Discrimination between benign and malignant gallbladder lesions on enhanced CT imaging using radiomics
Acta Radiologica · 2024
DOI: 10.1177/02841851241242042 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Radiologica, 2024. Verfasst von Ying-Ying Zhuang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Departments of Imaging, The Affiliated Huai'an No 1 People's Hospital of Nanjing Medical University, Huai'an, Jiangsu, PR China. Hauptthemen laut MEDLINE: Gallbladder Neoplasms, Tomography, X-Ray Computed, Gallbladder, Contrast Media. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 23 Literaturangaben.
Abstract (Originalsprache)
Background
Gallbladder cancer is a rare but aggressive malignancy that is often diagnosed at an advanced stage and is associated with poor outcomes.
Purpose
To develop a radiomics model to discriminate between benign and malignant gallbladder lesions using enhanced computed tomography (CT) imaging. Material and Methods All patients had a preoperative contrast-enhanced CT scan, which was independently analyzed by two radiologists. Regions of interest were manually delineated on portal venous phase images, and radiomics features were extracted. Feature selection was performed using mRMR and LASSO methods. The patients were randomly divided into training and test groups at a ratio of 7:3. Clinical and radiomics parameters were identified in the training group, three models were constructed, and the models’ prediction accuracy and ability were evaluated using AUC and calibration curves.
Results
In the training group, the AUCs of the clinical model and radiomics model were 0.914 and 0.968, and that of the nomogram model was 0.980, respectively. There were statistically significant differences in diagnostic accuracy between nomograms and radiomics features ( P 0.05) or between the clinical features and radiomics features ( P >0.05). In the testing group, the AUC of the clinical model and radiomics model were 0.904 and 0.941, and that of the nomogram model was 0.948, respectively. There was no significant difference in diagnostic accuracy between the three groups ( P >0.05).
Conclusion
It was suggested that radiomics analysis using enhanced CT imaging can effectively discriminate between benign and malignant gallbladder lesions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Departments of Imaging, The Affiliated Huai'an No 1 People's Hospital of Nanjing Medical University, Huai'an, Jiangsu, PR China.
ORCID-Profile: Ying-Ying Zhuang, Li-Li Guo
Zitieren
APA
Zhuang, Y. Y., Feng, Y., Kong, D., & Guo, L. L. (2024). Discrimination between benign and malignant gallbladder lesions on enhanced CT imaging using radiomics. Acta Radiologica. https://doi.org/10.1177/02841851241242042
Vancouver
Zhuang YY, Feng Y, Kong D, Guo LL. Discrimination between benign and malignant gallbladder lesions on enhanced CT imaging using radiomics. Acta Radiologica. 2024. doi:10.1177/02841851241242042
BibTeX
@article{Zhuang2024,
author = {Zhuang, Ying-Ying and Feng, Yun and Kong, Dan and Guo, Li-Li},
title = {Discrimination between benign and malignant gallbladder lesions on enhanced CT imaging using radiomics},
journal = {Acta Radiologica},
year = {2024},
doi = {10.1177/02841851241242042}
}
EUVIMED