CT imaging-based radiomics signatures improve prognosis prediction in postoperative colorectal cancer
Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics · 15.11.2023 · 31 (6) · 1281-1294
DOI: 10.3233/xst-230090 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics, online erschienen am 18.08.2023. Verfasst von Yan Kong und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China. Hauptthemen laut MEDLINE: Colorectal Neoplasms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 19 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVE: To investigate the use of non-contrast-enhanced (NCE) and contrast-enhanced (CE) CT radiomics signatures (Rad-scores) as prognostic factors to help improve the prediction of the overall survival (OS) of postoperative colorectal cancer (CRC) patients. METHODS: A retrospective analysis was performed on 65 CRC patients who underwent surgical resection in our hospital as the training set, and 19 patient images retrieved from The Cancer Imaging Archive (TCIA) as the external validation set. In training, radiomics features were extracted from the preoperative NCE/CE-CT, then selected through 5-fold cross validation LASSO Cox method and used to construct Rad-scores. Models derived from Rad-scores and clinical factors were constructed and compared. Kaplan-Meier analyses were also used to compare the survival probability between the high- and low-risk Rad-score groups. Finally, a nomogram was developed to predict the OS. RESULTS: In training, a clinical model achieved a C-index of 0.796 (95% CI: 0.722–0.870), while clinical and two Rad-scores combined model performed the best, achieving a C-index of 0.821 (95% CI: 0.743–0.899). Furthermore, the models with the CE-CT Rad-score yielded slightly better performance than that of NCE-CT in training. For the combined model with CE-CT Rad-scores, a C-index of 0.818 (95% CI: 0.742–0.894) and 0.774 (95% CI: 0.556–0.992) were achieved in both the training and validation sets. Kaplan-Meier analysis demonstrated a significant difference in survival probability between the high- and low-risk groups. Finally, the areas under the receiver operating characteristics (ROC) curves for the model were 0.904, 0.777, and 0.843 for 1, 3, and 5-year survival, respectively. CONCLUSION: NCE-CT or CE-CT radiomics and clinical combined models can predict the OS for CRC patients, and both Rad-scores are recommended to be included when available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China.
- Department of Radiation Oncology, Dushu Lake Hospital Affiliated to Soochow University, Medical Center of Soochow University, Suzhou, Jiangsu, China.
- Wuxi Cancer Institute, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu, China.
- Department of Diagnostic and Interventional Radiology, University of Tsukuba, Ibaraki, Japan.
Zitieren
APA
Kong, Y., Xu, M., Wei, X., Qian, D., Yin, Y., Huang, Z., Gu, W., & Zhou, L. (2023). CT imaging-based radiomics signatures improve prognosis prediction in postoperative colorectal cancer. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics, 31(6), 1281-1294. https://doi.org/10.3233/xst-230090
Vancouver
Kong Y, Xu M, Wei X, Qian D, Yin Y, Huang Z, et al. CT imaging-based radiomics signatures improve prognosis prediction in postoperative colorectal cancer. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics. 2023;31(6):1281-1294. doi:10.3233/xst-230090
BibTeX
@article{Kong2023,
author = {Kong, Yan and Xu, Muchen and Wei, Xianding and Qian, Danqi and Yin, Yuan and Huang, Zhaohui and Gu, Wenchao and Zhou, Leyuan},
title = {CT imaging-based radiomics signatures improve prognosis prediction in postoperative colorectal cancer},
journal = {Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics},
year = {2023},
volume = {31},
number = {6},
pages = {1281--1294},
doi = {10.3233/xst-230090}
}
EUVIMED