人工神经网络在视神经疾病诊断中的应用。
Utilization of artificial neural networks in the diagnosis of optic nerve diseases.
作者信息
Kara Sadik, Güven Ayşegül, Oner Ayşe Oztürk
机构信息
Department of Electrical and Electronics Engineering, Erciyes University, 38039 Kayseri, Turkey.
出版信息
Comput Biol Med. 2006 Apr;36(4):428-37. doi: 10.1016/j.compbiomed.2005.01.003.
This research is concentrated on the diagnosis of optic nerve disease through the analysis of pattern electroretinography (PERG) signals with the help of artificial neural network (ANN). Multilayer feed forward ANN trained with a Levenberg Marquart (LM) backpropagation algorithm was implemented. The designed classification structure has about 96.4% sensitivity, 90.4% specifity and positive prediction is calculated to be 94.2%. The end results are classified as healthy and diseased. Testing results were found to be compliant with the expected results that are derived from the physician's direct diagnosis. The end benefit would be to assist the physician to make the final decision without hesitation.
本研究致力于借助人工神经网络（ANN）分析图形视网膜电图（PERG）信号来诊断视神经疾病。实现了采用Levenberg Marquart（LM）反向传播算法训练的多层前馈人工神经网络。所设计的分类结构灵敏度约为96.4%，特异性为90.4%，阳性预测值经计算为94.2%。最终结果分为健康和患病两类。测试结果与从医生直接诊断得出的预期结果相符。最终的益处是协助医生毫不犹豫地做出最终决策。
Zotero 插件