Different CT slice thickness and contrast‐enhancement phase in radiomics models on the differential performance of lung adenocarcinoma
Abstract
Abstract Background To investigate the effects of computed tomography (CT) reconstruction slice thickness and contrast‐enhancement phase on the differential diagnosis performance of radiomic signature in lung adenocarcinoma. Methods A total of 187 patients who had been pathologically confirmed with lung adenocarcinoma and nonadenocarcinoma were divided into a training cohort ( n = 149) and validation cohort ( n = 38). All the patients underwent contrast‐enhanced CT and the images were reconstructed with different slice thickness. The radiomic features were extracted from different slice thickness and scan phase. The logistic regression (LR) algorithm was used to build a machine learning model for each group. The area under the curve (AUC) obtained from the receiver operating characteristic (ROC) curve and DeLong test was used to evaluate its discriminating performance. Results Finally, 34 image features and five semantic features were selected to establish a radiomics model. Based on the three contrast‐enhanced CT phases and four reconstruction slice thickness, 12 groups of radiomics models showed good discrimination ability with the AUCs range from 0.9287 to 0.9631, sensitivity range from 0.8349 to 0.9083, specificity range from 0.825 to 0.925 in the training group. Similar results were observed in the validation group. However, there was no statistical significancemore »
- Authors:
-
- Department of Radiology, Shandong Provincial Hospital Shandong University Jinan Shandong China
- Department of Radiology Shandong Provincial Hospital Affiliated to Shandong First Medical University Jinan Shandong China
- Department of Research Collaboration, R&,D center Beijing Deepwise &, League of PHD Technology Co., Ltd Beijing China
- Department of Thoracic Surgery, Chengxin Hospital Yuncheng Shandong China
- Department of Thoracic Surgery Shandong Provincial Hospital, Shandong University Jinan Shandong China
- Department of Thoracic Surgery Shandong Provincial Hospital Affiliated to Shandong First Medical University Jinan Shandong China
- Publication Date:
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1867291
- Alternate Identifier(s):
- OSTI ID: 1867292
- Resource Type:
- Published Article
- Journal Name:
- Thoracic Cancer
- Additional Journal Information:
- Journal Name: Thoracic Cancer Journal Volume: 13 Journal Issue: 12; Journal ID: ISSN 1759-7706
- Publisher:
- Wiley-Blackwell
- Country of Publication:
- Australia
- Language:
- English
Citation Formats
Wang, Yang, Liu, Fang, Mo, Yan, Huang, Chencui, Chen, Yingxin, Chen, Fuliang, Zhang, Xiangwei, Yin, Yunxin, Liu, Qiang, and Zhang, Lin. Different CT slice thickness and contrast‐enhancement phase in radiomics models on the differential performance of lung adenocarcinoma. Australia: N. p., 2022.
Web. doi:10.1111/1759-7714.14459.
Wang, Yang, Liu, Fang, Mo, Yan, Huang, Chencui, Chen, Yingxin, Chen, Fuliang, Zhang, Xiangwei, Yin, Yunxin, Liu, Qiang, & Zhang, Lin. Different CT slice thickness and contrast‐enhancement phase in radiomics models on the differential performance of lung adenocarcinoma. Australia. https://doi.org/10.1111/1759-7714.14459
Wang, Yang, Liu, Fang, Mo, Yan, Huang, Chencui, Chen, Yingxin, Chen, Fuliang, Zhang, Xiangwei, Yin, Yunxin, Liu, Qiang, and Zhang, Lin. Wed .
"Different CT slice thickness and contrast‐enhancement phase in radiomics models on the differential performance of lung adenocarcinoma". Australia. https://doi.org/10.1111/1759-7714.14459.
@article{osti_1867291,
title = {Different CT slice thickness and contrast‐enhancement phase in radiomics models on the differential performance of lung adenocarcinoma},
author = {Wang, Yang and Liu, Fang and Mo, Yan and Huang, Chencui and Chen, Yingxin and Chen, Fuliang and Zhang, Xiangwei and Yin, Yunxin and Liu, Qiang and Zhang, Lin},
abstractNote = {Abstract Background To investigate the effects of computed tomography (CT) reconstruction slice thickness and contrast‐enhancement phase on the differential diagnosis performance of radiomic signature in lung adenocarcinoma. Methods A total of 187 patients who had been pathologically confirmed with lung adenocarcinoma and nonadenocarcinoma were divided into a training cohort ( n = 149) and validation cohort ( n = 38). All the patients underwent contrast‐enhanced CT and the images were reconstructed with different slice thickness. The radiomic features were extracted from different slice thickness and scan phase. The logistic regression (LR) algorithm was used to build a machine learning model for each group. The area under the curve (AUC) obtained from the receiver operating characteristic (ROC) curve and DeLong test was used to evaluate its discriminating performance. Results Finally, 34 image features and five semantic features were selected to establish a radiomics model. Based on the three contrast‐enhanced CT phases and four reconstruction slice thickness, 12 groups of radiomics models showed good discrimination ability with the AUCs range from 0.9287 to 0.9631, sensitivity range from 0.8349 to 0.9083, specificity range from 0.825 to 0.925 in the training group. Similar results were observed in the validation group. However, there was no statistical significance between the different CT scan phase groups and different slice thickness ( p > 0.05). Conclusions The radiomic analysis of contrast‐enhanced CT can be used for the differential diagnosis of lung adenocarcinoma. Moreover, different slice thickness and contrast‐enhanced scan phase did not affect the discriminating ability in the radiomics models.},
doi = {10.1111/1759-7714.14459},
journal = {Thoracic Cancer},
number = 12,
volume = 13,
place = {Australia},
year = {2022},
month = {5}
}
https://doi.org/10.1111/1759-7714.14459
Works referenced in this record:
The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping
journal, May 2020
- Zwanenburg, Alex; Vallières, Martin; Abdalah, Mahmoud A.
- Radiology, Vol. 295, Issue 2
Radiomics and radiogenomics in lung cancer: A review for the clinician
journal, January 2018
- Thawani, Rajat; McLane, Michael; Beig, Niha
- Lung Cancer, Vol. 115
CT Slice Thickness and Convolution Kernel Affect Performance of a Radiomic Model for Predicting EGFR Status in Non-Small Cell Lung Cancer: A Preliminary Study
journal, December 2018
- Li, Yajun; Lu, Lin; Xiao, Manjun
- Scientific Reports, Vol. 8, Issue 1
Radiomics: Images Are More than Pictures, They Are Data
journal, February 2016
- Gillies, Robert J.; Kinahan, Paul E.; Hricak, Hedvig
- Radiology, Vol. 278, Issue 2
Quantitative Image Quality and Histogram-Based Evaluations of an Iterative Reconstruction Algorithm at Low-to-Ultralow Radiation Dose Levels: A Phantom Study in Chest CT
journal, January 2018
- Lee, Ki Baek; Goo, Hyun Woo
- Korean Journal of Radiology, Vol. 19, Issue 1
CT-based radiomics signature for differentiating solitary granulomatous nodules from solid lung adenocarcinoma
journal, November 2018
- Yang, Xinguan; He, Jianxing; Wang, Jiao
- Lung Cancer, Vol. 125
Computerized Texture Analysis of Persistent Part-Solid Ground-Glass Nodules: Differentiation of Preinvasive Lesions from Invasive Pulmonary Adenocarcinomas
journal, October 2014
- Chae, Hee-Dong; Park, Chang Min; Park, Sang Joon
- Radiology, Vol. 273, Issue 1
Intraclass correlations: Uses in assessing rater reliability.
journal, January 1979
- Shrout, Patrick E.; Fleiss, Joseph L.
- Psychological Bulletin, Vol. 86, Issue 2
Spatial registration and normalization of images
journal, January 1995
- Friston, Karl. J.; Ashburner, J.; Frith, C. D.
- Human Brain Mapping, Vol. 3, Issue 3
Machine learning-based radiomics strategy for prediction of cell proliferation in non-small cell lung cancer
journal, September 2019
- Gu, Qianbiao; Feng, Zhichao; Liang, Qi
- European Journal of Radiology, Vol. 118
Tumor segmentation analysis at different post-contrast time points: A possible source of variability of quantitative DCE-MRI parameters in locally advanced breast cancer
journal, May 2020
- Romeo, Valeria; Cavaliere, Carlo; Imbriaco, Massimo
- European Journal of Radiology, Vol. 126
Potential Application of Radiomics for Differentiating Solitary Pulmonary Nodules
journal, January 2016
- Wei, Kaikai; Su, Huifang
- OMICS Journal of Radiology, Vol. 05, Issue 02
Lung Cancer 2020
journal, March 2020
- Bade, Brett C.; Dela Cruz, Charles S.
- Clinics in Chest Medicine, Vol. 41, Issue 1
Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach
journal, September 1988
- DeLong, Elizabeth R.; DeLong, David M.; Clarke-Pearson, Daniel L.
- Biometrics, Vol. 44, Issue 3
Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule
journal, October 2016
- He, Lan; Huang, Yanqi; Ma, Zelan
- Scientific Reports, Vol. 6, Issue 1
Radiomics: the process and the challenges
journal, November 2012
- Kumar, Virendra; Gu, Yuhua; Basu, Satrajit
- Magnetic Resonance Imaging, Vol. 30, Issue 9
The 2015 World Health Organization Classification of Lung Tumors
journal, September 2015
- Travis, William D.; Brambilla, Elisabeth; Nicholson, Andrew G.
- Journal of Thoracic Oncology, Vol. 10, Issue 9
Radiomics Approach to Prediction of Occult Mediastinal Lymph Node Metastasis of Lung Adenocarcinoma
journal, July 2018
- Zhong, Yan; Yuan, Mei; Zhang, Teng
- American Journal of Roentgenology, Vol. 211, Issue 1
Radiomics: the bridge between medical imaging and personalized medicine
journal, October 2017
- Lambin, Philippe; Leijenaar, Ralph T. H.; Deist, Timo M.
- Nature Reviews Clinical Oncology, Vol. 14, Issue 12
B-spline interpolation technique for digital signal processing
conference, July 2015
- Svoboda, Marcus; Matiu-Iovan, Liliana; Frigura-Iliasa, Flaviu Mihai
- 2015 International Conference on Information and Digital Technologies (IDT)