基于显微高光谱成像技术的尿沉渣结晶样本分析

doi:10.3964/j.issn.1000-0593(2025)05-1243-08

Abstract
References
Related Citation (15)

Download: PDF (16650 KB)
Export: BibTeX | EndNote (RIS)

Abstract The analysis of urine components, called urine sediment, is paramount in clinical practice. By observing particles, cells, and crystals in urine sediment, doctors can obtain important information about the patient's urogenital health, which is crucial for diagnosing urogenital-related ailments. However, identifying urine sediment crystals heavily relies on medical professionals' manual observation under a microscope, which is time-consuming, subjective, and often inaccurate. Consequently, automated microscopic urine sediment image analysis using image analysis technology has gained significant attention. However, these methods rely solely on morphological information to classify crystal samples, making distinguishing between morphology-similar crystals difficult, resulting in low classification accuracy. Microscopic hyperspectral imaging technology integrates spatial and spectral information, revealing distinct spectral characteristics as different substances exhibit varying degrees of light absorption and scattering across different spectral bands. In this study, we introduced microscopic hyperspectral imaging technology to analyze urine sediment crystal samples and used a self-developed microscopic hyperspectral imaging system to acquire hyperspectral images. We collected microscopic hyperspectral image data of five urine sediment crystal sample types, including calcium oxalate, cystine, calcium phosphate, uric acid, and triple phosphate. Additionally, we trained four machine learning classifiers support vector machine (SVM), k-nearest neighbors (KNN), decision tree (DT), and neural network(NN) models on this dataset to classify the five types of urine sediment crystal samples. The classification accuracies of SVM, KNN, DT, and NN models for the five types of urine sediment crystals reached 0.959 8, 0.959 8, 0.982 9, and 0.991 7, respectively. Our research indicates that applying microscopic hyperspectral imaging technology to urine sediment sample analysis enables the acquisition of spatial information and facilitates the extraction of discriminative spectral features, thereby assisting physicians in microscopic examination and supporting the popularization of urine sediment microscopy techniques.

Key words：Microscopy hyperspectral imaging;Spectral analysis;Machine learning;Urine sediments;Crystalluria

Received: 2024-03-24 Accepted: 2024-09-03

ZTFLH:

O433.4

Corresponding Authors: LI Qing-li E-mail: qlli@cs.ecnu.edu.cn

Cite this article:

DENG Ying-jiao,CHEN Jun,WANG Jian-sheng, et al. Analysis of Urine Sediment Samples Based on Microscopy Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1243-1250.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)05-1243-08 OR https://www.gpxygpfx.com/EN/Y2025/V45/I05/1243

[1] ZHANG Shu-zhen, ZHANG An-na, SUN Xiao-jing（张淑珍, 张安娜, 孙小景）. Clinical Research（临床研究）, 2023, 31(3): 134.
[2] LUO Wei(罗伟). China Medical Device Information（中国医疗器械信息）, 2023, 29(24): 80.
[3] TIAN Wen-yan（田文艳）. China Medical Device Information(中国医疗器械信息)，2023, 29(5): 122.
[4] CHENG Xing, LI Zhang-yong, JIANG Xiao-ming, et al（程星, 李章勇, 姜小明, 等）. Electronics World（电子世界）, 2018, (5): 180.
[5] Ji Q, Li X, Qu Z, et al. IEEE Access, 2019, 7: 166711.
[6] LAI Ji-bao, KANG Xu-dong, LU Xu-kun, et al（赖积保, 康旭东, 鲁续坤，等）. National Remote Sensing Bulletin（遥感学报）, 2022, 26(8): 1530.
[7] Tamošaityt $\dot{e}$ S, Hendrixson V, Želvys A, et al. Journal of Biomedical Optics, 2013, 18(2): 27011.
[8] Day P L, Erdahl S, Rokke D L, et al. Mayo Clinic Proceedings: Digital Health, 2023, 1(1): 1.
[9] Durdaği Sevil (Porikli), Al- Jalawee Ahmed Hasan Hashim, Yalçin Paşa, et al. Chinese Journal of Physics, 2023，83：379.
[10] CHEN Yu-rong, WANG Yao-nan, ZHANG Hui, et al（陈煜嵘, 王耀南, 张辉, 等）. Artificial Intelligence View（人工智能）, 2022，(3): 22.
[11] KANG Rui, CHENG Ya-wen, ZHOU Ling-li, et al（康睿, 程雅雯, 周玲莉，等）. Spectroscopy And Spectral Analysis（光谱学与光谱分析）, 2024, 44(2): 392.
[12] Wang Qian, Wang Jianbiao, Zhou Mei, et al. Optics & Laser Technology, 2021, 139: 106931.
[13] Zhang Qing, Li Qingli, Yu Guanzhen, et al. IEEE Access, 2019, 7: 149414.
[14] Hosseini M P, Hosseini A, Ahi K. IEEE Reviews in Biomedical Engineering, 2021, 14: 204.
[15] Zhao P, Lai L. IEEE Transactions on Information Theory, 2022, 68(12): 7971.
[16] Dhar S, Cherkassky V. IEEE Transactions on Cybernetics, 2015, 45(4): 806.
[17] Tsang S, Kao B, Yip K Y, et al. IEEE Transactions on Knowledge and Data Engineering, 2011, 23(1): 64.
[18] WANG Chao-liang, LIANG Mei-yan(王朝亮, 梁美彦). Journal of Test and Measurement Technology(测试技术学报), 2024, 38(3): 281.
[19] LeCun Y, Bengio Y, Hinton G. Nature, 2015, 521(7553): 436.