Retrospective Study
Copyright ©The Author(s) 2024. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Oncol. Mar 15, 2024; 16(3): 819-832
Published online Mar 15, 2024. doi: 10.4251/wjgo.v16.i3.819
T2-weighted imaging-based radiomic-clinical machine learning model for predicting the differentiation of colorectal adenocarcinoma
Hui-Da Zheng, Qiao-Yi Huang, Qi-Ming Huang, Xiao-Ting Ke, Kai Ye, Shu Lin, Jian-Hua Xu
Hui-Da Zheng, Kai Ye, Jian-Hua Xu, Department of Gastrointestinal Surgery, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, Fujian Province, China
Qiao-Yi Huang, Department of Gynaecology and Obstetrics, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, Fujian Province, China
Qi-Ming Huang, Xiao-Ting Ke, Department of Computed Tomography/Magnetic Resonance Imaging, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, Fujian Province, China
Shu Lin, Centre of Neurological and Metabolic Research, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, Fujian Province, China
Shu Lin, Group of Neuroendocrinology, Garvan Institute of Medical Research, Sydney, NSW 2010, Australia
Co-corresponding authors: Shu Lin and Jian-Hua Xu.
Author contributions: Zheng HD and Huang QY provided the concept and designed; Zheng HD, Huang QM and Ke XT performed image interpretation and segmentation; Xu JH, Lin S and Ye K provided clinical advice, reviewed the manuscript and gave final approval of the version of the article to be published; Xu JH and Lin S contributed equally to this work as co-corresponding authors. The study was completed with the participation of multiple members, and the designation of the co-corresponding author accurately reflected the allocation of responsibilities and burdens related to the time and effort required to complete the study and the resulting paper. Xu JH and Lin S both gave great help in the study process. Because the study belongs to clinical study, the corresponding authors provided a large number of clinical opinions, reviewed the manuscript in detail and carefully, and finally approved the publication of the manuscript. These researchers were selected as co-corresponding authors, recognizing and respecting this equal contribution. In conclusion, we think it is appropriate to designate Xu JH and Lin S as the co-corresponding authors, because this can reflect the actual contributions of these authors.
Supported by the Fujian Province Clinical Key Specialty Construction Project, No. 2022884; Quanzhou Science and Technology Plan Project, No. 2021N034S; The Youth Research Project of Fujian Provincial Health Commission, No. 2022QNA067; Malignant Tumor Clinical Medicine Research Center, No. 2020N090s.
Institutional review board statement: The study was reviewed and approved for publication by Institutional Reviewer of The Second Affiliated Hospital of Fujian Medical University (No. 2023-429).
Informed consent statement: As the study used anonymous and pre-existing data, the requirement for the informed consent from patients was waived.
Conflict-of-interest statement: All the Authors have no conflict of interest related to the manuscript.
Data sharing statement: The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.
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: Jian-Hua Xu, MD, Chief Physician, Dean, Research Dean, Surgeon, Surgical Oncologist, Department of Gastrointestinal Surgery, The Second Affiliated Hospital of Fujian Medical University, No. 950 Donghai Street, Fengze District, Quanzhou 362000, Fujian Province, China. xjh630913@126.com
Received: October 9, 2023
Peer-review started: October 9, 2023
First decision: December 6, 2023
Revised: December 30, 2023
Accepted: January 29, 2024
Article in press: January 29, 2024
Published online: March 15, 2024
Processing time: 154 Days and 20.2 Hours
Abstract
BACKGROUND

The study on predicting the differentiation grade of colorectal cancer (CRC) based on magnetic resonance imaging (MRI) has not been reported yet. Developing a non-invasive model to predict the differentiation grade of CRC is of great value.

AIM

To develop and validate machine learning-based models for predicting the differentiation grade of CRC based on T2-weighted images (T2WI).

METHODS

We retrospectively collected the preoperative imaging and clinical data of 315 patients with CRC who underwent surgery from March 2018 to July 2023. Patients were randomly assigned to a training cohort (n = 220) or a validation cohort (n = 95) at a 7:3 ratio. Lesions were delineated layer by layer on high-resolution T2WI. Least absolute shrinkage and selection operator regression was applied to screen for radiomic features. Radiomics and clinical models were constructed using the multilayer perceptron (MLP) algorithm. These radiomic features and clinically relevant variables (selected based on a significance level of P < 0.05 in the training set) were used to construct radiomics-clinical models. The performance of the three models (clinical, radiomic, and radiomic-clinical model) were evaluated using the area under the curve (AUC), calibration curve and decision curve analysis (DCA).

RESULTS

After feature selection, eight radiomic features were retained from the initial 1781 features to construct the radiomic model. Eight different classifiers, including logistic regression, support vector machine, k-nearest neighbours, random forest, extreme trees, extreme gradient boosting, light gradient boosting machine, and MLP, were used to construct the model, with MLP demonstrating the best diagnostic performance. The AUC of the radiomic-clinical model was 0.862 (95%CI: 0.796-0.927) in the training cohort and 0.761 (95%CI: 0.635-0.887) in the validation cohort. The AUC for the radiomic model was 0.796 (95%CI: 0.723-0.869) in the training cohort and 0.735 (95%CI: 0.604-0.866) in the validation cohort. The clinical model achieved an AUC of 0.751 (95%CI: 0.661-0.842) in the training cohort and 0.676 (95%CI: 0.525-0.827) in the validation cohort. All three models demonstrated good accuracy. In the training cohort, the AUC of the radiomic-clinical model was significantly greater than that of the clinical model (P = 0.005) and the radiomic model (P = 0.016). DCA confirmed the clinical practicality of incorporating radiomic features into the diagnostic process.

CONCLUSION

In this study, we successfully developed and validated a T2WI-based machine learning model as an auxiliary tool for the preoperative differentiation between well/moderately and poorly differentiated CRC. This novel approach may assist clinicians in personalizing treatment strategies for patients and improving treatment efficacy.

Keywords: Radiomics, Colorectal cancer, Differentiation grade, Machine learning, T2-weighted imaging

Core Tip: In this study, a T2-weighted imaging-based radiomic-clinical machine learning model was developed to preoperatively predict the histological grade of colorectal cancer (CRC). The model showed good performance in both the training and validation cohorts. It provides an effective tool for accurately assessing the differentiation grade of CRC tissue before surgery, which is highly important for selecting the best treatment plan and predicting patient prognosis.