Evaluation of Few-Shot Learning Methods for Kidney Stone Type Recognition in Ureteroscopy
This work addresses the challenge of automated kidney stone recognition for urologists, enabling faster diagnosis during procedures, though it is incremental as it applies existing few-shot methods to a specific medical domain.
The paper tackled the problem of classifying kidney stone types from endoscopic images with limited training data, using few-shot learning to achieve performance equal to or better than traditional deep learning models while using only up to 25% of the training data.
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.