Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA.
Analyst. 2019 Feb 25;144(5):1642-1653. doi: 10.1039/c8an01495g.
Current methods for cancer detection rely on tissue biopsy, chemical labeling/staining, and examination of the tissue by a pathologist. Though these methods continue to remain the gold standard, they are non-quantitative and susceptible to human error. Fourier transform infrared (FTIR) spectroscopic imaging has shown potential as a quantitative alternative to traditional histology. However, identification of histological components requires reliable classification based on molecular spectra, which are susceptible to artifacts introduced by noise and scattering. Several tissue types, particularly in heterogeneous tissue regions, tend to confound traditional classification methods. Convolutional neural networks (CNNs) are the current state-of-the-art in image classification, providing the ability to learn spatial characteristics of images. In this paper, we demonstrate that CNNs with architectures designed to process both spectral and spatial information can significantly improve classifier performance over per-pixel spectral classification. We report classification results after applying CNNs to data from tissue microarrays (TMAs) to identify six major cellular and acellular constituents of tissue, namely adipocytes, blood, collagen, epithelium, necrosis, and myofibroblasts. Experimental results show that the use of spatial information in addition to the spectral information brings significant improvements in the classifier performance and allows classification of cellular subtypes, such as adipocytes, that exhibit minimal chemical information but have distinct spatial characteristics. This work demonstrates the application and efficiency of deep learning algorithms in improving the diagnostic techniques in clinical and research activities related to cancer.
当前的癌症检测方法依赖于组织活检、化学标记/染色以及病理学家对组织的检查。尽管这些方法仍然是金标准，但它们是非定量的，容易出现人为错误。傅里叶变换红外（FTIR）光谱成像是一种有潜力的定量替代传统组织学的方法。然而，要识别组织学成分，需要基于分子光谱进行可靠的分类，而这些光谱容易受到噪声和散射引入的伪影的影响。几种组织类型，特别是在异质组织区域，往往会使传统的分类方法变得复杂。卷积神经网络（CNN）是目前图像分类的最新技术，它提供了学习图像空间特征的能力。在本文中，我们证明了经过设计可以处理光谱和空间信息的 CNN 可以显著提高分类器的性能，优于逐像素的光谱分类。我们报告了将 CNN 应用于组织微阵列（TMA）数据以识别组织的六种主要细胞和无细胞成分（即脂肪细胞、血液、胶原、上皮、坏死和肌成纤维细胞）后的分类结果。实验结果表明，除了光谱信息之外，使用空间信息可以显著提高分类器的性能，并允许对具有明显空间特征但化学信息较少的细胞亚型（如脂肪细胞）进行分类。这项工作展示了深度学习算法在改善与癌症相关的临床和研究活动中的诊断技术方面的应用和效率。
