biostudies-literatureZhang YGuangdong Esophageal Cancer Research InstituteNational Natural Science Foundation of ChinaNatural Science Foundation of Guangdong Province165https://www.ebi.ac.uk/biostudies/studies/S-EPMC12316629biostudies-literatureUnknown16(1)<h4>Objectives</h4>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.<h4>Materials and methods</h4>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 Insights into imagingDeep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study.PMC12316629No. Q202313No. 2023A1515011564No. 82320108011Zhou SWu QHu XXu DLi QCampo IBertolotto MZheng WXu JZhang YPeng CLu SWang YWang ZZhou JfalseDeep learning-based super-resolution US radiomics to differentiate testicular seminoma and non-seminoma: an international multicenter study.<h4>Objectives</h4>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.<h4>Materials and methods</h4>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 2025-01-01T00:00:00Z2025 Aug2026-03-15T12:01:41.929Z2025-08-12T03:05:09.792ZS-EPMC123166294075094910.1186/s13244-025-02045-y