Prediction of the composition of urinary stones using deep learning

Abstract

Purpose This study aimed to predict the composition of urolithiasis using deep learning from urinary stone images. Materials and Methods We classified 1,332 stones into 31 classes according to the stone composition. The top 4 classes with a frequency of 110 or more (class 1: calcium oxalate monohydrate [COM] 100%, class 2: COM 80%+struvite 20%, class 3: COM 60%+calcium oxalate dihydrate [COD] 40%, class 4: uric acid 100%) were selected. With the 965 stone images of the top 4 classes, we used the seven convolutional neural networks (CNN) to classify urinary stones and compared their classification performances. Results Among the seven models, Xception_Ir0.001 showed the highest accuracy, precision, and recall and was selected as the CNN model to predict the stone composition. The sensitivity and specificity for the 4 classes by Xception_Ir0.001 were as follows: class 1 (94.24%, 91.73%), class 2 (85.42%, 96.14%), class 3 (86.86%, 99.59%), and class 4 (94.96%, 98.82%). The sensitivity and specificity of the individual components of the stones were as follows. COM (98.82%, 94.96%), COD (86.86%, 99.64%), struvite (85.42%, 95.59%), and uric acid (94.96%, 98.82%). The area under the curves for class 1, 2, 3, and 4 were 0.98, 0.97, 1.00, and 1.00, respectively. Conclusions This study showed the feasibility of deep learning for the diagnostic ability to assess urinary stone composition from images. It can be an alternative tool for conventional stone analysis and provide decision support to urologists, improving the effectiveness of diagnosis and treatment.

Transforming urinary stone disease management by artificial intelligence-based methods: A comprehensive review

“…[ 76 ] Stone composition by visual image Cross-sectional Overall accuracy of 74.38% and 88.52%, depending on the image capturing method Overall accuracy of 45% Kim et al. [ 77 ] Stone composition by visual image Cross-sectional AUC of 0.98–1.00, depending on stone type Other multivariate models with lower performance Fitri et al. [ 78 ] Stone composition by microtomography Cross-sectional Overall accuracy of 99.59% No comparator Saçlı et al.…”

“…Kim et al. [ 77 ] used the largest set of stone images captured by a digital camera, depicting 1332 stones of 31 different chemical compositions. Among them, images of 965 stones, representing the four more frequent classes, were used to construct and train a number of models, based on CNNs.…”

Fifty years of basic and clinical renal stone research: have we achieved major breakthroughs? A debate

“…Artificial neural networks (ANN) were also successfully used to predict spontaneous passage of ureteral calculi, outcome after percutaneous nephrolithotomy, stone-free status after SWL and stone growth after SWL. A promising application of artificial intelligence is the determination of stone composition from the analysis of digital photographs of stones by deep convolutional neural networks (CNNs) [34–36]. This technology was also applied for the identification of stone composition from endoscopic intra-operative view [37 ▪▪ ,38 ▪▪ ].…”

A New Parameter for Calcium Oxalate Stones: Impact of Linear Calculus Density on Non-Contrast Computed Tomography

“…For patients with recurrent stones, analyses of stone compositions are especially important, as they may reveal an underlying metabolic abnormality, including cystinuria. Although a detailed analysis can be performed after the stone has been extracted through Fourier transform infrared (FTIR) spectroscopy [ 5 ], several theories have been proposed to predict the composition preoperatively through clinical data, including stone characteristics and urine parameters.…”