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
[41]   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
[42]   A RANDOM FOREST-BASED FRAMEWORK FOR 3D KIDNEY SEGMENTATION FROM DYNAMIC CONTRAST-ENHANCED CT IMAGES [J].
Khalifa, Fahmi ;
Soliman, Ahmed ;
Dwyer, Amy C. ;
Gimel'farb, Georgy ;
El-Baz, Ayman .
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, :3399-3403
[43]   Advanced Hepatocellular Carcinoma: Pretreatment Contrast-enhanced CT Texture Parameters as Predictive Biomarkers of Survival in Patients Treated with Sorafenib [J].
Mule, Sebastien ;
Thiefin, Gerard ;
Costentin, Charlotte ;
Durot, Carole ;
Rahmouni, Alain ;
Luciani, Alain ;
Hoeffel, Christine .
RADIOLOGY, 2018, 288 (02) :445-455
[44]   Auto-segmentation, radiomic reproducibility, and comparison of radiomics between manual and AI-derived segmentations for coronary arteries in cardiac [18F]NaF PET/CT images [J].
Li, Suning ;
Kendrick, Jake ;
Ebert, Martin A. ;
Hassan, Ghulam Mubashar ;
Barry, Nathaniel ;
Wright, Keaton ;
Lee, Sing Ching ;
Bellinge, Jamie W. ;
Schultz, Carl .
EJNMMI PHYSICS, 2025, 12 (01)
[45]   Deep learning-based automatic segmentation of meningioma from T1-weighted contrast-enhanced MRI for preoperative meningioma differentiation using radiomic features [J].
Yang, Liping ;
Wang, Tianzuo ;
Zhang, Jinling ;
Kang, Shi ;
Xu, Shichuan ;
Wang, Kezheng .
BMC MEDICAL IMAGING, 2024, 24 (01)
[46]   Automated segmentation of upper digestive tract from abdominal contrast-enhanced CT data using hierarchical statistical modeling of organ interrelations [J].
Hirayama, S. ;
Otake, Y. ;
Okada, T. ;
Hori, M. ;
Tomiyama, N. ;
Sato, Y. .
MEDICAL IMAGING 2016: IMAGE PROCESSING, 2016, 9784
[47]   Automatic detection of brain metastases on contrast-enhanced CT with deep-learning feature-fused single-shot detectors [J].
Amemiya, Shiori ;
Takao, Hidemasa ;
Kato, Shimpei ;
Yamashita, Hiroshi ;
Sakamoto, Naoya ;
Abe, Osamu .
EUROPEAN JOURNAL OF RADIOLOGY, 2021, 136
[48]   Assessment of Synovitis in the Osteoarthritic Knee: Comparison Between Manual Segmentation, Semiautomated Segmentation, and Semiquantitative Assessment Using Contrast-Enhanced Fat-Suppressed T1-Weighted MRI [J].
Fotinos-Hoyer, Amber Kassel ;
Guermazi, Ali ;
Jara, Hernan ;
Eckstein, Felix ;
Ozonoff, Al ;
Khard, Hussain ;
Norbash, Alexander ;
Bohndorf, Klaus ;
Roemer, Frank W. .
MAGNETIC RESONANCE IN MEDICINE, 2010, 64 (02) :604-609
[49]   Development and validation of a radiomic prediction model for TACC3 expression and prognosis in non-small cell lung cancer using contrast-enhanced CT imaging [J].
Bai, Weichao ;
Zhao, Xinhan ;
Ning, Qian .
TRANSLATIONAL ONCOLOGY, 2025, 51
[50]   RFLSE: Joint radiomics feature-enhanced level-set segmentation for low-contrast SPECT/CT tumour images [J].
Guo, Zhaotong ;
Qin, Pinle ;
Zeng, Jianchao ;
Chai, Rui ;
Wu, Zhifang ;
Zhang, Jinjing ;
Qin, Jia ;
Jin, Zanxia ;
Zhao, Pengcheng ;
Wang, Yixiong .
IET IMAGE PROCESSING, 2024, 18 (10) :2715-2731