Handels H, Ross T, Kreusch J, Wolff H H, Pöppl S J
Institute for Medical Informatics, Medical University of Lübeck, Germany.
Methods Inf Med. 1999 Mar;38(1):43-9.
Laser profilometry offers new possibilities to improve non-invasive tumor diagnostics in dermatology. In this paper, a new approach to computer-supported analysis and interpretation of high-resolution skin-surface profiles of melanomas and nevocellular nevi is presented. Image analysis methods are used to describe the profile's structures by texture parameters based on co-occurrence matrices, features extracted from the Fourier power spectrum, and fractal features. Different feature selection strategies, including genetic algorithms, are applied to determine the best possible subsets of features for the classification task. Several architectures of multilayer perceptrons with error back-propagation as learning paradigm are trained for the automatic recognition of melanomas and nevi. Furthermore, network-pruning algorithms are applied to optimize the network topology. In the study, the best neural classifier showed an error rate of 4.5% and was obtained after network pruning. The smallest error rate in all, of 2.3%, was achieved with nearest neighbor classification.
激光轮廓测量法为改善皮肤病学中的非侵入性肿瘤诊断提供了新的可能性。本文提出了一种新方法，用于计算机支持的黑素瘤和痣细胞痣高分辨率皮肤表面轮廓的分析与解释。图像分析方法用于通过基于共生矩阵的纹理参数、从傅里叶功率谱提取的特征以及分形特征来描述轮廓结构。应用了包括遗传算法在内的不同特征选择策略，以确定用于分类任务的最佳特征子集。训练了几种以误差反向传播作为学习范式的多层感知器架构，用于自动识别黑素瘤和痣。此外，应用网络剪枝算法来优化网络拓扑。在该研究中，最佳神经分类器在网络剪枝后显示出4.5%的错误率。总体上最小的错误率为2.3%，是通过最近邻分类实现的。
