Xiao MJ, Pan YT, Tan JH, Li HO, Wang HY. Computed tomography-based radiomics combined with machine learning allows differentiation between primary intestinal lymphoma and Crohn's disease. World J Gastroenterol 2024; 30(25): 3155-3165 [PMID: 39006389 DOI: 10.3748/wjg.v30.i25.3155]
Corresponding Author of This Article
Hai-Yan Wang, MD, PhD, Professor, Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, No. 324 Jingwu Road, Jinan 250021, Shandong Province, China. whyott@163.com
Research Domain of This Article
Radiology, Nuclear Medicine & Medical Imaging
Article-Type of This Article
Retrospective Study
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
World J Gastroenterol. Jul 7, 2024; 30(25): 3155-3165 Published online Jul 7, 2024. doi: 10.3748/wjg.v30.i25.3155
Computed tomography-based radiomics combined with machine learning allows differentiation between primary intestinal lymphoma and Crohn's disease
Meng-Jun Xiao, Yu-Teng Pan, Jia-He Tan, Hai-Ou Li, Hai-Yan Wang
Meng-Jun Xiao, Hai-Yan Wang, Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan 250021, Shandong Province, China
Yu-Teng Pan, Medical Science and Technology Innovation Center, Shandong First Medical University & Shandong Academy of Medical Sciences, Jinan 250000, Shandong Province, China
Jia-He Tan, University of California, Davis, CA 95616, United States
Hai-Ou Li, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan 250012, Shandong Province, China
Co-first authors: Meng-Jun Xiao and Yu-Teng Pan.
Author contributions: Xiao MJ and Pan YT have the equal contribution to the manuscript; Xiao MJ, Pan YT, and Wang HY contributed to the conception and design of the research, they also contributed to the revision of manuscript for important intellectual content; Xiao MJ, Pan YT and Li HO contributed to the acquisition of data; Xiao MJ and Pan YT contributed to the analysis and interpretation of data and contributed to the drafting the manuscript; Wang HY contributed to the obtaining funding; All authors have read and approve the final manuscript.
Supported byKey Technology Research and Development Program of Shandong Province, China, No. 2021SFGC0104.
Institutional review board statement: This study was reviewed and approved by the Ethics Committee of Shandong Provincial Hospital Affiliated to Shandong First Medical University, China, NO. 2023-422.
Informed consent statement: Informed consent has been obtained for the publication of experimental data and images.
Conflict-of-interest statement: We have no financial relationships to disclose.
Data sharing statement: No additional data are available.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Hai-Yan Wang, MD, PhD, Professor, Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, No. 324 Jingwu Road, Jinan 250021, Shandong Province, China. whyott@163.com
Received: January 9, 2024 Revised: May 20, 2024 Accepted: June 7, 2024 Published online: July 7, 2024 Processing time: 174 Days and 4.2 Hours
Abstract
BACKGROUND
Due to similar clinical manifestations and imaging signs, differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical practice.
AIM
To investigate the ability of radiomics combined with machine learning methods to differentiate PIL from CD.
METHODS
We collected contrast-enhanced computed tomography (CECT) and clinical data from 120 patients form center 1. A total of 944 features were extracted single-phase images of CECT scans. Using the last absolute shrinkage and selection operator model, the best predictive radiographic features and clinical indications were screened. Data from 54 patients were collected at center 2 as an external validation set to verify the robustness of the model. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity were used for evaluation.
RESULTS
A total of five machine learning models were built to distinguish PIL from CD. Based on the results from the test group, most models performed well with a large area under the curve (AUC) (> 0.850) and high accuracy (> 0.900). The combined clinical and radiomics model (AUC = 1.000, accuracy = 1.000) was the best model among all models.
CONCLUSION
Based on machine learning, a model combining clinical data with radiologic features was constructed that can effectively differentiate PIL from CD.
Core Tip: In the present study employed radiomics to extract features from computed tomography images of primary intestinal lymphoma and Crohn's disease, followed by the construction of machine learning models for improved differentiation between these two conditions. The least absolute shrinkage and selection operator regression model with 5-fold cross validation was utilized for feature selection, resulting in the identification of 13 optimal predictive radiomics features along with 4 clinical features. Ultimately, all phase models incorporating radiomics features and a combined model integrating both radiomics and clinical features were developed.