Automatic Ultrasound Habitat Radiomics for Differentiating Henoch-Schonlein Purpura Nephritis from IgA Nephropathy in Children: A Multicenter Study.
Authors
Affiliations (3)
Affiliations (3)
- Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College and State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Huazhong University of Science and Technology, Wuhan, 430030, Hubei, China (S.G., W.Z., T.X., X.-F.Z., P.G., X.-Y.Z., Q.W., X.-W.C.).
- Department of Medical Ultrasound, The First Affiliated Hospital of Henan Medical University, Xinxiang, Henan, China (M.-J.Z.).
- Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College and State Key Laboratory for Diagnosis and Treatment of Severe Zoonotic Infectious Diseases, Huazhong University of Science and Technology, Wuhan, 430030, Hubei, China (S.G., W.Z., T.X., X.-F.Z., P.G., X.-Y.Z., Q.W., X.-W.C.). Electronic address: [email protected].
Abstract
To assess a noninvasive ultrasound habitat radiomics approach with automatic kidney segmentation for distinguishing pediatric Henoch-Schonlein purpura nephritis (HSPN) from immunoglobulin A nephropathy (IgAN). This retrospective multicenter study included 592 biopsy-confirmed pediatric patients from three centers (HSPN, n = 338; IgAN, n = 254). The development cohort (n = 453) was split into training (n = 362) and internal validation (n = 91) cohorts, and an independent external validation cohort (n = 139) was used for final testing. Kidney regions of interest were automatically segmented using nnU-Net. K-means clustering defined three echogenic habitat subregions, and 408 radiomics features were extracted from the whole-kidney region and habitat subregions. Feature selection was performed in the training cohort, and three machine-learning classifiers were evaluated. The selected radiomics model was compared with clinical and combined models. nnU-Net achieved high kidney segmentation performance, with a mean Dice similarity coefficient of 0.957 and a mean intersection over union of 0.918 in the independent healthy-child test set. Fifteen radiomics features were retained, including six whole-kidney features and nine habitat-derived features. Logistic regression showed stable performance, with areas under the receiver operating characteristic curve (AUCs) of 0.806 (95% confidence interval [CI], 0.715-0.897) internally and 0.825 (95% CI, 0.758-0.892) externally. The combined model outperformed the clinical model in AUC in both cohorts (0.846 vs 0.717; 0.805 vs 0.733). This deep-learning-assisted ultrasound habitat radiomics approach enabled automatic kidney delineation and showed encouraging performance as a reproducible imaging adjunct for differentiating pediatric HSPN from IgAN.