Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences

Abstract The aim of this study was to develop a medical imaging and comprehensive stacked learning-based method for predicting high- and low-risk thymoma. A total of 126 patients with thymomas and 5 patients with thymic carcinoma treated at our institution, including 65 low-risk patients and 66 high...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhu Liang, Jiamin Li, Yihan Tang, Yaxuan Zhang, Chunyuan Chen, Siyuan Li, Xuefeng Wang, Xinyan Xu, Ziye Zhuang, Shuyan He, Biao Deng
Format: Article
Language:English
Published: Nature Portfolio 2024-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-69735-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063919704440832
author Zhu Liang
Jiamin Li
Yihan Tang
Yaxuan Zhang
Chunyuan Chen
Siyuan Li
Xuefeng Wang
Xinyan Xu
Ziye Zhuang
Shuyan He
Biao Deng
author_facet Zhu Liang
Jiamin Li
Yihan Tang
Yaxuan Zhang
Chunyuan Chen
Siyuan Li
Xuefeng Wang
Xinyan Xu
Ziye Zhuang
Shuyan He
Biao Deng
author_sort Zhu Liang
collection DOAJ
description Abstract The aim of this study was to develop a medical imaging and comprehensive stacked learning-based method for predicting high- and low-risk thymoma. A total of 126 patients with thymomas and 5 patients with thymic carcinoma treated at our institution, including 65 low-risk patients and 66 high-risk patients, were retrospectively recruited. Among them, 78 patients composed the training cohort, while the remaining 53 patients formed the validation cohort. We extracted 1702 features each from the patients’ arterial-, venous-, and plain-phase images. Pairwise subtraction of these features yielded 1702 arterial-venous, arterial-plain, and venous-plain difference features each. The Mann‒Whitney U test and least absolute shrinkage and selection operator (LASSO) and SelectKBest methods were employed to select the best features from the training set. Six models were built with a stacked learning algorithm. By applying stacked ensemble learning, three machine learning algorithms (XGBoost, multilayer perceptron (MLP), and random forest) were combined by XGBoost to produce the the six basic imaging models. Then, the XGBoost algorithm was applied to the six basic imaging models to construct a combined radiomic model. Finally, the radiomic model was combined with clinical information to create a nomogram that could easily be used in clinical practice to predict the thymoma risk category. The areas under the curve (AUCs) of the combined radiomic model in the training and validation cohorts were 0.999 (95% CI 0.988–1.000) and 0.967 (95% CI 0.916–1.000), respectively, while those of the nomogram were 0.999 (95% CI 0.996–1.000) and 0.983 (95% CI 0.990–1.000). This study describes the application of CT-based radiomics in thymoma patients and proposes a nomogram for predicting the risk category for this disease, which could be advantageous for clinical decision-making for affected patients.
format Article
id doaj-art-95bbfe7b9371493da27a7100680dfa48
institution DOAJ
issn 2045-2322
language English
publishDate 2024-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-95bbfe7b9371493da27a7100680dfa482025-08-20T02:49:26ZengNature PortfolioScientific Reports2045-23222024-08-0114111210.1038/s41598-024-69735-3Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differencesZhu Liang0Jiamin Li1Yihan Tang2Yaxuan Zhang3Chunyuan Chen4Siyuan Li5Xuefeng Wang6Xinyan Xu7Ziye Zhuang8Shuyan He9Biao Deng10Department of Cardiothoracic Surgery, Affiliated Hospital of Guangdong Medical UniversityGuangdong Medical UniversiyGuangdong Medical UniversiyGuangdong Medical UniversiyDepartment of Cardiothoracic Surgery, Affiliated Hospital of Guangdong Medical UniversitySun Yat-Sen UniversityDepartment of Cardiothoracic Surgery, Affiliated Hospital of Guangdong Medical UniversityGuangdong Medical UniversiyGuangdong Medical UniversiyGuangzhou Medical UniversityDepartment of Cardiothoracic Surgery, Affiliated Hospital of Guangdong Medical UniversityAbstract The aim of this study was to develop a medical imaging and comprehensive stacked learning-based method for predicting high- and low-risk thymoma. A total of 126 patients with thymomas and 5 patients with thymic carcinoma treated at our institution, including 65 low-risk patients and 66 high-risk patients, were retrospectively recruited. Among them, 78 patients composed the training cohort, while the remaining 53 patients formed the validation cohort. We extracted 1702 features each from the patients’ arterial-, venous-, and plain-phase images. Pairwise subtraction of these features yielded 1702 arterial-venous, arterial-plain, and venous-plain difference features each. The Mann‒Whitney U test and least absolute shrinkage and selection operator (LASSO) and SelectKBest methods were employed to select the best features from the training set. Six models were built with a stacked learning algorithm. By applying stacked ensemble learning, three machine learning algorithms (XGBoost, multilayer perceptron (MLP), and random forest) were combined by XGBoost to produce the the six basic imaging models. Then, the XGBoost algorithm was applied to the six basic imaging models to construct a combined radiomic model. Finally, the radiomic model was combined with clinical information to create a nomogram that could easily be used in clinical practice to predict the thymoma risk category. The areas under the curve (AUCs) of the combined radiomic model in the training and validation cohorts were 0.999 (95% CI 0.988–1.000) and 0.967 (95% CI 0.916–1.000), respectively, while those of the nomogram were 0.999 (95% CI 0.996–1.000) and 0.983 (95% CI 0.990–1.000). This study describes the application of CT-based radiomics in thymoma patients and proposes a nomogram for predicting the risk category for this disease, which could be advantageous for clinical decision-making for affected patients.https://doi.org/10.1038/s41598-024-69735-3Machine learningCTThymoma
spellingShingle Zhu Liang
Jiamin Li
Yihan Tang
Yaxuan Zhang
Chunyuan Chen
Siyuan Li
Xuefeng Wang
Xinyan Xu
Ziye Zhuang
Shuyan He
Biao Deng
Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences
Scientific Reports
Machine learning
CT
Thymoma
title Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences
title_full Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences
title_fullStr Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences
title_full_unstemmed Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences
title_short Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences
title_sort predicting the risk category of thymoma with machine learning based computed tomography radiomics signatures and their between imaging phase differences
topic Machine learning
CT
Thymoma
url https://doi.org/10.1038/s41598-024-69735-3
work_keys_str_mv AT zhuliang predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT jiaminli predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT yihantang predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT yaxuanzhang predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT chunyuanchen predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT siyuanli predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT xuefengwang predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT xinyanxu predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT ziyezhuang predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT shuyanhe predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences
AT biaodeng predictingtheriskcategoryofthymomawithmachinelearningbasedcomputedtomographyradiomicssignaturesandtheirbetweenimagingphasedifferences