Evaluation of Few-Shot Learning Methods for Kidney Stone Type Recognition in Ureteroscopy

TL;DR

This paper introduces a few-shot learning approach using Prototypical Networks to accurately classify kidney stone types in ureteroscopic images with limited training data, potentially matching or surpassing traditional methods.

Contribution

It presents a novel application of few-shot learning for kidney stone classification, enabling effective diagnosis with scarce data and uncommon classes.

Findings

Prototypical Networks achieve comparable or better accuracy with 25% of training data.

The method is effective for rare classes with limited samples.

Deep learning models can be trained efficiently with minimal data.

Abstract

Determining the type of kidney stones is crucial for prescribing appropriate treatments to prevent recurrence. Currently, various approaches exist to identify the type of kidney stones. However, obtaining results through the reference ex vivo identification procedure can take several weeks, while in vivo visual recognition requires highly trained specialists. For this reason, deep learning models have been developed to provide urologists with an automated classification of kidney stones during ureteroscopies. Nevertheless, a common issue with these models is the lack of training data. This contribution presents a deep learning method based on few-shot learning, aimed at producing sufficiently discriminative features for identifying kidney stone types in endoscopic images, even with a very limited number of samples. This approach was specifically designed for scenarios where endoscopic images are scarce or where uncommon classes are present, enabling classification even with a limited training dataset. The results demonstrate that Prototypical Networks, using up to 25% of the training data, can achieve performance equal to or better than traditional deep learning models trained with the complete dataset.