径向基函数在前列腺癌计算机辅助诊断中的应用。

Use of radial basis functions in computer-aided diagnosis of prostate cancer.

作者信息

Marín Oscar, Ruiz Daniel, Pérez Irene, Soriano Antonio

机构信息

Bioinspired Engineering and Health Computing Research Group, University of Alicante, Alicante, PO 99 E-03080, Spain.

出版信息

Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:6422-5. doi: 10.1109/IEMBS.2011.6091585.

DOI:10.1109/IEMBS.2011.6091585

PMID:22255808

Abstract

In this paper, we show the results of a study in which we try to test the feasibility of using radial basis functions neural networks (RBFs for short) in clinical decision support systems. We have implemented two instances of RBFs in order to diagnose possible prostate cancer cases from a clinical database. To give an idea about how good the results are, we follow a two-fold approach. On the one hand they are independently evaluated in terms of accuracy, sensitivity and specificity and on the other hand they are compared with the performance over the same database of a classifier widely applied to the medical field problems, as it is multi-layer perceptron (MLP). The experimental results show that RBFs are a useful tool to build up clinical decision support systems.

摘要

在本文中，我们展示了一项研究的结果，在该研究中我们试图测试在临床决策支持系统中使用径向基函数神经网络（简称为RBF）的可行性。我们实现了两个RBF实例，以便从临床数据库中诊断可能的前列腺癌病例。为了说明结果有多好，我们采用了双重方法。一方面，根据准确性、敏感性和特异性对它们进行独立评估，另一方面，将它们与广泛应用于医学领域问题的分类器（即多层感知器（MLP））在同一数据库上的性能进行比较。实验结果表明，RBF是构建临床决策支持系统的有用工具。