Fernandez Katrina, Korinek Mark, Camp Jon, Lieske John, Holmes David
Biomedical Imaging Resource, Mayo Clinic, Rochester, MN, USA.
University of Minnesota, Minneapolis, MN, USA.
Healthc Technol Lett. 2019 Dec 6;6(6):271-274. doi: 10.1049/htl.2019.0086. eCollection 2019 Dec.
Kidney stones are a common urologic condition with a high amount of recurrence. Recurrence depends on a multitude of factors the incidence of precursors to kidney stones, plugs, and plaques. One method of characterising the stone precursors is endoscopic assessment, though it is manual and time-consuming. Deep learning has become a popular technique for semantic segmentation because of the high accuracy that has been demonstrated. The present Letter examined the efficacy of deep learning to segment the renal papilla, plaque, and plugs. A U-Net model with ResNet-34 encoder was tested; the Letter examined dropout (to avoid overtraining) and two different loss functions (to address the class imbalance problem. The models were then trained in 1666 images and tested on 185 images. The Jaccard-cross-entropy loss function was more effective than the focal loss function. The model with the dropout rate 0.4 was found to be more effective due to its generalisability. The model was largely successful at delineating the papilla. The model was able to correctly detect the plaques and plugs; however, small plaques were challenging. Deep learning was found to be applicable for segmentation of an endoscopic image for the papilla, plaque, and plug, with room for improvement.
肾结石是一种常见的泌尿系统疾病，复发率很高。复发取决于多种因素，包括肾结石、堵塞物和斑块的前驱病变的发生率。表征结石前驱病变的一种方法是内镜评估，不过这是手动操作且耗时。由于已证明具有高精度，深度学习已成为语义分割的一种流行技术。本信函研究了深度学习对肾乳头、斑块和堵塞物进行分割的效果。测试了一个带有ResNet - 34编码器的U - Net模型；该信函研究了随机失活（以避免过训练）和两种不同的损失函数（以解决类别不平衡问题）。然后在1666张图像上训练这些模型，并在185张图像上进行测试。Jaccard交叉熵损失函数比焦点损失函数更有效。发现随机失活率为0.4的模型因其通用性而更有效。该模型在勾勒乳头轮廓方面基本成功。该模型能够正确检测斑块和堵塞物；然而，小斑块具有挑战性。研究发现深度学习适用于对内镜图像中的乳头、斑块和堵塞物进行分割，但仍有改进空间。
