Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study

Year 2026, Volume: 7 Issue: 2, 255 - 260, 27.03.2026

Rabia Mihriban Kılınç , Ömer Suat Fitoz

https://izlik.org/JA52TK26NX

Abstract

Aims: Congenital urinary tract dilatations are among the most common anomalies in pediatric urology and may lead to significant morbidity if not properly managed. Although magnetic resonance urography (MRU) enables detailed anatomic and functional assessment, conventional interpretation remains subjective and operator-dependent. Radiomics, coupled with machine learning (ML) and eXplainable Artificial Intelligence (XAI), has the potential to provide objective and reproducible diagnostic support.
Methods: The dataset used in this study comprises a subset of data obtained from a previously completed medical residency thesis. From the computerized archives of this thesis, data from 13 patients could be retrieved. For radiological assessment and ML modeling, three-dimensional heavily T2-weighted images were utilized. Radiomic features were extracted, and ML–based classification models were developed to predict disease severity. To identify the most relevant imaging features contributing to model performance, XAI methods, including Shapley Additive Explanations (SHAP), were applied. No clinical variables were incorporated into the modeling pipeline; the analysis was based exclusively on imaging-derived radiomic features.
Results: The radiomics-based ML model demonstrated preliminary classification performance in this small cohort, as assessed by cross-validation metrics. SHAP analysis revealed that texture and intensity-derived features were the most influential predictors of disease severity.
Conclusion: Radiomics combined with ML and XAI represents a promising and technically feasible approach for the evaluation of congenital urinary tract dilatation in small exploratory cohorts. While the present findings are preliminary, this framework may support future development of decision-support tools following validation in larger, independent datasets.

Keywords

Congenital urinary tract dilatation , magnetic resonance urography , radiomics , machine learning , explainable Artificial Intelligence

Ethical Statement

Ethical approval for this study was obtained from the Muğla University Faculty of Medicine Clinical Research Ethics Committee (Approval No: 2025/250104).

Supporting Institution

The authors declared that this study has received no financial support.

References

• Aldughiem A. Imaging diagnosis of major kidney and urinary tract disorders in children. Medicina (Kaunas). 2025;61(4):696. doi:10.3390/medicina61040696
• Lockwood GM, Leach AJ, Shelton J, et al. Interrater reliability of objective and subjective measures of urinary tract dilation by pediatric urologists: a multicenter analysis. J Pediatr Urol. 2025;21(6):1764-1770. doi:10.1016/j.jpurol.2025.06.025
• Chung AD, Lee KS, Kim JH, Park SH. MR urography: pitfalls and solutions. AJR Am J Roentgenol. 2016;206(6):1236-1246. doi:10.2214/AJR.16.16348
• Goya C, Kilickesmez O, Kocak B, et al. Radiomics and Artificial Intelligence in genitourinary imaging: current applications and future perspectives. Eur J Radiol. 2021;142:109836. doi:10.1016/j.ejrad.2021. 109836
• Wang H, Zhou Z, Li Y, et al. Magnetic resonance imaging–based radiomics analysis for evaluating renal lesions: a systematic review. Eur Radiol. 2020;30(6):3512-3524.
• Lundberg SM, Lee SI. A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. 2017;30:4765-4774.
• Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278(2):563-577. doi:10.1148/radiol.2015151169
• Kocak B, Durmaz ES, Ates E, Kilickesmez O. Radiomics with Artificial Intelligence: a practical guide for beginners. Eur Radiol. 2020;30(7): 3930-3940. doi:10.1007/s00330-019-06572-7
• Kılınç RM. Çocuk hastalarda üriner sistemin değerlendirilmesinde MR ürografi [Tıpta uzmanlık tezi]. Ankara: Ankara Üniversitesi Tıp Fakültesi; 2008. Tez No: 229990. YÖK Ulusal Tez Merkezi.
• Vabalas A, Gowen E, Poliakoff E, Casson AJ. Machine learning algorithm validation with a limited sample size. PLoS One. 2019;14(11):e0224365. doi:10.1371/journal.pone.0224365
• Yankeelov TE, Gore JC. Dynamic contrast enhanced magnetic resonance imaging in oncology: theory, data acquisition, analysis, and examples. Curr Med Imaging Rev. 2009;3(2):91-107. doi:10.2174/ 157340507780619179
• Ganeshan B, Miles KA. Quantifying tumour heterogeneity with CT and MRI: a review of texture analysis methods and applications. Cancer Imag. 2013;13(1):140-149. doi:10.1102/1470-7330.2013.001