Department of Urology, CHU Nancy - Brabois, Nancy, France.
Université de Lorraine, Nancy, France.
BJU Int. 2022 Dec;130(6):786-798. doi: 10.1111/bju.15767. Epub 2022 May 23.
To assess the potential of automated machine-learning methods for recognizing urinary stones in endoscopy.
Surface and section images of 123 urinary calculi (109 ex vivo and 14 in vivo stones) were acquired using ureteroscopes. The stones were more than 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 stone recognition methods that were developed for this study followed two types of approach: 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 to classify them into one of the main morphological groups (subgroups were not considered in this study).
Using shallow methods (based on texture and colour criteria), relatively high sensitivity, specificity and PPV for the six classes were attained: 91%, 90% and 89%, respectively, 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.
Endoscopic stone recognition is challenging, and few urologists have sufficient expertise to achieve a diagnosis performance comparable to morpho-constitutional analysis. This work is a proof of concept that artificial intelligence could be a solution, with promising results achieved for pure stones. Further studies on a larger panel of stones (pure and mixed) are needed to further develop these methods.
评估自动化机器学习方法在识别内窥镜下尿路结石方面的潜力。
使用输尿管镜采集 123 个尿路结石（109 个离体结石和 14 个体内结石）的表面和切片图像。结石的“纯度”超过 85%。代表了六种结石类型：I 组（一水草酸钙，水合草酸钙）、II 组（二水草酸钙，一水合草酸钙）、III 组（尿酸）、IV 组（磷酸钙和鸟粪石结石）和 V 组（胱氨酸）。为这项研究开发的自动化结石识别方法遵循两种方法：浅层分类方法和基于深度学习的方法。通过同时使用结石的表面和切片图像将其分类到主要形态组之一，评估了它们的敏感性、特异性和阳性预测值（PPV）（在这项研究中没有考虑亚组）。
使用浅层方法（基于纹理和颜色标准），对于六种结石类型，获得了较高的敏感性、特异性和 PPV：一水合草酸钙分别为 91%、90%和 89%；一水合草酸钙分别为 99%、98%和 99%；尿酸分别为 88%、89%和 88%；鸟粪石分别为 91%、89%和 90%；胱氨酸分别为 99%、99%和 99%；磷酸钙分别为 94%、98%和 99%。使用深度学习方法，对于每种结石类型，其敏感性、特异性和 PPV 如下：一水合草酸钙分别为 99%、98%和 97%；一水合草酸钙分别为 98%、98%和 98%；尿酸分别为 97%、98%和 98%；鸟粪石分别为 97%、97%和 96%；胱氨酸分别为 99%、99%和 99%；磷酸钙分别为 94%、97%和 98%。
内镜下结石识别具有挑战性，很少有泌尿科医生具备足够的专业知识来达到与形态学分析相当的诊断性能。这项工作是人工智能可以作为一种解决方案的概念验证，对于纯结石取得了有希望的结果。需要进一步研究更大的结石（纯结石和混合结石）样本，以进一步开发这些方法。
