Related Experiment Video
Updated: Sep 11, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Integrated radiomics and deep learning model for identifying medullary sponge kidney stones
Yubao Liu1, Haifeng Song1, Daxun Luo1
1Department of Urology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China.
Background:
Medullary sponge kidney (MSK) is a rare congenital anomaly frequently associated with nephrolithiasis. Accurate preoperative differentiation between MSK stones and non-MSK multiple kidney stones remains challenging, yet it is essential for effective clinical decision-making. This study aims to develop a novel diagnostic model that integrates radiomics and deep learning features to improve the differentiation of MSK stones using CT imaging.
Methods:
This single-center, retrospective study included patients who underwent surgical treatment for multiple kidney stones at Beijing Tsinghua Changgung Hospital between 2021 and 2023. All MSK and non-MSK cases were confirmed via endoscopic surgery. Radiomics features were extracted from manually delineated regions of interest (ROI) on nephrographic-phase CT images, while deep learning features were derived from a ResNet101-based model. Three diagnostic signatures-Radiomics (Rad), Deep Transfer Learning (DTL), and Deep Learning Radiomics (DLR)-were developed. A Combined model was constructed by integrating clinical variables with DLR features to further enhance diagnostic accuracy. Model performance was evaluated using AUC, calibration curves, Net Reclassification Index (NRI), and Integrated Discrimination Improvement (IDI) analyses. Additionally, Gradient-weighted Class Activation Mapping (Grad-CAM) visualization was employed to identify imaging regions critical to classification, improving interpretability.
Results:
A total of 73 patients with multiple kidney stones were analyzed, comprising 34 MSK cases and 39 non-MSK cases, encompassing 110 kidneys in total. The DLR signature demonstrated high diagnostic accuracy, with AUCs of 0.96 in both the training and test cohorts. The Combined model further enhanced diagnostic performance, achieving AUCs of 0.98 in the training cohort and 0.95 in the test cohort. Calibration curves indicated strong agreement between predicted probabilities and observed outcomes. Furthermore, NRI and IDI analyses highlighted the superior predictive power of both the DLR and Combined models compared to other approaches.
Conclusion:
This study introduces an innovative approach for MSK stone diagnosis by integrating radiomics and deep learning features. The proposed model offers high diagnostic accuracy and promising clinical utility.
Insights
This study developed a novel diagnostic model integrating radiomics and deep learning for differentiating medullary sponge kidney (MSK) stones. The combined model achieved high accuracy, improving clinical decision-making for kidney stone patients.
Area of Science:
- Nephrology
- Radiology
- Artificial Intelligence
Background:
- Medullary sponge kidney (MSK) is a rare congenital anomaly often linked to nephrolithiasis.
- Differentiating MSK stones from other kidney stones preoperatively is clinically challenging.
- Accurate differentiation is crucial for effective patient management and treatment planning.
Purpose of the Study:
- To develop and validate a novel diagnostic model for improved differentiation of MSK stones.
- To integrate radiomics and deep learning features from CT imaging for enhanced diagnostic accuracy.
- To assess the clinical utility of the proposed diagnostic model.
Main Methods:
- Retrospective single-center study of 73 patients with multiple kidney stones (34 MSK, 39 non-MSK).
- Extraction of radiomics features from CT images and deep learning features using ResNet101.
- Development of Radiomics (Rad), Deep Transfer Learning (DTL), Deep Learning Radiomics (DLR), and a Combined model integrating clinical variables.
Main Results:
- The Deep Learning Radiomics (DLR) signature achieved high diagnostic accuracy (AUC 0.96 in training and test sets).
- The Combined model, integrating DLR features and clinical variables, further improved performance (AUC 0.98 training, 0.95 test).
- Calibration curves, NRI, and IDI analyses confirmed the superior predictive power of the DLR and Combined models.
Conclusions:
- An innovative diagnostic model combining radiomics and deep learning was developed for MSK stone differentiation.
- The proposed model demonstrates high diagnostic accuracy and significant clinical potential.
- This approach offers a promising tool for improving preoperative diagnosis of MSK stones.
