基于BP神经网络的视网膜不规则病变面积的测量研究

Measurement of the Irregular Retinal Lesion Area Based on the Back Propagation Neural Network Method

报告采用改进的Back Propagation(BP)神经网络算法,实现了对眼底血管造影图像中不规则病变区域的自动分割,并依据图像像素与实际尺寸间的比例系数,完成视网膜不规则病变面积的测量。本研究可为视网膜病变的临床诊断、治疗以及预后评价等提供有价值的依据。

In this study,the automatic segmentation of the irregular lesion region in the image of fundus fluorescence angiography was actualized by means of the modified Back Propagation（BP） neural network method.Combining the transfer scaling coefficient between pixel of the image and the actual size,the area of the irregular lesion region was measured.The results may provide valuable data for the clinical diagnosis,treatment and prognostic evaluation.