Microwave dielectric property based classification of renal calculi: Application of a kNN algorithm

• Published in: Computers in biology and medicine Vol. 112; p. 103366
• Main Authors: Saçlı, Banu, Aydınalp, Cemanur, Cansız, Gökhan, Joof, Sulayman, Yilmaz, Tuba, Çayören, Mehmet, Önal, Bülent, Akduman, Ibrahim
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.09.2019; Elsevier Limited
• Subjects: Accuracy; Algorithms; Artificial intelligence; Calcium oxalate; Calculi; Classification; Classification of kidney stones; Cole–Cole parameters; Cystine; Data analysis; Dielectric properties; Dielectric properties of renal calculi; k-nearest neighbors; K-nearest neighbors algorithm; Kidney stone; Kidney stones; Kidneys; Learning algorithms; Lithiasis; Machine learning; Molecular structure; Open-ended coaxial probe; Oxalic acid; Parameters; Pathogenesis; Struvite; X ray powder diffraction; X-rays; Dielectric properties of renal calculi; Machine learning; Open-ended coaxial probe; Cole–Cole parameters; Classification of kidney stones; Kidney stone; k-nearest neighbors
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.103366

The proper management of renal lithiasis presents a challenge, with the recurrence rate of the disease being as high as 46%. To prevent recurrence, the first step is the accurate categorization of the discarded renal calculi. Currently, the discarded renal calculi type is determined with the X-ray powder diffraction method which requires a cumbersome sample preparation. This work presents a new approach that can enable fast and accurate classification of discarded renal calculi with minimal sample preparation requirements. To do so, first, the measurements of the dielectric properties of naturally formed renal calculi are collected with the open-ended contact probe technique between 500 MHz and 6 GHz with 100 MHz intervals. Cole–Cole parameters are fitted to the measured dielectric properties with the generalized Newton–Raphson method. The renal calculi types are classified based on their Cole–Cole parameters as calcium oxalate, cystine, or struvite. The classification is performed using k-nearest neighbors (kNN) machine learning algorithm with the 10 nearest neighbors, where accuracy as high as 98.17% is achieved. [Display omitted] •Discarded renal calculi (calcium oxalate, cystine, and struvite) show an inherent microwave dielectric property discrepancy.•The dielectric properties can be utilized to identify the renal calculi type.•Cole-Cole parameters were used to mathematically model the dielectric property measurement data.•The kNN algorithm provided 98.17% accuracy.