biostudies-literatureWang Ythe 2023 Whole Laboratory Automation System and Intelligent Analysis System Projecthe Key Research and Development Program of Shandong ProvinceShanghai Jiaotong University School of Medicine Shanghai high-level local university construction projectthe Suzhou Science and Technology Plan Projectthe Taishan Industrial Experts Programthe Key Research and Development Program of Jiangsu Province84https://www.ebi.ac.uk/biostudies/studies/S-EPMC11977085biostudies-literatureUnknown16(1)<h4>Objectives</h4>To address SPECT's radioactivity, complexity, and costliness in measuring renal function, this study employs artificial intelligence (AI) with non-contrast CT to estimate single-kidney glomerular filtration rate (GFR) and split renal function (SRF).<h4>Methods</h4>245 patients with atrophic kidney or hydronephrosis were included from two centers (Training set: 128 patients from Center I; Test set: 117 patients from Center II). The renal parenchyma and hydronephrosis regions in non-contrast CT were automatically segmented by deep learning. Radiomic features were extracted and combined with clinical characteristics using multivariable linear regression (MLR) to obtain a radiomics-clinical-estimated GFR (rcGFR). The relative contribution of single-kidney rcGFR to overall rcInsights into imagingAI-based automatic estimation of single-kidney glomerular filtration rate and split renal function using non-contrast CT.PMC11977085tscx202312131ZTZB-23-990-008BE2021663, BE20237142021SFGC01042022zxy005SJC2021014, SZS2022008Geng DHan QXu BXu FGao XWang YXia WfalseAI-based automatic estimation of single-kidney glomerular filtration rate and split renal function using non-contrast CT.<h4>Objectives</h4>To address SPECT's radioactivity, complexity, and costliness in measuring renal function, this study employs artificial intelligence (AI) with non-contrast CT to estimate single-kidney glomerular filtration rate (GFR) and split renal function (SRF).<h4>Methods</h4>245 patients with atrophic kidney or hydronephrosis were included from two centers (Training set: 128 patients from Center I; Test set: 117 patients from Center II). The renal parenchyma and hydronephrosis regions in non-contrast CT were automatically segmented by deep learning. Radiomic features were extracted and combined with clinical characteristics using multivariable linear regression (MLR) to obtain a radiomics-clinical-estimated GFR (rcGFR). The relative contribution of single-kidney rcGFR to overall rc2025-01-01T00:00:00Z2025 Apr2025-07-13T03:04:58.542Z2025-07-13T03:04:58.542ZS-EPMC119770854019286210.1186/s13244-025-01959-x