On the In Vivo Recognition of Kidney Stones Using Machine Learning

Determining the type of kidney stones allows urologists to prescribe a treatment to avoid the recurrence of renal lithiasis. An automated in-vivo image-based classification method would be an important step towards an immediate identification of the kidney stone type required as a first phase of the diagnosis. In the literature, it was shown on ex-vivo data (i.e., in very controlled scene and image acquisition conditions) that an automated kidney stone classification is indeed feasible. This pilot study compares the kidney stone recognition performances of six shallow machine learning methods and three deep-learning architectures which were tested with in-vivo images of the four most frequent urinary calculus types acquired with an endoscope during standard ureteroscopies. This contribution details the construction of an in-vivo dataset of endoscopic images with four of the most recurrent classes in clinical practice. It also describes the design, implementation, and results of the classifiers (shallow machine learning and deep learning-based methods) of kidney stones. Even if the best results were obtained by the InceptionV3 architecture (weighted accuracy, precision, recall and F1-Score of
$97\pm 03\%, 97\pm 03\%, 98\pm 04\%$
, and
$98\pm 03\%$
, respectively), it is also shown that choosing an appropriate colour space and texture features allows a shallow machine learning method to approach closely the performances of the most promising deep-learning methods (the XGBoost classifier led to weighted accuracy, precision, recall and F1-Score values of
$96\pm 14\%$
).