Lihacova Ilze, Bondarenko Andrey, Chizhov Yuriy, Uteshev Dilshat, Bliznuks Dmitrijs, Kiss Norbert, Lihachev Alexey
Institute of Atomic Physics and Spectroscopy, University of Latvia, 1004 Riga, Latvia.
Faculty of Computer Science and Information Technology, Riga Technical University, 1048 Riga, Latvia.
J Clin Med. 2022 May 17;11(10):2833. doi: 10.3390/jcm11102833.
In this work, we propose to use an artificial neural network to classify limited data of clinical multispectral and autofluorescence images of skin lesions. Although the amount of data is limited, the deep convolutional neural network classification of skin lesions using a multi-modal image set is studied and proposed for the first time. The unique dataset consists of spectral reflectance images acquired under 526 nm, 663 nm, 964 nm, and autofluorescence images under 405 nm LED excitation. The augmentation algorithm was applied for multi-modal clinical images of different skin lesion groups to expand the training datasets. It was concluded from saliency maps that the classification performed by the convolutional neural network is based on the distribution of the major skin chromophores and endogenous fluorophores. The resulting classification confusion matrices, as well as the performance of trained neural networks, have been investigated and discussed.
在这项工作中，我们提议使用人工神经网络对皮肤病变的临床多光谱和自体荧光图像的有限数据进行分类。尽管数据量有限，但首次研究并提出了使用多模态图像集对皮肤病变进行深度卷积神经网络分类。独特的数据集包括在526纳米、663纳米、964纳米下采集的光谱反射图像，以及在405纳米发光二极管激发下的自体荧光图像。对不同皮肤病变组的多模态临床图像应用增强算法以扩展训练数据集。从显著性图得出的结论是，卷积神经网络执行的分类基于主要皮肤发色团和内源性荧光团的分布。已对所得的分类混淆矩阵以及训练神经网络的性能进行了研究和讨论。
