Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction

Abstract This study developed a 5-year survival prediction model for gastric cancer patients by combining radiomics and deep learning, focusing on CT-based 2D and 3D features of the iliopsoas and erector spinae muscles. Retrospective data from 705 patients across two centers were analyzed, with clin...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan Hong, Peng Zhang, Zhijun Teng, Kang Cheng, Zimo Zhang, Yixian Cheng, Guodong Cao, Bo Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-09083-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238560138330112
author Yuan Hong
Peng Zhang
Zhijun Teng
Kang Cheng
Zimo Zhang
Yixian Cheng
Guodong Cao
Bo Chen
author_facet Yuan Hong
Peng Zhang
Zhijun Teng
Kang Cheng
Zimo Zhang
Yixian Cheng
Guodong Cao
Bo Chen
author_sort Yuan Hong
collection DOAJ
description Abstract This study developed a 5-year survival prediction model for gastric cancer patients by combining radiomics and deep learning, focusing on CT-based 2D and 3D features of the iliopsoas and erector spinae muscles. Retrospective data from 705 patients across two centers were analyzed, with clinical variables assessed via Cox regression and radiomic features extracted using deep learning. The 2D model outperformed the 3D approach, leading to feature fusion across five dimensions, optimized via logistic regression. Results showed no significant association between clinical baseline characteristics and survival, but the 2D model demonstrated strong prognostic performance (AUC ~ 0.8), with attention heatmaps emphasizing spinal muscle regions. The 3D model underperformed due to irrelevant data. The final integrated model achieved stable predictive accuracy, confirming the link between muscle mass and survival. This approach advances precision medicine by enabling personalized prognosis and exploring 3D imaging feasibility, offering insights for gastric cancer research.
format Article
id doaj-art-9ec8687c85a84c9dbfe68d765adade23
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9ec8687c85a84c9dbfe68d765adade232025-08-20T04:01:34ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-09083-yMuscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival predictionYuan Hong0Peng Zhang1Zhijun Teng2Kang Cheng3Zimo Zhang4Yixian Cheng5Guodong Cao6Bo Chen7Department of General Surgery, The First Affiliated Hospital of Anhui Medical UniversityDepartment of General Surgery, The First Affiliated Hospital of Anhui Medical UniversityDepartment of General Surgery, The First Affiliated Hospital of Anhui Medical UniversityDepartment of The First Clinical Medical College, Anhui Medical UniversityDepartment of The First Clinical Medical College, Anhui Medical UniversityDepartment of General Surgery, The First Affiliated Hospital of Anhui Medical UniversityDepartment of General Surgery, The First Affiliated Hospital of Anhui Medical UniversityDepartment of General Surgery, The First Affiliated Hospital of Anhui Medical UniversityAbstract This study developed a 5-year survival prediction model for gastric cancer patients by combining radiomics and deep learning, focusing on CT-based 2D and 3D features of the iliopsoas and erector spinae muscles. Retrospective data from 705 patients across two centers were analyzed, with clinical variables assessed via Cox regression and radiomic features extracted using deep learning. The 2D model outperformed the 3D approach, leading to feature fusion across five dimensions, optimized via logistic regression. Results showed no significant association between clinical baseline characteristics and survival, but the 2D model demonstrated strong prognostic performance (AUC ~ 0.8), with attention heatmaps emphasizing spinal muscle regions. The 3D model underperformed due to irrelevant data. The final integrated model achieved stable predictive accuracy, confirming the link between muscle mass and survival. This approach advances precision medicine by enabling personalized prognosis and exploring 3D imaging feasibility, offering insights for gastric cancer research.https://doi.org/10.1038/s41598-025-09083-ySarcopeniaGastric cancerRadical gastrectomyDeep learning
spellingShingle Yuan Hong
Peng Zhang
Zhijun Teng
Kang Cheng
Zimo Zhang
Yixian Cheng
Guodong Cao
Bo Chen
Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction
Scientific Reports
Sarcopenia
Gastric cancer
Radical gastrectomy
Deep learning
title Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction
title_full Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction
title_fullStr Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction
title_full_unstemmed Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction
title_short Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction
title_sort muscle driven prognostication in gastric cancer a multicenter deep learning framework integrating iliopsoas and erector spinae radiomics for 5 year survival prediction
topic Sarcopenia
Gastric cancer
Radical gastrectomy
Deep learning
url https://doi.org/10.1038/s41598-025-09083-y
work_keys_str_mv AT yuanhong muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT pengzhang muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT zhijunteng muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT kangcheng muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT zimozhang muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT yixiancheng muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT guodongcao muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction
AT bochen muscledrivenprognosticationingastriccanceramulticenterdeeplearningframeworkintegratingiliopsoasanderectorspinaeradiomicsfor5yearsurvivalprediction