A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors

Abstract Objectives Post-surgical prediction of recurrence or metastasis for primary gastrointestinal stromal tumors (GISTs) remains challenging. We aim to develop individualized clinical follow-up strategies for primary GIST patients, such as shortening follow-up time or extending drug administrati...

Full description

Saved in:
Bibliographic Details
Main Authors: WenJie Xie, Zhen Zhang, Zhao Sun, XiaoChen Wan, JieHan Li, JianWu Jiang, Qi Liu, Ge Yang, Yang Fu
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Insights into Imaging
Subjects:
Online Access:https://doi.org/10.1186/s13244-025-02011-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849420408264065024
author WenJie Xie
Zhen Zhang
Zhao Sun
XiaoChen Wan
JieHan Li
JianWu Jiang
Qi Liu
Ge Yang
Yang Fu
author_facet WenJie Xie
Zhen Zhang
Zhao Sun
XiaoChen Wan
JieHan Li
JianWu Jiang
Qi Liu
Ge Yang
Yang Fu
author_sort WenJie Xie
collection DOAJ
description Abstract Objectives Post-surgical prediction of recurrence or metastasis for primary gastrointestinal stromal tumors (GISTs) remains challenging. We aim to develop individualized clinical follow-up strategies for primary GIST patients, such as shortening follow-up time or extending drug administration based on the clinical deep learning radiomics model (CDLRM). Methods The clinical information on primary GISTs was collected from two independent centers. Postoperative recurrence or metastasis in GIST patients was defined as the endpoint of the study. A total of nine machine learning models were established based on the selected features. The performance of the models was assessed by calculating the area under the curve (AUC). The CDLRM with the best predictive performance was constructed. Decision curve analysis (DCA) and calibration curves were analyzed separately. Ultimately, our model was applied to the high-potential malignant group vs the low-malignant-potential group. The optimal clinical application scenarios of the model were further explored by comparing the DCA performance of the two subgroups. Results A total of 526 patients, 260 men and 266 women, with a mean age of 62 years, were enrolled in the study. CDLRM performed excellently with AUC values of 0.999, 0.963, and 0.995 for the training, external validation, and aggregated sets, respectively. The calibration curve indicated that CDLRM was in good agreement between predicted and observed probabilities in the validation cohort. The results of DCA’s performance in different subgroups show that it was more clinically valuable in populations with high malignant potential. Conclusion CDLRM could help the development of personalized treatment and improved follow-up of patients with a high probability of recurrence or metastasis in the future. Critical relevance statement This model utilizes imaging features extracted from CT scans (including radiomic features and deep features) and clinical data to accurately predict postoperative recurrence and metastasis in patients with primary GISTs, which has a certain auxiliary role in clinical decision-making. Key Points We developed and validated a model to predict recurrence or metastasis in patients taking oral imatinib after GIST. We demonstrate that CT image features were associated with recurrence or metastases. The model had good predictive performance and clinical benefit. Graphical Abstract
format Article
id doaj-art-fe63ee0135524bada3db361c7906b9c8
institution Kabale University
issn 1869-4101
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Insights into Imaging
spelling doaj-art-fe63ee0135524bada3db361c7906b9c82025-08-20T03:31:45ZengSpringerOpenInsights into Imaging1869-41012025-06-0116111310.1186/s13244-025-02011-8A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumorsWenJie Xie0Zhen Zhang1Zhao Sun2XiaoChen Wan3JieHan Li4JianWu Jiang5Qi Liu6Ge Yang7Yang Fu8Department of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Gastrointestinal Surgery, Henan Cancer HospitalDepartment of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityOphthalmology, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Gastrointestinal Surgery, The First Affiliated Hospital of Zhengzhou UniversityAbstract Objectives Post-surgical prediction of recurrence or metastasis for primary gastrointestinal stromal tumors (GISTs) remains challenging. We aim to develop individualized clinical follow-up strategies for primary GIST patients, such as shortening follow-up time or extending drug administration based on the clinical deep learning radiomics model (CDLRM). Methods The clinical information on primary GISTs was collected from two independent centers. Postoperative recurrence or metastasis in GIST patients was defined as the endpoint of the study. A total of nine machine learning models were established based on the selected features. The performance of the models was assessed by calculating the area under the curve (AUC). The CDLRM with the best predictive performance was constructed. Decision curve analysis (DCA) and calibration curves were analyzed separately. Ultimately, our model was applied to the high-potential malignant group vs the low-malignant-potential group. The optimal clinical application scenarios of the model were further explored by comparing the DCA performance of the two subgroups. Results A total of 526 patients, 260 men and 266 women, with a mean age of 62 years, were enrolled in the study. CDLRM performed excellently with AUC values of 0.999, 0.963, and 0.995 for the training, external validation, and aggregated sets, respectively. The calibration curve indicated that CDLRM was in good agreement between predicted and observed probabilities in the validation cohort. The results of DCA’s performance in different subgroups show that it was more clinically valuable in populations with high malignant potential. Conclusion CDLRM could help the development of personalized treatment and improved follow-up of patients with a high probability of recurrence or metastasis in the future. Critical relevance statement This model utilizes imaging features extracted from CT scans (including radiomic features and deep features) and clinical data to accurately predict postoperative recurrence and metastasis in patients with primary GISTs, which has a certain auxiliary role in clinical decision-making. Key Points We developed and validated a model to predict recurrence or metastasis in patients taking oral imatinib after GIST. We demonstrate that CT image features were associated with recurrence or metastases. The model had good predictive performance and clinical benefit. Graphical Abstracthttps://doi.org/10.1186/s13244-025-02011-8Gastrointestinal stromal tumorsRadiomicsMachine learningDeep learningRecurrence or metastasis
spellingShingle WenJie Xie
Zhen Zhang
Zhao Sun
XiaoChen Wan
JieHan Li
JianWu Jiang
Qi Liu
Ge Yang
Yang Fu
A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
Insights into Imaging
Gastrointestinal stromal tumors
Radiomics
Machine learning
Deep learning
Recurrence or metastasis
title A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
title_full A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
title_fullStr A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
title_full_unstemmed A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
title_short A machine learning model integrating clinical-radiomics-deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
title_sort machine learning model integrating clinical radiomics deep learning features accurately predicts postoperative recurrence and metastasis of primary gastrointestinal stromal tumors
topic Gastrointestinal stromal tumors
Radiomics
Machine learning
Deep learning
Recurrence or metastasis
url https://doi.org/10.1186/s13244-025-02011-8
work_keys_str_mv AT wenjiexie amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT zhenzhang amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT zhaosun amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT xiaochenwan amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT jiehanli amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT jianwujiang amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT qiliu amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT geyang amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT yangfu amachinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT wenjiexie machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT zhenzhang machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT zhaosun machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT xiaochenwan machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT jiehanli machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT jianwujiang machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT qiliu machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT geyang machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors
AT yangfu machinelearningmodelintegratingclinicalradiomicsdeeplearningfeaturesaccuratelypredictspostoperativerecurrenceandmetastasisofprimarygastrointestinalstromaltumors