欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
图像分割是医学影像技术中重要的组成部分,分割效果直接影响进一步的诊断和治疗。提出采用遗传神经网络对皮肤癌图像进行分割的方法,该算法充分考虑了医学图像中内容复杂,不确定性大的特点。为了提高神经网络的收敛速度,引入遗传算法优化神经网络的权值和阈值。与采用标准BP神经网络相比,采用的遗传神经网络分割速度明显提高。采用遗传神经网络分割后的皮肤癌图像边缘连续、轮廓清晰,可在定量分析和识别中使用。
英文摘要：
The segment of medical images is the important component of medical imaging technology, and the effect of which will impact the diagnosis and therapy directly. By taking the complexity and uncertainty of the medical images, the genetic neural network is proposed to segment the skin cancer images. Optimization of weights and thresholds in neural network based on genetic algorithm is executed to improve the convergence speed of the BP neural network. Compared with the standard BP neural network, the segment speed of the genetic neural network adopted is much higher. The skin cancer images segmented by this method have continuous edge and clear contour, which is used in the quantitative analysis and identification of the skin cancer.
同期刊论文项目
同项目期刊论文
期刊信息
位置：