Literature DB >> 33576859

Automatic screening of tear meniscus from lacrimal duct obstructions using anterior segment optical coherence tomography images by deep learning.

Hitoshi Imamura1, Hitoshi Tabuchi1,2, Daisuke Nagasato3,4, Hiroki Masumoto1,2, Hiroaki Baba1, Hiroki Furukawa1, Sachiko Maruoka1.   

Abstract

PURPOSE: We assessed the ability of deep learning (DL) models to distinguish between tear meniscus of lacrimal duct obstruction (LDO) patients and normal subjects using anterior segment optical coherence tomography (ASOCT) images.
METHODS: The study included 117 ASOCT images (19 men and 98 women; mean age, 66.6 ± 13.6 years) from 101 LDO patients and 113 ASOCT images (29 men and 84 women; mean age, 38.3 ± 19.9 years) from 71 normal subjects. We trained to construct 9 single and 502 ensemble DL models with 9 different network structures, and calculated the area under the curve (AUC), sensitivity, and specificity to compare the distinguishing abilities of these single and ensemble DL models.
RESULTS: For the highest single DL model (DenseNet169), the AUC, sensitivity, and specificity for distinguishing LDO were 0.778, 64.6%, and 72.1%, respectively. For the highest ensemble DL model (VGG16, ResNet50, DenseNet121, DenseNet169, InceptionResNetV2, InceptionV3, and Xception), the AUC, sensitivity, and specificity for distinguishing LDO were 0.824, 84.8%, and 58.8%, respectively. The heat maps indicated that these DL models placed their focus on the tear meniscus region of the ASOCT images.
CONCLUSION: The combination of DL and ASOCT images could distinguish between tear meniscus of LDO patients and normal subjects with a high level of accuracy. These results suggest that DL might be useful for automatic screening of patients for LDO.

Entities:  

Keywords:  Anterior segment optical coherence tomography image; Area under the curve; Deep learning; Lacrimal duct obstruction; Tear meniscus

Year:  2021        PMID: 33576859     DOI: 10.1007/s00417-021-05078-3

Source DB:  PubMed          Journal:  Graefes Arch Clin Exp Ophthalmol        ISSN: 0721-832X            Impact factor:   3.117


  36 in total

1.  Tear meniscus measurement by spectral optical coherence tomography.

Authors:  Grzegorz Czajkowski; Bartlomiej J Kaluzny; Adriana Laudencka; Grażyna Malukiewicz; Jakub J Kaluzny
Journal:  Optom Vis Sci       Date:  2012-03       Impact factor: 1.973

2.  Nasolacrimal duct obstruction classified by dacryoendoscopy and treated with inferior meatal dacryorhinotomy. Part I: Positional diagnosis of primary nasolacrimal duct obstruction with dacryoendoscope.

Authors:  Tsugihisa Sasaki; Yuuko Nagata; Kazuhisa Sugiyama
Journal:  Am J Ophthalmol       Date:  2005-12       Impact factor: 5.258

3.  Nasolacrimal duct obstruction classified by dacryoendoscopy and treated with inferior meatal dacryorhinotomy: Part II. Inferior meatal dacryorhinotomy.

Authors:  Tsugihisa Sasaki; Yuuko Nagata; Kazuhisa Sugiyama
Journal:  Am J Ophthalmol       Date:  2005-12       Impact factor: 5.258

4.  Agreement between stratus and visante optical coherence tomography systems in tear meniscus measurements.

Authors:  Giacomo Savini; Eiki Goto; Michele Carbonelli; Piero Barboni; David Huang
Journal:  Cornea       Date:  2009-02       Impact factor: 2.651

5.  The dynamics and drainage of tears.

Authors:  D M Maurice
Journal:  Int Ophthalmol Clin       Date:  1973

6.  Digital subtraction macrodacryocystography. A new method of lacrimal system imaging.

Authors:  J E Galloway; T A Kavic; G T Raflo
Journal:  Ophthalmology       Date:  1984-08       Impact factor: 12.079

7.  Dacryoendoscopic observation and incidence of canalicular obstruction/stenosis associated with S-1, an oral anticancer drug.

Authors:  Tsugihisa Sasaki; Hiroaki Miyashita; Tamon Miyanaga; Katsushi Yamamoto; Kazuhisa Sugiyama
Journal:  Jpn J Ophthalmol       Date:  2012-03-13       Impact factor: 2.447

8.  Age-related variations of human tear meniscus and diagnosis of dry eye with Fourier-domain anterior segment optical coherence tomography.

Authors:  Xiaodi Qiu; Lan Gong; Xinghuai Sun; Huan Jin
Journal:  Cornea       Date:  2011-05       Impact factor: 2.651

9.  Application of visante optical coherence tomography tear meniscus height measurement in the diagnosis of dry eye disease.

Authors:  Osama M A Ibrahim; Murat Dogru; Yoji Takano; Yoshiyuki Satake; Tais Hitomi Wakamatsu; Kazumi Fukagawa; Kazuo Tsubota; Hiroshi Fujishima
Journal:  Ophthalmology       Date:  2010-06-03       Impact factor: 12.079

10.  Upper and lower tear menisci in the diagnosis of dry eye.

Authors:  Meixiao Shen; Jianhua Li; Jianhua Wang; Huixiang Ma; Chunyan Cai; Aizhu Tao; Yimin Yuan; Fan Lu
Journal:  Invest Ophthalmol Vis Sci       Date:  2009-02-14       Impact factor: 4.799

View more
  1 in total

Review 1.  Understanding required to consider AI applications to the field of ophthalmology.

Authors:  Hitoshi Tabuchi
Journal:  Taiwan J Ophthalmol       Date:  2022-04-13
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.