Automatic Kidney Stone Composition Analysis Method Based on Dual-energy CT.

BACKGROUND: The composition of kidney stones is related to the hardness of the stones. Knowing the composition of the stones before surgery can help plan the laser power and operation time of percutaneous nephroscopic surgery. Moreover, patients can be treated with medications if the kidney stone is compounded by uric acid before treatment, which can relieve the patients of the pain of surgery. However, although the literature generally reports the kidney stone composition analysis method base on dual-energy CT images, the accuracy of these methods is not enough; they need manual delineation of the kidney stone location, and these methods cannot analyze mixed composition kidney stones. OBJECTIVE: This study aimed to overcome the problem related to identifying kidney stone composition; we need an accurate method to analyze the composition of kidney stones. METHODS: In this paper, we proposed the automatic kidney stone composition analysis algorithm based on a dual-energy CT image. The algorithm first segmented the kidney stone mask by deep learning model, then analyzed the composition of each stone by machine learning model. RESULTS: The experimental results indicate that the proposed algorithm can segment kidney stones accurately (AUC=0.96) and predict kidney stone composition accurately (mean Acc=0.86, mean Se=0.75, mean Sp=0.9, mean F1=0.75, mean AUC=0.83, MR (Exact match ratio)=0.6). CONCLUSION: The proposed method can predict the composition and location of kidney stones, which can guide its treatment. Experimental results show that the weighting strategy can improve kidney stone segmentation performance. In addition, the multi-label classification model can predict kidney stone composition precisely, including the mixed composition kidney stones.

Are conventional stone analysis techniques reliable for the identification of 2,8-dihydroxyadenine kidney stones? A case series.

We have recently encountered patients incorrectly diagnosed with adenine phosphoribosyltransferase (APRT) deficiency due to misidentification of kidney stones as 2,8-dihydroxyadenine (DHA) stones. The objective of this study was to examine the accuracy of stone analysis for identification of DHA. Medical records of patients referred to the APRT Deficiency Research Program of the Rare Kidney Stone Consortium in 2010-2018 with a diagnosis of APRT deficiency based on kidney stone analysis were reviewed. The diagnosis was verified by measurement of APRT enzyme activity or genetic testing. Attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectra of pure crystalline DHA and a kidney stone obtained from one of the confirmed APRT deficiency cases were generated. The ATR-FTIR spectrum of the kidney stone matched the crystalline DHA spectrum and was used for comparison with available infrared spectra of stone samples from the patients. Of 17 patients referred, 14 had sufficient data available to be included in the study. In all 14 cases, the stone analysis had been performed by FTIR spectroscopy. The diagnosis of APRT deficiency was confirmed in seven cases and rejected in the remaining seven cases. Comparison of the ATR-FTIR spectrum of the DHA stone with the FTIR spectra from three patients who did not have APRT deficiency showed no indication of DHA as a stone component. Misidentification of DHA as a kidney stone component by clinical laboratories appears common among patients referred to our program. Since current clinical protocols used to interpret infrared spectra for stone analysis cannot be considered reliable for the identification of DHA stones, the diagnosis of APRT deficiency must be confirmed by other methods.

Kidney stones: Composition, frequency and relation to metabolic diagnosis.

Nephrolithiasis is one of the most frequent urologic diseases. The aim of this paper is to study the composition and frequency of 8854 patient kidney stones and in a subset of them their metabolic risk factors to be related to their type of calculi. Physicochemical and crystallographic methods were used to assess kidney stone composition. In a subset of 715 patients, we performed an ambulatory metabolic protocol with diagnostic purposes. From the total sample 79% of stones were made of calcium salts (oxalate and phosphate), followed by uric acid stones in 16.5%, calcium salts and uric acid in 2%, other salts in 1.9% and cystine in 0.6%. Male to female ratio was almost three times higher in calcium salts and other types of stones, reaching a marked male predominance in uric acid stones, M/F 18.8 /1.0. The major risk factors for calcium stones are idiopathic hypercalciuria, followed by unduly acidic urine pH and hyperuricosuria. In uric acid stones unduly acidic urine pH and less commonly hyperuricosuria are the most frequent biochemical diagnosis. Our results show that analysis of kidney stones composition and the corresponding metabolic diagnosis may provide a scientific basis for the best management and prevention of kidney stone formation, as well as it may help us to study the mechanisms of urine stone formation.

Kidney stones: composition, frequency and relation to metabolic diagnosis

Nephrolithiasis is one of the most frequent urologic diseases. The aim of this paper is to study the composition and frequency of 8854 patient kidney stones and in a subset of them their metabolic risk factors to be related to their type of calculi. Physicochemical and crystallographic methods were used to assess kidney stone composition. In a subset of 715 patients, we performed an ambulatory metabolic protocol with diagnostic purposes. From the total sample 79% of stones were made of calcium salts (oxalate and phosphate), followed by uric acid stones in 16.5%, calcium salts and uric acid in 2%, other salts in 1.9% and cystine in 0.6%. Male to female ratio was almost three times higher in calcium salts and other types of stones, reaching a marked male predominance in uric acid stones, M/F 18.8 /1.0. The major risk factors for calcium stones are idiopathic hypercalciuria, followed by unduly acidic urine pH and hyperuricosuria. In uric acid stones unduly acidic urine pH and less commonly hyperuricosuria are the most frequent biochemical diagnosis. Our results show that analysis of kidney stones composition and the corresponding metabolic diagnosis may provide a scientific basis for the best management and prevention of kidney stone formation, as well as it may help us to study the mechanisms of urine stone formation.

La litiasis renal es una de las enfermedades urológicas más frecuentes. El objetivo de este trabajo fue estudiar la composición y frecuencia de 8854 cálculos renales y evaluar en un subgrupo de ellos la relación de los factores de riesgo metabólicos con el tipo de cálculo hallado. Se utilizaron métodos fisicoquímicos y cristalográficos para evaluar la composición de los cálculos renales. En un subgrupo de 715 pacientes, se pudo realizar un protocolo metabólico ambulatorio con fines diagnóstico. De la muestra total, 79.0% de los cálculos fueron de sales de calcio (oxalato y fosfato), seguido por cálculos de ácido úrico en 16.5%, sales de calcio y ácido úrico en 2.0%, otras sales en 1.9% y cistina en 0.6%. La relación hombre/mujer fue casi tres veces mayor en las sales de calcio y otros tipos de cálculos, alcanzando un marcado predominio en varones con cálculos de ácido úrico, M/F 18.8/1.0. Los principales factores de riesgo para los cálculos de calcio fueron la hipercalciuria idiopática, seguida del pH urinario excesivamente ácido y la hiperuricosuria. En los cálculos de ácido úrico el pH urinario excesivamente ácido y con menor frecuencia la hiperuricosuria fueron los diagnósticos más frecuentes. Nuestros resultados muestran que el análisis de la composición de los cálculos renales y el correspondiente diagnóstico metabólico pueden proporcionar una base científica para el mejor manejo y prevención en la formación de cálculos renales, así como que nos puede ayudar a estudiar los mecanismos de formación de los mismos.