An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer

Abstract Objective To investigate whether radiomics based on ultrasound images can predict lymphovascular invasion (LVI) of rectal cancer (RC) before surgery. Methods A total of 203 patients with RC were enrolled retrospectively, and they were divided into a training set (143 patients) and a validat...

Full description

Bibliographic Details
Main Authors: Yu-quan Wu, Rui-zhi Gao, Peng Lin, Rong Wen, Hai-yuan Li, Mei-yan Mou, Feng-huan Chen, Fen Huang, Wei-jie Zhou, Hong Yang, Yun He, Ji Wu
Format: Article
Language:English
Published: BMC 2022-05-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-022-00813-6
_version_ 1817988225558380544
author Yu-quan Wu
Rui-zhi Gao
Peng Lin
Rong Wen
Hai-yuan Li
Mei-yan Mou
Feng-huan Chen
Fen Huang
Wei-jie Zhou
Hong Yang
Yun He
Ji Wu
author_facet Yu-quan Wu
Rui-zhi Gao
Peng Lin
Rong Wen
Hai-yuan Li
Mei-yan Mou
Feng-huan Chen
Fen Huang
Wei-jie Zhou
Hong Yang
Yun He
Ji Wu
author_sort Yu-quan Wu
collection DOAJ
description Abstract Objective To investigate whether radiomics based on ultrasound images can predict lymphovascular invasion (LVI) of rectal cancer (RC) before surgery. Methods A total of 203 patients with RC were enrolled retrospectively, and they were divided into a training set (143 patients) and a validation set (60 patients). We extracted the radiomic features from the largest gray ultrasound image of the RC lesion. The intraclass correlation coefficient (ICC) was applied to test the repeatability of the radiomic features. The least absolute shrinkage and selection operator (LASSO) was used to reduce the data dimension and select significant features. Logistic regression (LR) analysis was applied to establish the radiomics model. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the comprehensive performance of the model. Results Among the 203 patients, 33 (16.7%) were LVI positive and 170 (83.7%) were LVI negative. A total of 5350 (90.1%) radiomic features with ICC values of ≥ 0.75 were reported, which were subsequently subjected to hypothesis testing and LASSO regression dimension reduction analysis. Finally, 15 selected features were used to construct the radiomics model. The area under the curve (AUC) of the training set was 0.849, and the AUC of the validation set was 0.781. The calibration curve indicated that the radiomics model had good calibration, and DCA demonstrated that the model had clinical benefits. Conclusion The proposed endorectal ultrasound-based radiomics model has the potential to predict LVI preoperatively in RC.
first_indexed 2024-04-14T00:31:35Z
format Article
id doaj.art-f62a48df01b642358ee28a09079601a4
institution Directory Open Access Journal
issn 1471-2342
language English
last_indexed 2024-04-14T00:31:35Z
publishDate 2022-05-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj.art-f62a48df01b642358ee28a09079601a42022-12-22T02:22:32ZengBMCBMC Medical Imaging1471-23422022-05-0122111010.1186/s12880-022-00813-6An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancerYu-quan Wu0Rui-zhi Gao1Peng Lin2Rong Wen3Hai-yuan Li4Mei-yan Mou5Feng-huan Chen6Fen Huang7Wei-jie Zhou8Hong Yang9Yun He10Ji Wu11Department of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityThe Second Clinical Medical College, Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityAbstract Objective To investigate whether radiomics based on ultrasound images can predict lymphovascular invasion (LVI) of rectal cancer (RC) before surgery. Methods A total of 203 patients with RC were enrolled retrospectively, and they were divided into a training set (143 patients) and a validation set (60 patients). We extracted the radiomic features from the largest gray ultrasound image of the RC lesion. The intraclass correlation coefficient (ICC) was applied to test the repeatability of the radiomic features. The least absolute shrinkage and selection operator (LASSO) was used to reduce the data dimension and select significant features. Logistic regression (LR) analysis was applied to establish the radiomics model. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the comprehensive performance of the model. Results Among the 203 patients, 33 (16.7%) were LVI positive and 170 (83.7%) were LVI negative. A total of 5350 (90.1%) radiomic features with ICC values of ≥ 0.75 were reported, which were subsequently subjected to hypothesis testing and LASSO regression dimension reduction analysis. Finally, 15 selected features were used to construct the radiomics model. The area under the curve (AUC) of the training set was 0.849, and the AUC of the validation set was 0.781. The calibration curve indicated that the radiomics model had good calibration, and DCA demonstrated that the model had clinical benefits. Conclusion The proposed endorectal ultrasound-based radiomics model has the potential to predict LVI preoperatively in RC.https://doi.org/10.1186/s12880-022-00813-6UltrasoundRadiomicsModelRectal cancerLymphovascular invasion
spellingShingle Yu-quan Wu
Rui-zhi Gao
Peng Lin
Rong Wen
Hai-yuan Li
Mei-yan Mou
Feng-huan Chen
Fen Huang
Wei-jie Zhou
Hong Yang
Yun He
Ji Wu
An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
BMC Medical Imaging
Ultrasound
Radiomics
Model
Rectal cancer
Lymphovascular invasion
title An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
title_full An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
title_fullStr An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
title_full_unstemmed An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
title_short An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
title_sort endorectal ultrasound based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer
topic Ultrasound
Radiomics
Model
Rectal cancer
Lymphovascular invasion
url https://doi.org/10.1186/s12880-022-00813-6
work_keys_str_mv AT yuquanwu anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT ruizhigao anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT penglin anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT rongwen anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT haiyuanli anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT meiyanmou anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT fenghuanchen anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT fenhuang anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT weijiezhou anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT hongyang anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT yunhe anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT jiwu anendorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT yuquanwu endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT ruizhigao endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT penglin endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT rongwen endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT haiyuanli endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT meiyanmou endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT fenghuanchen endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT fenhuang endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT weijiezhou endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT hongyang endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT yunhe endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer
AT jiwu endorectalultrasoundbasedradiomicssignatureforpreoperativepredictionoflymphovascularinvasionofrectalcancer