Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity
The British Journal of Radiology · 01.01.2023 · 96 (1141)
DOI: 10.1259/bjr.20220512 ↗Kurz gefasst
Fachartikel in der Zeitschrift The British Journal of Radiology, online erschienen am 21.11.2022. Verfasst von Huanhuan Wei und 10 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Medical Sciences, the People's Hospital of Zhengzhou University, Zhengzhou, Henan, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Liver Cirrhosis. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Objective
To evaluate the value of radiomics models created based on non-contrast enhanced T 1 weighted (T 1W) and T 2W fat-saturated (T 2WFS) images for staging hepatic fibrosis (HF) and grading inflammatory activity. Methods and materials: Data of 280 patients with pathologically confirmed HF and 48 healthy volunteers were included. The participants were divided into the training set and the test set at the proportion of 4:1 by the random seed method. We used the Pyradiomics software to extract radiomics features, and then use the least absolute shrinkage and selection operator to select the optimal subset. Finally, we used the stochastic gradient descent classifier to build the prediction models. DeLong test was used to compare the diagnostic performance of the models. Receiver operating characteristics was used to evaluate the prediction ability of the models.
Results
The diagnostic efficiency of the models based on T 1W & T 2WFS images were the highest (all p < 0.05). When discriminating significant fibrosis (≥ F2), there were significant differences in the AUCs between the machine learning models based on T 1W and T 2WFS images (p < 0.05), but there were no significant differences in area under the receiver operating characteristic curves between the two models in other groups (all p > 0.05).
Conclusion
The radiomics models built on T 1W and T 2WFS images are effective in assessing HF and inflammatory activity. Advances in knowledge: Based on conventional MR sequences that are readily available in the clinic, namely unenhanced T 1W and T 2W images. Radiomics can be used for diagnosis and differential diagnosis of liver fibrosis staging and inflammatory activity grading.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Academy of Medical Sciences, the People's Hospital of Zhengzhou University, Zhengzhou, Henan, China.
- Heart Center of Zhengzhou University People's Hospital, Henan Provincial People's Hospital, Zhengzhou, Henan Province, China.
- Department of Medical Imaging, Henan Provincial People's Hospital & the People's Hospital of Zhengzhou University, Zhengzhou, Henan, China.
- The First People's Hospital of Zhoukou, Zhoukou, Henan, China.
- Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Zitieren
APA
Wei, H., Shao, Z., Fu, F., Yu, X., Wu, Y., Bai, Y., Wei, W., Meng, N., Liu, K., Han, H., & Wang, M. (2023). Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity. The British Journal of Radiology, 96(1141). https://doi.org/10.1259/bjr.20220512
Vancouver
Wei H, Shao Z, Fu F, Yu X, Wu Y, Bai Y, et al. Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity. The British Journal of Radiology. 2023;96(1141). doi:10.1259/bjr.20220512
BibTeX
@article{Wei2023,
author = {Wei, Huanhuan and Shao, Zehua and Fu, Fangfang and Yu, Xuan and Wu, Yaping and Bai, Yan and Wei, Wei and Meng, Nan and Liu, Kewei and Han, Hui and Wang, Meiyun},
title = {Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity},
journal = {The British Journal of Radiology},
year = {2023},
volume = {96},
number = {1141},
doi = {10.1259/bjr.20220512}
}
EUVIMED