Serón D, Moreso F, Gratin C, Vitriá J, Condom E, Grinyó J M, Alsina J
Department of Nephrology, Ciudad Sanitaria and University of Bellvitge, Barcelona, Spain.
Anal Quant Cytol Histol. 1996 Oct;18(5):410-9.
To segment renal interstitial space in order to automatically quantify renal cortical interstitial volume fraction (Vvint/cortex) by means of image analysis techniques.
The study group consisted of 35 renal biopsies with different degrees of chronic interstitial damage. Biopsies were stained with Sirius red and digitized under polarized light. Two methods were employed to segment interstitial space: (1) interstitial bright particles were thresholded, and afterwards interstitial space was reconstructed with a morphologic operation, and (2) the texture of the surroundings of each pixel was quantified by means of local granulometry, and this information was employed as the input of a neural network in order to classify interstitial and tubular pixels.
The correlation between Vvint/cortex obtained manually and both methods was r = .92. The first method produced some deformation of tubular contours and underestimated Vvint/cortex (beta = .70) when compared to the second approach (beta = .95) (P < .05).
Two different algorithms based on image analysis techniques allow the classification of renal interstitial and tubular structures and consequently allow the automated and precise estimation of renal Vvint/cortex.
通过图像分析技术分割肾间质空间，以自动定量肾皮质间质体积分数（Vvint/cortex）。
研究组包括35例具有不同程度慢性间质损伤的肾活检标本。活检标本用天狼星红染色，并在偏振光下数字化。采用两种方法分割间质空间：（1）对间质明亮颗粒进行阈值处理，然后通过形态学操作重建间质空间；（2）通过局部粒度分析对每个像素周围的纹理进行量化，并将此信息作为神经网络的输入，以对间质像素和肾小管像素进行分类。
手动获得的Vvint/cortex与两种方法之间的相关性为r = 0.92。与第二种方法（β = 0.95）相比，第一种方法使肾小管轮廓产生了一些变形，并低估了Vvint/cortex（β = 0.70）（P < 0.05）。
基于图像分析技术的两种不同算法可对肾间质和肾小管结构进行分类，从而实现对肾Vvint/cortex的自动精确估计。
