BREAST CANCER, 2021, 21 (04) :E388-E401
[32]   Effects of simulated dose variation on contrast-enhanced CT-based radiomic analysis for Non-Small Cell Lung Cancer [J].
Hepp, Tobias ;
Othman, Ahmed ;
Liebgott, Annika ;
Kim, Jong Hyo ;
Pfannenberg, Christina ;
Gatidis, Sergios .
EUROPEAN JOURNAL OF RADIOLOGY, 2020, 124
[33]   Dynamic contrast-enhanced MRI differentiates hepatocellular carcinoma from hepatic metastasis of rectal cancer by extracting pharmacokinetic parameters and radiomic features [J].
Li, Jianzhi ;
Xue, Feng ;
Xu, Xinghua ;
Wang, Qing ;
Zhang, Xuexi .
EXPERIMENTAL AND THERAPEUTIC MEDICINE, 2020, 20 (04) :3643-3652
[34]   Enhanced lung cancer subtype classification using attention-integrated DeepCNN and radiomic features from CT images: a focus on feature reproducibility [J].
Alsallal, Muna ;
Ahmed, Hanan Hassan ;
Kareem, Radhwan Abdul ;
Yadav, Anupam ;
Ganesan, Subbulakshmi ;
Shankhyan, Aman ;
Gupta, Sofia ;
Joshi, Kamal Kant ;
Sameer, Hayder Naji ;
Yaseen, Ahmed ;
Athab, Zainab H. ;
Adil, Mohaned ;
Farhood, Bagher .
DISCOVER ONCOLOGY, 2025, 16 (01)
[35]   Value of contrast-enhanced CT based radiomic machine learning algorithm in differentiating gastrointestinal stromal tumors with KIT exon 11 mutation: a two-center study [J].
Liu, Bo ;
Liu, Hao ;
Zhang, Lequan ;
Song, Yancheng ;
Yang, Shifeng ;
Zheng, Ziwen ;
Zhao, Junjiang ;
Hou, Feng ;
Zhang, Jian .
DIAGNOSTIC AND INTERVENTIONAL RADIOLOGY, 2022, 28 (01) :29-38
[36]   Cerebral Blood Volume Analysis in Glioblastomas Using Dynamic Susceptibility Contrast-Enhanced Perfusion MRI: A Comparison of Manual and Semiautomatic Segmentation Methods [J].
Jung, Seung Chai ;
Choi, Seung Hong ;
Yeom, Jeong A. ;
Kim, Ji-Hoon ;
Ryoo, Inseon ;
Kim, Soo Chin ;
Shin, Hwaseon ;
Lee, A. Leum ;
Yun, Tae Jin ;
Park, Chul-Kee ;
Sohn, Chul-Ho ;
Park, Sung-Hye .
PLOS ONE, 2013, 8 (08)
[37]   Ring-enhancement pattern on contrast-enhanced CT predicts adenosquamous carcinoma of the pancreas: A matched case-control study [J].
Imaoka, Hiroshi ;
Shimizu, Yasuhiro ;
Mizuno, Nobumasa ;
Hara, Kazuo ;
Hijioka, Susumu ;
Tajika, Masahiro ;
Tanaka, Tsutomu ;
Ishihara, Makoto ;
Ogura, Takeshi ;
Obayashi, Tomohiko ;
Shinagawa, Akihide ;
Sakaguchi, Masafumi ;
Yamaura, Hidekazu ;
Kato, Mina ;
Niwa, Yasumasa ;
Yamao, Kenji .
PANCREATOLOGY, 2014, 14 (03) :221-226
[38]   Feasibility Study of a Contrast-Enhanced Multi-Detector CT (64 Channels) Protocol for Papillary Thyroid Carcinoma: The Influence of Different Scan Delays on Tumor Conspicuity [J].
Lee, Young Hen ;
Seo, Hyung Suk ;
Suh, Sang-il ;
Ryoo, Inseon ;
You, Sung-Hye ;
Son, Kyu Ri ;
Kwon, Soon-Young ;
Son, Gil Soo ;
Yang, Kyung-Sook .
THYROID, 2016, 26 (05) :726-733
[39]   Additional value of FDG PET/CT to contrast-enhanced CT in the differentiation between benign and malignant intraductal papillary mucinous neoplasms of the pancreas with mural nodules [J].
Takanami, Kentaro ;
Hiraide, Tomomichi ;
Tsuda, Masashi ;
Nakamura, Yasuhiro ;
Kaneta, Tomohiro ;
Takase, Kei ;
Fukuda, Hiroshi ;
Takahashi, Shoki .
ANNALS OF NUCLEAR MEDICINE, 2011, 25 (07) :501-510
[40]   Deep learning–based automatic segmentation of meningioma from T1-weighted contrast-enhanced MRI for preoperative meningioma differentiation using radiomic features [J].
Liping Yang ;
Tianzuo Wang ;
Jinling Zhang ;
Shi Kang ;
Shichuan Xu ;
Kezheng Wang .
BMC Medical Imaging, 24