Bai, Harrison X.

ABSTRACTBackgroundDeep learning (DL) models for accurate renal tumor characterization may benefit from multi‐center datasets for improved generalizability; however, data‐sharing constraints necessitate privacy‐preserving solutions like federated learning (FL).PurposeTo assess the performance and reliability of FL for renal tumor segmentation and classification in multi‐institutional MRI datasets.Study TypeRetrospective multi‐center study.PopulationA total of 987 patients (403 female) from six hospitals were included for analysis. 73% (723/987) had malignant renal tumors, primarily clear cell carcinoma (n = 509). Patients were split into training (n = 785), validation (n = 104), and test (n = 99) sets, stratified across three simulated institutions.Field Strength/SequenceMRI was performed at 1.5 T and 3 T using T2‐weighted imaging (T2WI) and contrast‐enhanced T1‐weighted imaging (CE‐T1WI) sequences.AssessmentFL and non‐FL approaches used nnU‐Net for tumor segmentation and ResNet for its classification. FL‐trained models across three simulated institutional clients with central weight aggregation, while the non‐FL approach used centralized training on the full dataset.Statistical TestsSegmentation was evaluated using Dice coefficients, and classification between malignant and benign lesions was assessed using accuracy, sensitivity, specificity, and area under the curves (AUCs). FL and non‐FL performance was compared using the Wilcoxon test for segmentation Dice and Delong's test for AUC (p < 0.05).ResultsNo significant difference was observed between FL and non‐FL models in segmentation (Dice: 0.43 vs. 0.45, p = 0.202) or classification (AUC: 0.69 vs. 0.64, p = 0.959) on the test set. For classification, no significant difference was observed between the models in accuracy (p = 0.912), sensitivity (p = 0.862), or specificity (p = 0.847) on the test set.Data ConclusionFL demonstrated comparable performance to non‐FL approaches in renal tumor segmentation and classification, supporting its potential as a privacy‐preserving alternative for multi‐institutional DL models.Evidence Level4.Technical EfficacyStage 2.

BackgroundPretreatment determination of renal cell carcinoma aggressiveness may help to guide clinical decision‐making.PurposeTo evaluate the efficacy of residual convolutional neural network using routine MRI in differentiating low‐grade (grade I–II) from high‐grade (grade III–IV) in stage I and II renal cell carcinoma.Study TypeRetrospective.PopulationIn all, 376 patients with 430 renal cell carcinoma lesions from 2008–2019 in a multicenter cohort were acquired. The 353 Fuhrman‐graded renal cell carcinomas were divided into a training, validation, and test set with a 7:2:1 split. The 77 WHO/ISUP graded renal cell carcinomas were used as a separate WHO/ISUP test set.Field Strength/Sequence1.5T and 3.0T/T2‐weighted and T1 contrast‐enhanced sequences.AssessmentThe accuracy, sensitivity, and specificity of the final model were assessed. The receiver operating characteristic (ROC) curve and precision‐recall curve were plotted to measure the performance of the binary classifier. A confusion matrix was drawn to show the true positive, true negative, false positive, and false negative of the model.Statistical TestsMann–Whitney U‐test for continuous data and the chi‐square test or Fisher's exact test for categorical data were used to compare the difference of clinicopathologic characteristics between the low‐ and high‐grade groups. The adjusted Wald method was used to calculate the 95% confidence interval (CI) of accuracy, sensitivity, and specificity.ResultsThe final deep‐learning model achieved a test accuracy of 0.88 (95% CI: 0.73–0.96), sensitivity of 0.89 (95% CI: 0.74–0.96), and specificity of 0.88 (95% CI: 0.73–0.96) in the Fuhrman test set and a test accuracy of 0.83 (95% CI: 0.73–0.90), sensitivity of 0.92 (95% CI: 0.84–0.97), and specificity of 0.78 (95% CI: 0.68–0.86) in the WHO/ISUP test set.Data ConclusionDeep learning can noninvasively predict the histological grade of stage I and II renal cell carcinoma using conventional MRI in a multiinstitutional dataset with high accuracy.Level of Evidence3Technical Efficacy Stage2