Unsupervised band selection of medical hyperspectral images guided by data gravitation and weak correlation

Chenglong Zhang; Zhimin Zhang; Dexin Yu; Qiyuan Cheng; Shihao Shan; Mengjiao Li; Lichao Mou; Xiaoli Yang; Xiaopeng Ma

doi:10.1016/j.cmpb.2023.107721

Unsupervised band selection of medical hyperspectral images guided by data gravitation and weak correlation

Comput Methods Programs Biomed. 2023 Oct:240:107721. doi: 10.1016/j.cmpb.2023.107721. Epub 2023 Jul 15.

Authors

Chenglong Zhang¹, Zhimin Zhang¹, Dexin Yu², Qiyuan Cheng³, Shihao Shan¹, Mengjiao Li¹, Lichao Mou⁴, Xiaoli Yang⁵, Xiaopeng Ma⁶

Affiliations

¹ School of Control Science and Engineering, Shandong University, Jinan 250061, China.
² Radiology Department, Qilu Hospital of Shandong University, Jinan 250000, China.
³ Medical Engineering Department, Shandong Provincial Hospital affiliated to Shandong First Medical University, Jinan 250021, China.
⁴ Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, 80333, Germany.
⁵ School of Control Science and Engineering, Shandong University, Jinan 250061, China; Weifang Xinli Superconducting Magnet Technology Co., Ltd, Weifang 261005, China. Electronic address: yangxiaoli424@163.com.
⁶ School of Control Science and Engineering, Shandong University, Jinan 250061, China. Electronic address: xiaopeng.ma@sdu.edu.cn.

PMID: 37506601
DOI: 10.1016/j.cmpb.2023.107721

Abstract

Background and objective: 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.

Methods: 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.

Results: 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.

Conclusion: 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.

Keywords: Band selection; Data gravitation; Human brain; Medical hyperspectral images.

MeSH terms

Algorithms*
Brain*
Cluster Analysis
Humans
Software