深度学习计算机视觉算法检测肾结石成分
本研究评估深度学习(DL)方法从结石数字照片自动检测肾结石成分的召回率。使用63颗不同成分的人肾结石,采用ResNet-101卷积神经网络进行多类分类,留一交叉验证显示总体加权召回率为85%,各成分召回率在71%至94%之间。结论认为深度卷积神经网络可从数字照片识别结石成分,未来需探索内镜中应用。
要点
- DL模型从结石照片识别成分的总体加权召回率为85%。
- 尿酸结石召回率最高达94%,刷石最低为71%。
- 该技术有望集成内镜与激光系统,根据成分自动设置激光参数。
核心结论
- 深度卷积神经网络可从数字照片识别肾结石成分,召回率良好。
- 未来需研究DL能否在数字内镜中检测结石成分。
研究设计与样本
- 研究获取63颗不同成分的人肾结石,包括一水草酸钙(COM)、尿酸(UA)、六水磷酸铵镁(MAPH/鸟粪石)、二水磷酸氢钙(CHPD/刷石)和胱氨酸结石。
- 每颗结石至少拍摄表面和内核两张数字照片,使用ResNet-101卷积神经网络作为多类分类模型,采用留一交叉验证评估,主要结局为网络预测召回率。
主要发现
- 各成分预测召回率:UA 94%(n=17),COM 90%(n=21),MAPH/鸟粪石86%(n=7),胱氨酸75%(n=4),CHPD/刷石71%(n=14)。
- 整个队列的CNN成分分析总体加权召回率为85%。
- 各结石类型的特异度和精确度:UA(97.83%,94.12%),COM(97.62%,95%),鸟粪石(91.84%,71.43%),胱氨酸(98.31%,75%),刷石(96.43%,75%)。
临床怎么用
- 该技术可能使内镜和激光系统集成,根据结石成分识别自动提供激光设置,以提高手术效率。
局限性
- 未来需要研究DL能否在数字内镜期间检测结石成分。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: To assess the recall of a deep learning (DL) method to automatically detect kidney stones composition from digital photographs of stones. MATERIALS AND METHODS: A total of 63 human kidney stones of varied compositions were obtained from a stone laboratory including calcium oxalate monohydrate (COM), uric acid (UA), magnesium ammonium phosphate hexahydrate (MAPH/struvite), calcium hydrogen phosphate dihydrate (CHPD/brushite), and cystine stones. At least two images of the stones, both surface and inner core, were captured on a digital camera for all stones. A deep convolutional neural network (CNN), ResNet-101 (ResNet, Microsoft), was applied as a multi-class classification model, to each image. This model was assessed using leave-one-out cross-validation with the primary outcome being network prediction recall. RESULTS: The composition prediction recall for each composition was as follows: UA 94% (n = 17), COM 90% (n = 21), MAPH/struvite 86% (n = 7), cystine 75% (n = 4), CHPD/brushite 71% (n = 14). The overall weighted recall of the CNNs composition analysis was 85% for the entire cohort. Specificity and precision for each stone type were as follows: UA (97.83%, 94.12%), COM (97.62%, 95%), struvite (91.84%, 71.43%), cystine (98.31%, 75%), and brushite (96.43%, 75%). CONCLUSION: Deep CNNs can be used to identify kidney stone composition from digital photographs with good recall. Future work is needed to see if DL can be used for detecting stone composition during digital endoscopy. This technology may enable integrated endoscopic and laser systems that automatically provide laser settings based on stone composition recognition with the goal to improve surgical efficiency.
引用
- Black KM, Law H, Aldoukhi A, et al. Deep learning computer vision algorithm for detecting kidney stone composition. BJU Int. 2020. PMID: 32045113. doi:10.1111/bju.15035
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。