Evaluation and understanding of automated urinary stone recognition methods
Résumé
OBJECTIVE: To assess the potential of automated machine learning methods for recognizing urinary stones in endoscopy.
MATERIALS AND METHODS: Surface and section images of 123 urinary calculi (109 ex vivo and 14 in vivo stones), were acquired using ureteroscopes. They were over 85% pure. Six classes of urolithiasis were represented: groups I (calcium oxalate monohydrate, whewellite), II (calcium oxalate dihydrate, weddellite), III (uric acid), IV (brushite and struvite stones), and V (cystine).
The automated stones recognition methods that were developed for this study belong to two types of approaches: shallow classification methods and deep learning-based methods. Their sensitivity, specificity and positive predictive value (PPV) were evaluated by simultaneously using stone surface and section images for classifying them into one of the main morphologic groups (sub-groups were not considered in this study).
RESULTS: Using shallow methods (based on texture and color criteria), relatively high values of sensitivity, specificity and PPV for the six classes were attained: 91%, 90% and 89% for whewellite; 99%, 98% and 99% for weddellite; 88%,89% and 88% for uric acid; 91%, 89% and 90% for struvite; 99%, 99% and 99% for cystine; and 94%, 98% and 99% for brushite.
Using deep learning methods, the sensitivity, specificity and PPV for each of the classes were as follows: 99%, 98% and 97% for whewellite; 98%, 98% and 98% for weddellite; 97%, 98% and 98% for uric acid; 97%, 97% and 96% for struvite; 99%, 99% and 99% for cystine; and 94%, 97% and 98% for brushite.
CONCLUSION: Endoscopic stone recognition is a real challenge. But few urologists have sufficient expertise to have a diagnosis performance comparable to morpho-constitutional analysis. Artificial Intelligence can be a solution, with promising results for pure stones.
Further studies on a larger panel of stones (pure and mixed) are needed to further develop these methods.