在乳腺钼靶x线片计算机辅助诊断中,微钙化点的自动检测是难点问题之一.本文基于模糊神经网络,建议了一种乳腺微钙化点提取的新方法.算法首先利用随机方法产生大量的样本,经模糊判别后,输入神经网络进行训练,训练后的神经网络对感兴趣区域进行分类得到微钙化点.最后,仿真结果同其它算法进行比较,证明本文算法具有更高的阳性检出率。 In the computer-aided diagnosis of breast mammography, automatic detection of microcalcifications is one of the difficult issues.In this paper, a new method of breast microcalcification extraction is proposed based on the fuzzy neural network.The algorithm firstly uses a random method to generate a large number of , The neural network is trained to input the neural network, and the trained neural network classifies the regions of interest to obtain the microcalcifications. Finally, the simulation results are compared with other algorithms to prove that the algorithm has a higher positive detection rate.