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

Rabia Mihriban Kılınç; Ömer Suat Fitoz

doi:10.47582/jompac.1869854

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

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

Supporting Institution

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

Ethical Statement

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

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

Details

Primary Language

English

Subjects

Radiology and Organ Imaging

Journal Section

Research Article

Authors

Rabia Mihriban Kılınç ^*
0000-0002-6845-5496
Türkiye

Ömer Suat Fitoz This is me
0000-0002-0180-0013
Türkiye

Publication Date

March 27, 2026

Submission Date

January 23, 2026

Acceptance Date

February 25, 2026

Published in Issue

Year 2026 Volume: 7 Number: 2

DOI

https://doi.org/10.47582/jompac.1869854

IZ

https://izlik.org/JA52TK26NX

Cite

RIS / Bibtex

APA

Kılınç, R. M., & Fitoz, Ö. S. (2026). Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study. Journal of Medicine and Palliative Care, 7(2), 255-260. https://doi.org/10.47582/jompac.1869854

AMA

1.Kılınç RM, Fitoz ÖS. Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study. J Med Palliat Care / JOMPAC / jompac. 2026;7(2):255-260. doi:10.47582/jompac.1869854

Chicago

Kılınç, Rabia Mihriban, and Ömer Suat Fitoz. 2026. “Machine Learning-Based Evaluation of Congenital Urinary System Dilatation Severity: A Radiomics Approach With EXplainable AI in a Small Cohort Study”. Journal of Medicine and Palliative Care 7 (2): 255-60. https://doi.org/10.47582/jompac.1869854.

EndNote

Kılınç RM, Fitoz ÖS (March 1, 2026) Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study. Journal of Medicine and Palliative Care 7 2 255–260.

IEEE

[1]R. M. Kılınç and Ö. S. Fitoz, “Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study”, J Med Palliat Care / JOMPAC / jompac, vol. 7, no. 2, pp. 255–260, Mar. 2026, doi: 10.47582/jompac.1869854.

ISNAD

Kılınç, Rabia Mihriban - Fitoz, Ömer Suat. “Machine Learning-Based Evaluation of Congenital Urinary System Dilatation Severity: A Radiomics Approach With EXplainable AI in a Small Cohort Study”. Journal of Medicine and Palliative Care 7/2 (March 1, 2026): 255-260. https://doi.org/10.47582/jompac.1869854.

JAMA

1.Kılınç RM, Fitoz ÖS. Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study. J Med Palliat Care / JOMPAC / jompac. 2026;7:255–260.

MLA

Kılınç, Rabia Mihriban, and Ömer Suat Fitoz. “Machine Learning-Based Evaluation of Congenital Urinary System Dilatation Severity: A Radiomics Approach With EXplainable AI in a Small Cohort Study”. Journal of Medicine and Palliative Care, vol. 7, no. 2, Mar. 2026, pp. 255-60, doi:10.47582/jompac.1869854.

Vancouver

1.Rabia Mihriban Kılınç, Ömer Suat Fitoz. Machine learning-based evaluation of congenital urinary system dilatation severity: a radiomics approach with eXplainable AI in a small cohort study. J Med Palliat Care / JOMPAC / jompac. 2026 Mar. 1;7(2):255-60. doi:10.47582/jompac.1869854