基于角膜共聚焦显微镜的神经纤维人工智能分析方法

吴俊; 费思佳; 沈博; 张瀚文; 黄剑锋; 潘琦; 赵建春; 丁大勇

doi:10.12290/xhyxzz.2021-0510

基于角膜共聚焦显微镜的神经纤维人工智能分析方法

doi: 10.12290/xhyxzz.2021-0510

吴俊¹,
费思佳^{2, 4},
沈博¹,
张瀚文¹,
黄剑锋³,
潘琦^4, ,,
赵建春⁵,
丁大勇⁵

基金项目:

国家重点研发计划 2020YFC2009006

国家重点研发计划 2020YFC2009000

陕西省自然科学基础研究计划 2020JM-129

西北工业大学硕士研究生创意创新种子基金 CX2020162

西北工业大学国家级大学生创新创业训练计划 S202010699207

西北工业大学国家级大学生创新创业训练计划 S202010699630

详细信息

通讯作者:
潘琦电话：010-85138663，E-mail: panqi621@126.com

中图分类号: R-1; R770.4; R587.1
计量
- 文章访问数: 132
- HTML全文浏览量: 101
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2021-07-02
- 录用日期: 2021-07-29
- 网络出版日期: 2021-11-26
- 发布日期: 2021-09-22
- 刊出日期: 2021-09-30

Artificial Intelligence Analysis of Nerve Fibers Based on Corneal Confocal Microscopy

Funds:

China National Key R & D Program 2020YFC2009006

China National Key R & D Program 2020YFC2009000

Natural Science Basic Research Plan in Shaanxi Province of China 2020JM-129

Seed Foundation of Innovation and Creation for Postgraduate Students in Northwestern Polytechnical University CX2020162

National Innovation and Entrepreneurship Training Program for College Students S202010699207

National Innovation and Entrepreneurship Training Program for College Students S202010699630

More Information

Corresponding author: PAN Qi Tel: 86-10-85138663, E-mail: panqi621@126.com

摘要

摘要: 糖尿病周围神经病变(diabetic peripheral neuropathy, DPN)是糖尿病最常见的慢性并发症之一。基于临床症状体征以及电生理检查的传统DPN诊断方法主要用于检测大神经纤维病变，而DPN最早出现损伤的部位是小神经纤维。角膜共聚焦显微镜(corneal confocal microscopy, CCM)能够在高倍镜下分析角膜神经纤维的变化，是一种快速、可重复、定量测量小神经纤维病变的无创技术，可早期诊断DPN并前瞻性评估神经形态学改变，具有良好的应用前景。本文就CCM评估糖尿病神经病变的临床应用研究以及CCM相关人工智能分析方法进行综述，以期为临床诊疗提供借鉴。
- 人工智能 /
- 深度学习 /
- 角膜共聚焦显微镜 /
- 糖尿病周围神经病变
Abstract: Diabetic peripheral neuropathy (DPN) is one of the most common chronic complications of diabetes. Traditional DPN diagnostic methods are based on clinical symptoms and signs as well as electrophysiological examination, which are mainly used to detect the lesions of large nerve fibers. However, the small nerve fibers are the earliest ones damaged in DPN. Corneal confocal microscopy (CCM) can analyze the changes of corneal nerve fibers under a high power microscope. It is a rapid, repeatable and quantitative noninvasive technique to measure small nerve fibers. It can diagnose DPN early and evaluate neuromorphological changes prospectively. It has a good application expectation. During this article, we summarized the role and limitations of DPN's most reliable parameters of corneal nerve in evaluating diabetic autonomic neuropathy and diabetic micro-vascular complications. Further, we reviewed the clinical application of CCM in evaluating diabetic neuropathy and analysis methods of CCM related artificial intelligence, in order to provide references for clinical diagnosis and treatment.
- artificial intelligence /
- deep learning /
- corneal confocal microscopy /
- diabetic peripheral neuropathy

HTML全文

参考文献(37)

[1]	Maddaloni E, Sabatino F. In vivo corneal confocal microscopy in diabetes: Where we are and where we can get[J]. World J Diabetes, 2016, 7: 406-411. doi: 10.4239/wjd.v7.i17.406
[2]	Mansoor H, Tan HC, Lin MT, et al. Diabetic Corneal Neuropathy[J]. J Clin Med, 2020, 9: 3956. doi: 10.3390/jcm9123956
[3]	Shtein RM, Callaghan BC. Corneal confocal microscopy as a measure of diabetic neuropathy[J]. Diabetes, 2013, 62: 25-26. doi: 10.2337/db12-1114
[4]	Ferdousi M, Kalteniece A, Azmi S, et al. Diagnosis of Neuropathy and Risk Factors for Corneal Nerve Loss in Type 1 and Type 2 Diabetes: A Corneal Confocal Microscopy Study[J]. Diabetes Care, 2021, 44: 150-156. doi: 10.2337/dc20-1482
[5]	Chen X, Graham J, Dabbah MA, et al. Small nerve fiber quantification in the diagnosis of diabetic sensorimotor polyneuropathy: comparing corneal confocal microscopy with intraepidermal nerve fiber density[J]. Diabetes Care, 2015, 38: 1138-1144. doi: 10.2337/dc14-2422
[6]	Ziegler D, Papanas N, Zhivov A, et al. Early detection of nerve fiber loss by corneal confocal microscopy and skin biopsy in recently diagnosed type 2 diabetes[J]. Diabetes, 2014, 63: 2454-2463. doi: 10.2337/db13-1819
[7]	Tavakoli M, Quattrini C, Abbott C, et al. Corneal confocal microscopy: a novel noninvasive test to diagnose and stratify the severity of human diabetic neuropathy[J]. Diabetes Care, 2010, 33: 1792-1798. doi: 10.2337/dc10-0253
[8]	Roszkowska AM, Licitra C, Tumminello G, et al. Corneal nerves in diabetes-The role of the in vivo corneal confocal microscopy of the subbasal nerve plexus in the assessment of peripheral small fiber neuropathy[J]. Surv Ophthalmol, 2021, 66: 493-513. doi: 10.1016/j.survophthal.2020.09.003
[9]	Medeiros CS, Santhiago MR. Corneal nerves anatomy, function, injury and regeneration[J]. Exp Eye Res, 2020, 200: 108243. doi: 10.1016/j.exer.2020.108243
[10]	Malik RA, Kallinikos P, Abbott CA, et al. Corneal confocal microscopy: a non-invasive surrogate of nerve fibre damage and repair in diabetic patients[J]. Diabetologia, 2003, 46: 683-688. doi: 10.1007/s00125-003-1086-8
[11]	Markoulli M, Flanagan J, Tummanapalli SS, et al. The impact of diabetes on corneal nerve morphology and ocular surface integrity[J]. Ocul Surf, 2018, 16: 45-57. doi: 10.1016/j.jtos.2017.10.006
[12]	Salahouddin T, Petropoulos IN, Ferdousi M, et al. Artificial Intelligence-Based Classification of Diabetic Peripheral Neuropathy From Corneal Confocal Microscopy Images[J]. Diabetes Care, 2021, 44: e1-e3. doi: 10.2337/dc20-1534
[13]	De Clerck EE, Schouten JS, Berendschot TT, et al. New ophthalmologic imaging techniques for detection and monitoring of neurodegenerative changes in diabetes: a systematic review[J]. Lancet Diabetes Endocrinol, 2015, 3: 653-663. doi: 10.1016/S2213-8587(15)00136-9
[14]	Asghar O, Petropoulos IN, Alam U, et al. Corneal confocal microscopy detects neuropathy in subjects with impaired glucose tolerance[J]. Diabetes Care, 2014, 37: 2643-2646. doi: 10.2337/dc14-0279
[15]	Szalai E, Deák E, Módis L Jr, et al. Early Corneal Cellular and Nerve Fiber Pathology in Young Patients With Type 1 Diabetes Mellitus Identified Using Corneal Confocal Microscopy[J]. Invest Ophthalmol Vis Sci, 2016, 57: 853-859. doi: 10.1167/iovs.15-18735
[16]	Yan A, Issar T, Tummanapalli SS, et al. Relationship between corneal confocal microscopy and markers of peripheral nerve structure and function in Type 2 diabetes[J]. Diabet Med, 2020, 37: 326-334. doi: 10.1111/dme.13952
[17]	Jiang MS, Yuan Y, Gu ZX, et al. Corneal confocal microscopy for assessment of diabetic peripheral neuropathy: a meta-analysis[J]. Br J Ophthalmol, 2016, 100: 9-14. doi: 10.1136/bjophthalmol-2014-306038
[18]	贾晓凡. 角膜共焦显微镜在2型糖尿病周围神经病变中的应用价值研究[D]. 北京: 北京协和医学院, 2017.
[19]	Ferdousi M, Kalteniece A, Azmi S, et al. Corneal confocal microscopy compared with quantitative sensory testing and nerve conduction for diagnosing and stratifying the severity of diabetic peripheral neuropathy[J]. BMJ Open Diabetes Res Care, 2020, 8: e001801. doi: 10.1136/bmjdrc-2020-001801
[20]	Hossain P, Sachdev A, Malik RA. Early detection of diabetic peripheral neuropathy with corneal confocal microscopy[J]. Lancet, 2005, 366: 1340-1343. doi: 10.1016/S0140-6736(05)67546-0
[21]	Petropoulos IN, Ponirakis G, Khan A, et al. Diagnosing Diabetic Neuropathy: Something Old, Something New[J]. Diabetes Metab J, 2018, 42: 255-269. doi: 10.4093/dmj.2018.0056
[22]	Tavakoli M, Begum P, Mclaughlin J, et al. Corneal confocal microscopy for the diagnosis of diabetic autonomic neuropathy[J]. Muscle Nerve, 2015, 52: 363-370. doi: 10.1002/mus.24553
[23]	Maddaloni E, Sabatino F, Del Toro R, et al. In vivo corneal confocal microscopy as a novel non-invasive tool to investi-gate cardiac autonomic neuropathy in Type 1 diabetes[J]. Diabet Med, 2015, 32: 262-266. doi: 10.1111/dme.12583
[24]	Petropoulos IN, Green P, Chan AW, et al. Corneal confocal microscopy detects neuropathy in patients with type 1 diabetes without retinopathy or microalbuminuria[J]. PLoS One, 2015, 10: e0123517. doi: 10.1371/journal.pone.0123517
[25]	Srinivasan S, Dehghani C, Pritchard N, et al. Ophthalmic and clinical factors that predict four-year development and worsening of diabetic retinopathy in type 1 diabetes[J]. J Diabetes Complications, 2018, 32: 67-74. doi: 10.1016/j.jdiacomp.2017.09.002
[26]	Brines M, Dunne AN, Velzen MV, et al. ARA 290, a non-erythropoietic peptide engineered from erythropoiethin, improves metabolic control and neuropathic symptoms in patients with type 2 diabetes[J]. Mol Med, 2015, 20: 658-666. http://europepmc.org/articles/PMC4365069/
[27]	Tavakoli M, Mitu-Pretorian M, Petropoulos IN, et al. Corneal confocal microscopy detects early nerve regeneration in diabetic neuropathy after simultaneous pancreas and kidney transplantation[J]. Diabetes, 2013, 62: 254-260. doi: 10.2337/db12-0574
[28]	Dabbah MA, Graham J, Petropoulos I, et al. Dual-Model Automatic Detection of Nerve-Fibres in Corneal Confocal Microscopy Images[C]. International Conference on Medical Image Computing & Computer-assisted Intervention, 2010, 13: 300-307.
[29]	Chen X, Graham J, Dabbah M, et al. An Automatic Tool for Quantification of Nerve Fibres in Corneal Confocal Micros-copy Images[J]. IEEE Trans Biomed Eng, 2017, 64: 786-794. doi: 10.1109/TBME.2016.2573642
[30]	Kim J, Markoulli M. Automatic analysis of corneal nerves imaged using in vivo confocal microscopy[J]. Clin Exp Optom, 2018, 101: 147-161. doi: 10.1111/cxo.12640
[31]	陈新建, 石霏, 周鑫鑫, 等. 一种U型网络及角膜图像中神经纤维的分割方法[P]. 中国专利: CN202010068764. X, 2020-06-23.
[32]	Williams BM, Borroni D, Liu R, et al. An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study[J]. Diabetologia, 2020, 63: 419-430. doi: 10.1007/s00125-019-05023-4
[33]	Yildiz E, Arslan AT, Yildiz Tas A, et al. Generative Adversarial Network Based Automatic Segmentation of Corneal Subbasal Nerves on In Vivo Confocal Microscopy Images[J]. Transl Vis Sci Technol, 2021, 10: 33. http://www.researchgate.net/publication/351892278_Generative_Adversarial_Network_Based_Automatic_Segmentation_of_Corneal_Subbasal_Nerves_on_In_Vivo_Confocal_Microscopy_Images
[34]	Salahuddin T, Qidwai U. Evaluation of Loss Functions for Segmentation of Corneal Nerves[C]. IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2021: 533-537.
[35]	Kucharski A, Fabijańska A. CNN-watershed: A watershed transform with predicted markers for corneal endothelium image segmentation[J]. Biomed Signal Proces, 2021, 68: 1746-8094. http://www.researchgate.net/publication/352009652_CNN-watershed_A_watershed_transform_with_predicted_markers_for_corneal_endothelium_image_segmentation
[36]	Mou L, Zhao Y, Fu H, et al. CS2-Net: Deep learning segmentation of curvilinear structures in medical imaging[J], Med Image Anal, 2021, 67: 1361-8415. http://www.sciencedirect.com/science/article/pii/S1361841520302383
[37]	Wei S, Shi F, Wang Y, et al. A deep learning model for automated sub-basal corneal nerve segmentation and evaluation using in vivo confocal microscopy[J]. Transl Vis Sci Technol, 2020, 9: 32. http://www.researchgate.net/publication/342288647_A_Deep_Learning_Model_for_Automated_Sub-Basal_Corneal_Nerve_Segmentation_and_Evaluation_Using_In_Vivo_Confocal_Microscopy