School of Control Science and Engineering, Shandong University, Jinan 250061, China.
Radiology Department, Qilu Hospital of Shandong University, Jinan 250000, China.
Comput Methods Programs Biomed. 2023 Oct;240:107721. doi: 10.1016/j.cmpb.2023.107721. Epub 2023 Jul 15.
Medical hyperspectral images (MHSIs) are used for a contact-free examination of patients without harmful radiation. However, high-dimensionality images contain large amounts of data that are sparsely distributed in a high-dimensional space, which leads to the "curse of dimensionality" (called Hughes' phenomenon) and increases the complexity and cost of data processing and storage. Hence, there is a need for spectral dimensionality reduction before the clinical application of MHSIs. Some dimensionality-reducing strategies have been proposed; however, they distort the data within MHSIs.
To compress dimensionality without destroying the original data structure, we propose a method that involves data gravitation and weak correlation-based ranking (DGWCR) for removing bands of noise from MHSIs while clustering signal-containing bands. Band clustering is done by using the connection centre evolution (CCE) algorithm and selecting the most representative bands in each cluster based on the composite force. The bands within the clusters are ranked using the new entropy-containing matrix, and a global ranking of bands is obtained by applying an S-shaped strategy. The source code is available at https://www.github.com/zhangchenglong1116/DGWCR.
Upon feeding the reduced-dimensional images into various classifiers, the experimental results demonstrated that the small number of bands selected by the proposed DGWCR consistently achieved higher classification accuracy than the original data. Unlike other reference methods (e.g. the latest deep-learning-based strategies), DGWCR chooses the spectral bands with the least redundancy and greatest discrimination.
In this study, we present a method for efficient band selection for MHSIs that alleviates the "curse of dimensionality". Experiments were validated with three MHSIs in the human brain, and they outperformed several other band selection methods, demonstrating the clinical potential of DGWCR.
医学高光谱图像（MHSI）用于对患者进行非接触式检查，不会产生有害辐射。然而，高维图像包含大量数据，这些数据在高维空间中稀疏分布，这导致了“维度灾难”（称为休斯现象），增加了数据处理和存储的复杂性和成本。因此，在 MHSI 的临床应用之前，需要进行光谱降维。已经提出了一些降维策略，但它们会扭曲 MHSI 中的数据。
为了在不破坏原始数据结构的情况下压缩维度，我们提出了一种方法，该方法涉及数据引力和基于弱相关性的排序（DGWCR），用于从 MHSI 中去除噪声带，同时对包含信号的带进行聚类。通过使用连接中心演化（CCE）算法和基于复合力选择每个聚类中最具代表性的带，来实现带聚类。使用新的包含熵的矩阵对聚类内的带进行排序，并通过应用 S 形策略获得带的全局排序。源代码可在 https://www.github.com/zhangchenglong1116/DGWCR 上获得。
将降维后的图像输入到各种分类器中，实验结果表明，所提出的 DGWCR 选择的少数带始终比原始数据获得更高的分类精度。与其他参考方法（例如最新的基于深度学习的策略）不同，DGWCR 选择的带具有最小的冗余度和最大的可辨别性。
在这项研究中，我们提出了一种用于 MHSI 的高效带选择方法，缓解了“维度灾难”。使用三种人脑 MHSI 进行了实验验证，它们优于其他几种带选择方法，证明了 DGWCR 的临床潜力。
