Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study

Abstract Objectives Subvariants of testicular germ cell tumor (TGCT) significantly affect therapeutic strategies and patient prognosis. However, preoperatively distinguishing seminoma (SE) from non-seminoma (n-SE) remains a challenge. This study aimed to evaluate the performance of a deep learning-b...

Full description

Saved in:
Bibliographic Details
Main Authors: Yafang Zhang, Shilin Lu, Chuan Peng, Shichong Zhou, Irene Campo, Michele Bertolotto, Qian Li, Zhiyuan Wang, Dong Xu, Yun Wang, Jinshun Xu, Qinfu Wu, Xiaoying Hu, Wei Zheng, Jianhua Zhou
Format: Article
Language:English
Published: SpringerOpen 2025-08-01
Series:Insights into Imaging
Subjects:
Online Access:https://doi.org/10.1186/s13244-025-02045-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234546568986624
author Yafang Zhang
Shilin Lu
Chuan Peng
Shichong Zhou
Irene Campo
Michele Bertolotto
Qian Li
Zhiyuan Wang
Dong Xu
Yun Wang
Jinshun Xu
Qinfu Wu
Xiaoying Hu
Wei Zheng
Jianhua Zhou
author_facet Yafang Zhang
Shilin Lu
Chuan Peng
Shichong Zhou
Irene Campo
Michele Bertolotto
Qian Li
Zhiyuan Wang
Dong Xu
Yun Wang
Jinshun Xu
Qinfu Wu
Xiaoying Hu
Wei Zheng
Jianhua Zhou
author_sort Yafang Zhang
collection DOAJ
description Abstract Objectives Subvariants of testicular germ cell tumor (TGCT) significantly affect therapeutic strategies and patient prognosis. However, preoperatively distinguishing seminoma (SE) from non-seminoma (n-SE) remains a challenge. This study aimed to evaluate the performance of a deep learning-based super-resolution (SR) US radiomics model for SE/n-SE differentiation. Materials and methods This international multicenter retrospective study recruited patients with confirmed TGCT between 2015 and 2023. A pre-trained SR reconstruction algorithm was applied to enhance native resolution (NR) images. NR and SR radiomics models were constructed, and the superior model was then integrated with clinical features to construct clinical-radiomics models. Diagnostic performance was evaluated by ROC analysis (AUC) and compared with radiologists’ assessments using the DeLong test. Results A total of 486 male patients were enrolled for training (n = 338), domestic (n = 92), and international (n = 59) validation sets. The SR radiomics model achieved AUCs of 0.90, 0.82, and 0.91, respectively, in the training, domestic, and international validation sets, significantly surpassing the NR model (p < 0.001, p = 0.031, and p = 0.001, respectively). The clinical-radiomics model exhibited a significantly higher across both domestic and international validation sets compared to the SR radiomics model alone (0.95 vs 0.82, p = 0.004; 0.97 vs 0.91, p = 0.031). Moreover, the clinical-radiomics model surpassed the performance of experienced radiologists in both domestic (AUC, 0.95 vs 0.85, p = 0.012) and international (AUC, 0.97 vs 0.77, p < 0.001) validation cohorts. Conclusions The SR-based clinical-radiomics model can effectively differentiate between SE and n-SE. Critical relevance statement This international multicenter study demonstrated that a radiomics model of deep learning-based SR reconstructed US images enabled effective differentiation between SE and n-SE. Key Points Clinical parameters and radiologists’ assessments exhibit limited diagnostic accuracy for SE/n-SE differentiation in TGCT. Based on scrotal US images of TGCT, the SR radiomics models performed better than the NR radiomics models. The SR-based clinical-radiomics model outperforms both the radiomics model and radiologists’ assessment, enabling accurate, non-invasive preoperative differentiation between SE and n-SE. Graphical Abstract
format Article
id doaj-art-4719b36dccf442f793b6e6adb0ea38fe
institution Kabale University
issn 1869-4101
language English
publishDate 2025-08-01
publisher SpringerOpen
record_format Article
series Insights into Imaging
spelling doaj-art-4719b36dccf442f793b6e6adb0ea38fe2025-08-20T04:03:07ZengSpringerOpenInsights into Imaging1869-41012025-08-0116111210.1186/s13244-025-02045-yDeep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter studyYafang Zhang0Shilin Lu1Chuan Peng2Shichong Zhou3Irene Campo4Michele Bertolotto5Qian Li6Zhiyuan Wang7Dong Xu8Yun Wang9Jinshun Xu10Qinfu Wu11Xiaoying Hu12Wei Zheng13Jianhua Zhou14Department of Ultrasound, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for CancerDepartment of Ultrasound, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for CancerDepartment of Ultrasound, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for CancerDepartment of Ultrasonography, Fudan University Shanghai Cancer CenterDepartment of Radiology, University of TriesteDepartment of Radiology, University Hospital TriesteDepartment of Ultrasound, The Affiliated Cancer Hospital of Zhengzhou University and Henan Cancer HospitalDepartment of Medical Ultrasound, Hunan Cancer Hospital/The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South UniversityDepartment of Ultrasound, Zhejiang Cancer HospitalDepartment of Medical Ultrasound, Yunnan Cancer HospitalDepartment of Ultrasound, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, Affiliated Cancer Hospital of University of Electronic Science and Technology of ChinaDepartment of Ultrasound, Zhuhai Hospital, Guangdong Hospital of Traditional Chinese MedicineDepartment of Ultrasound, Linyi Cancer HospitalDepartment of Ultrasound, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for CancerDepartment of Ultrasound, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for CancerAbstract Objectives Subvariants of testicular germ cell tumor (TGCT) significantly affect therapeutic strategies and patient prognosis. However, preoperatively distinguishing seminoma (SE) from non-seminoma (n-SE) remains a challenge. This study aimed to evaluate the performance of a deep learning-based super-resolution (SR) US radiomics model for SE/n-SE differentiation. Materials and methods This international multicenter retrospective study recruited patients with confirmed TGCT between 2015 and 2023. A pre-trained SR reconstruction algorithm was applied to enhance native resolution (NR) images. NR and SR radiomics models were constructed, and the superior model was then integrated with clinical features to construct clinical-radiomics models. Diagnostic performance was evaluated by ROC analysis (AUC) and compared with radiologists’ assessments using the DeLong test. Results A total of 486 male patients were enrolled for training (n = 338), domestic (n = 92), and international (n = 59) validation sets. The SR radiomics model achieved AUCs of 0.90, 0.82, and 0.91, respectively, in the training, domestic, and international validation sets, significantly surpassing the NR model (p < 0.001, p = 0.031, and p = 0.001, respectively). The clinical-radiomics model exhibited a significantly higher across both domestic and international validation sets compared to the SR radiomics model alone (0.95 vs 0.82, p = 0.004; 0.97 vs 0.91, p = 0.031). Moreover, the clinical-radiomics model surpassed the performance of experienced radiologists in both domestic (AUC, 0.95 vs 0.85, p = 0.012) and international (AUC, 0.97 vs 0.77, p < 0.001) validation cohorts. Conclusions The SR-based clinical-radiomics model can effectively differentiate between SE and n-SE. Critical relevance statement This international multicenter study demonstrated that a radiomics model of deep learning-based SR reconstructed US images enabled effective differentiation between SE and n-SE. Key Points Clinical parameters and radiologists’ assessments exhibit limited diagnostic accuracy for SE/n-SE differentiation in TGCT. Based on scrotal US images of TGCT, the SR radiomics models performed better than the NR radiomics models. The SR-based clinical-radiomics model outperforms both the radiomics model and radiologists’ assessment, enabling accurate, non-invasive preoperative differentiation between SE and n-SE. Graphical Abstracthttps://doi.org/10.1186/s13244-025-02045-ySeminomaNon-seminomaRadiomicsSuper-resolutionUltrasound
spellingShingle Yafang Zhang
Shilin Lu
Chuan Peng
Shichong Zhou
Irene Campo
Michele Bertolotto
Qian Li
Zhiyuan Wang
Dong Xu
Yun Wang
Jinshun Xu
Qinfu Wu
Xiaoying Hu
Wei Zheng
Jianhua Zhou
Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study
Insights into Imaging
Seminoma
Non-seminoma
Radiomics
Super-resolution
Ultrasound
title Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study
title_full Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study
title_fullStr Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study
title_full_unstemmed Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study
title_short Deep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study
title_sort deep learning based super resolution us radiomics to differentiate testicular seminoma and non seminoma an international multicenter study
topic Seminoma
Non-seminoma
Radiomics
Super-resolution
Ultrasound
url https://doi.org/10.1186/s13244-025-02045-y
work_keys_str_mv AT yafangzhang deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT shilinlu deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT chuanpeng deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT shichongzhou deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT irenecampo deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT michelebertolotto deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT qianli deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT zhiyuanwang deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT dongxu deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT yunwang deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT jinshunxu deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT qinfuwu deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT xiaoyinghu deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT weizheng deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy
AT jianhuazhou deeplearningbasedsuperresolutionusradiomicstodifferentiatetesticularseminomaandnonseminomaaninternationalmulticenterstudy