基于近红外图像处理的便携式干眼诊断仪研究

魏琪; 李杰; 邱选兵; 马晋; 李帅伟; 郭古青; 李传亮; 尚建平

基于近红外图像处理的便携式干眼诊断仪研究

魏琪¹,
李杰^{1, 2},
邱选兵^1, ,,
马晋¹,
李帅伟¹,
郭古青¹,
李传亮¹,
尚建平²

1.
太原科技大学应用科学学院, 山西太原 030024
2.
山西瑞豪生物科技有限公司, 山西太原 030025

基金项目:

国家自然科学基金 52076145

国家自然科学基金 U1810129

国家自然科学基金 11904252

详细信息

作者简介:
魏琪（1996-），男，山西霍州人，硕士研究生，研究方向为图像处理、激光光谱技术

通讯作者:
邱选兵（1980-），男，四川内江人，博士，教授，研究方向为激光光谱技术、嵌入式系统。E-mail：qiuxb@tyust.edu.cn

中图分类号: TH77, TP391.41
计量
- 文章访问数: 110
- HTML全文浏览量: 60
- PDF下载量: 22
- 被引次数: 0
出版历程
- 收稿日期: 2021-07-16
- 修回日期: 2021-08-26
- 刊出日期: 2023-02-20

Portable Dry Eye Diagnosis Instrument Using Near-infrared Image Procession

1.
School of Applied Science, Taiyuan University of Science and Technology, Taiyuan 030024, China
2.
Shanxi Rui Hao Biotechnology Co., Ltd., Taiyuan 030025, China

摘要

摘要: 针对目前市面上的干眼诊断设备有诸如成本高、体积大和由于使用帧差法导致检测结果准确度不高等一些问题，本文设计了基于近红外图像诊断干眼的便携式设备。该设备使用基于近红外成像的Windows计算机进行检测，便于携带，可用于检测泪膜破裂时间（tear film break-up time, TBUT）、睑板腺（meibomian gland, MG）与泪河高度（tear meniscus height, TMH）等干眼症状。采用分形盒维数法检测TBUT，避免帧差法检测不准确；通过近红外（850 nm）补光成像技术检测MG，采用对比度受限自适应直方图均衡（contrast-limited adaptive histogram equalization, CLAHE）算法处理，将腺体区域突出，能够更加准确地检测面积缺失率。为了验证该仪器检测结果准确性，使用50组测试样本进行验证性实验，实验结果与意大利的CSO Antares（安达斯）仪器和SBM公司的ICP OSA等的检测结果进行对比。该设备的TBUT和TMH检测的结果与两个对照组结果的相关系数为P < 0.05，检测的结果一致性较好；MG的检测正确率为86%，特异度为84%。实验结果表明，该设备可作为干眼症的筛查和诊断设备用于眼科医院和视觉光学中心。
- 干眼症 /
- 近红外图像处理 /
- 非侵入式泪膜破裂时间 /
- 睑板腺诊断 /
- 分形盒维数
Abstract: To address the limitations of current dry eye diagnostic equipment in the market, such as high cost, large volume, and low accuracy of detection results due to the use of the frame difference method, this study proposes portable dry eye diagnostic equipment based on near-infrared images. The device, which uses a Windows computer based on near-infrared imaging, is portable and can be used to detect dry eye symptoms such as the tear film break-up time (TBUT), meibomian gland (MG), and tear meniscus height (TMH). The fractal box dimension method was used to detect TBUT to avoid the inaccuracy of the frame difference method. MG was detected using near-infrared (850 nm) fill light imaging technology, and the contrast limited adaptive histogram equalization (CLAHE) algorithm was used to highlight the gland region, which can detect the area missing rate more accurately. To verify the accuracy of the test results, 50 samples were tested and compared with the CSO Antares instrument from Italy and the ICP OSA from SBM. The correlation coefficient between the TBUT and TMH measurements of the device and the results of the two controls was P < 0.05, whereas the detection results were consistent; the accuracy and specificity of MG were 86% and 84%, respectively. The experimental results showed that the device can be used as a screening and diagnostic device for dry eye disease in eye and vision optics centers.
- dry eye symptom /
- near-infrared image process /
- noninvasive tear film break-up time /
- meibomian gland diagnosis /
- fractal box dimension

HTML全文

图 1 干眼检测仪硬件结构

Figure 1. Hardware structure of dry eye detector

下载: 全尺寸图片幻灯片

图 2 实物图

Figure 2. Photo of real product

下载: 全尺寸图片幻灯片

图 3 睑板腺直方图

Figure 3. MG histogram

下载: 全尺寸图片幻灯片

图 4 未破裂与破裂区域分形维数

Figure 4. Fractal dimension diagram for the unbroken and broken regions

下载: 全尺寸图片幻灯片

图 5 软件用户界面框架

Figure 5. Software user interface framework

下载: 全尺寸图片幻灯片

图 6 患者信息管理界面

Figure 6. Patient management interface

下载: 全尺寸图片幻灯片

图 7 Antares和OSA设备

Figure 7. Antares and OSA instruments

下载: 全尺寸图片幻灯片

图 8 干眼诊断结果

Figure 8. Dry eye diagnosis results

下载: 全尺寸图片幻灯片

表 1 睑板腺检测结果

Table 1. Meibomian gland test results

Groups	TP	FP	TN	FN
Results	22	4	21	3

下载: 导出CSV

表 2 泪膜平均破裂时间实验结果对比

Table 2. Comparison of the experimental results of the average TBUT

Groups	Dry eye group	Critical group	Normal group
This work	4.58±2.843	9.725±0.069	14.466±6.055
Antares	4.808±2.857	9.75±0.043	14.583±6.342
OSA	4.900±3.176	9.875±0.223	14.533±7.235
P	< 0.001	< 0.001	< 0.001

下载: 导出CSV

表 3 泪河高度实验结果对比

Table 3. Comparison of experimental results of TMH

Groups	Dry eye group	Normal group
This work	0.2526±0.056	0.426±0.037
Antares	0.256±0.050	0.435±0.032
OSA	0.2689±0.051	0.490±0.035
P	< 0.05	< 0.05

下载: 导出CSV

参考文献(20)

[1]	孙铁, 石文卿, 邵毅. 干眼成像技术的研究进展[J]. 国际眼科杂志, 2019, 19(6): 937-940. https://www.cnki.com.cn/Article/CJFDTOTAL-GJYK201906014.htm SUN T, SHI W Q, SHAO Y. Research progress on dry eye imaging technology[J]. International Eye Science (IES), 2019, 19(6): 937-940. https://www.cnki.com.cn/Article/CJFDTOTAL-GJYK201906014.htm
[2]	余婷, 叶芬, 施宇华, 等. 睑板腺功能障碍患者的视觉质量分析[J]. 眼科新进展, 2017, 37(10): 966-969. https://www.cnki.com.cn/Article/CJFDTOTAL-XKJZ201710019.htm YU T, YE F, SHI Y H, et al. Evaluation of visual quality in patients with meibomian gland dysfunction[J]. Recent Advances in Ophthalmology, 2017, 37(10): 966-969. https://www.cnki.com.cn/Article/CJFDTOTAL-XKJZ201710019.htm
[3]	王蕊, 李岩, 高建民, 等. 干眼患者泪膜及睑板腺功能分析[J]. 眼科新进展, 2016, 36(12): 1145-1149. https://www.cnki.com.cn/Article/CJFDTOTAL-XKJZ201612013.htm WANG R, LI Y, GAO J M, et al. Assessment of tear film and meibomian gland function in dry eye patients[J]. Recent Advances in Ophthalmology, 2016, 36(12): 1145-1149. https://www.cnki.com.cn/Article/CJFDTOTAL-XKJZ201612013.htm
[4]	诸科璇, 谢文加, 应靖璐, 等. 运用Keratograph 5M眼表综合分析仪评价干眼患者的泪膜及睑板腺功能[J]. 浙江大学学报(医学版), 2016, 45(4): 422-42. https://www.cnki.com.cn/Article/CJFDTOTAL-ZJYB201604019.htm ZHU K X, XIE W J, YING J L, et al. Evaluation of tear film and meibomian gland function in dry eye patients using Keratograph[J]. Journal of Zhejiang University (Medical Science), 2016, 45(4): 422-42. https://www.cnki.com.cn/Article/CJFDTOTAL-ZJYB201604019.htm
[5]	宁玉贤, 赵少贞. 非侵入性眼表综合分析仪及Lipiview眼表面干涉仪评估儿童干眼的特点[J]. 眼科新进展, 2019, 39(1): 78-80. https://www.cnki.com.cn/Article/CJFDTOTAL-XKJZ201901018.htm NING Y X, ZHAO S Z, Evaluation of dry eye in children by Keratograph 5 M and lipiview ocular surface interometry[J]. Recent Advances in Ophthalmology, 2019, 39(1): 78-80. https://www.cnki.com.cn/Article/CJFDTOTAL-XKJZ201901018.htm
[6]	Lee J S, Jun I, Kim E K, et al. Clinical accuracy of an advanced corneal topographer with tear-film analysis in functional and structural evaluation of dry eye disease[J]. Seminars in ophthalmology, 2020, 35(2): 134-140. doi: 10.1080/08820538.2020.1755321
[7]	李萌萌, 张晓峰, 阙丽娟, 等. 睑板腺红外线成像装置两种图像分析方法的比较[J]. 中国现代医药杂志, 2016, 18(2): 6-9. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHTY201602003.htm LI M M, ZHANG X F, QUE L J, YIN Y C, et al. Comparison of the two methods of image analysis of infrared meibography[J]. Modern Medicine Journal of China, 2016, 18(2): 6-9. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHTY201602003.htm
[8]	顾可可, 付威威, 董月芳, 等. 基于改进轮廓跟踪的瞳孔快速检测[J]. 红外技术, 2017, 39(6): 574-578. http://hwjs.nvir.cn/article/id/hwjs201706017 GU K K, FU W W, DONG Y F, et al. Rapid pupil detection based on improved contour tracking[J]. Infrared Technology, 2017, 39(6): 574-578. http://hwjs.nvir.cn/article/id/hwjs201706017
[9]	Ratprakhon K, Neubauer W, Riehn K, et al. Developing an automatic color determination procedure for the quality assessment of mangos (Mangifera indica) using a CCD camera and color standards[J]. Foods, 2020, 9(11): 1709.
[10]	段一平, 李浩攀. MATLAB在图像处理中的应用[J]. 科技信息, 2009(10): 213-214. https://www.cnki.com.cn/Article/CJFDTOTAL-HLKX200826081.htm DUAN Y P, LI H P. Application of MATLAB in image processing[J]. Scientific and Technological Information, 2009(10): 213-214. https://www.cnki.com.cn/Article/CJFDTOTAL-HLKX200826081.htm
[11]	贾迪, 孟绿, 张一飞, 等. 一种彩色图像的同步去噪增强算法[J]. 小型微型计算机系统, 2014, 35(3): 659-662. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX201403048.htm JIA D, MENG L, ZHANG Y F, et al. Synchronization algorithm of color image denoising and enhancement[J]. Journal of Chinese Computer Systems, 2014, 35(3): 659-662. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX201403048.htm
[12]	王红茹, 李瑞, 王佳. 基于改进CLAHE的水下彩色图像增强算法[J]. 舰船电子工程, 2019, 39(11): 119-122, 141. https://www.cnki.com.cn/Article/CJFDTOTAL-JCGC201911030.htm WANG H R, LI R, WANG J. Underwater color image enhancement algorithm based on improved CLAHE[J]. Ship Electronic Engineering, 2019, 39(11): 119-122, 141. https://www.cnki.com.cn/Article/CJFDTOTAL-JCGC201911030.htm
[13]	罗强, 吴俊峰, 于红, 等. 一种基于改进直方图均衡化的显著图提取算法[J]. 小型微型计算机系统, 2018, 39(5): 1092-1096. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX201805041.htm LUO Q, WU J F, YU H, et al. Saliency detection algorithm based on improved histogram equalization[J]. Journal of Chinese Computer Systems, 2018, 39(5): 1092-1096. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX201805041.htm
[14]	Llorens-Quintana C, Iskander D R. Assessment of tear film using videokeratoscopy based on fractal dimension[J]. Optom. Vis. Sci., 2018, 95(1): 32-42.
[15]	Alonso-Caneiro D, Szczesna-Iskander D H, Iskander D R, et al. Application of texture analysis in tear film surface assessment based on videokeratoscopy[J]. Journal of Optometry, 2013, 6(4): 185-193.
[16]	Bisoi A K, Mishra J. On calculation of fractal dimension of images[J]. Pattern Recognition Letters, 2001, 22(6-7): 631-637.
[17]	Koprowski R, TIAN L, Olczyk P. A clinical utility assessment of the automatic measurement method of the quality of Meibomian glands[J]. Biomedical Engineering Online, 2017, 16(1): 82.
[18]	Bartuzel M M, Szczesna-Iskander D H, Iskander D R. Automatic dynamic tear meniscus measurement in optical coherence tomography[J]. Biomedical Optics Express, 2014, 5(8): 2759-2768.
[19]	Szczesna-Iskander D H, Alonso-Caneiro D, Iskander D R. Objective measures of pre-lens tear film dynamics versus visual responses[J]. Optometry & Vision Science Official Publication of the American Academy of Optometry, 2016, 93(8): 872-80.
[20]	陈娟, 梅芳, 陈志钧. 儿童泪膜破裂时间与瞬目异常的临床研究[J]. 南京医科大学学报, 2019, 39(12): 1816-1819. https://www.cnki.com.cn/Article/CJFDTOTAL-SYYZ201214046.htm CHEN J, MEI F, CHEN Z J. Clinical study of tear film rupture time and blink abnormality in children[J]. Journal of Nanjing Medical University(Natural Sciences), 2019, 39(12): 1816-1819. https://www.cnki.com.cn/Article/CJFDTOTAL-SYYZ201214046.htm