scholarly journals Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study

BMJ Open ◽  
2019 ◽  
Vol 9 (9) ◽  
pp. e031313 ◽  
Author(s):  
Kazutaka Kamiya ◽  
Yuji Ayatsuka ◽  
Yudai Kato ◽  
Fusako Fujimura ◽  
Masahide Takahashi ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Diagnostic Accuracy ◽  
Anterior Segment ◽  
Optical Coherence ◽  
Diagnostic Accuracy Study ◽  
Clinical Trial Registration ◽  
Swept Source ◽  
Refractive Power ◽  
Accuracy Study

ObjectiveTo evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).DesignA diagnostic accuracy study.SettingA single-centre study.ParticipantsA total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes.Main outcome measuresThe diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map).ResultsDeep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage.ConclusionsDeep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice.Clinical trial registration number000034587.

scholarly journals Objective quantification of lens nuclear opacities using swept-source anterior segment optical coherence tomography

2021 ◽  
pp. bjophthalmol-2020-318334
Author(s):  
Wei Wang ◽  
Jiaqing Zhang ◽  
Xiaoxun Gu ◽  
Xiaoting Ruan ◽  
Xiaoyun Chen ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Visual Acuity ◽  
Anterior Segment ◽  
Training Dataset ◽  
Dissipated Energy ◽  
Nuclear Density ◽  
Optical Coherence ◽  
Nuclear Cataract ◽  
Swept Source ◽  
Ultrasonic Time

Background/aimsThe primary objective is to quantify the lens nuclear opacity using swept-source anterior segment optical coherence tomography (SS-ASOCT) and to evaluate its correlations with Lens Opacities Classification System III (LOCS-III) system and surgical parameters. The secondary objective is to assess the diagnostic performance for hard nuclear cataract.MethodsThis cross-sectional study included 1222 patients eligible for cataract surgery (1222 eyes). The latest SS-ASOCT (CASIA-2) was used to obtain high-resolution lens images, and the average nuclear density (AND) and maximum nuclear density (MND) were measured by a custom ImageJ software. Spearman’s correlations analysis was used to assess associations of AND/MND with LOCS-III nuclear scores, visual acuity and surgical parameters. The subjects were then split randomly (9:1) into the training dataset and validating dataset. Receiver operating characteristic curves and calibration curves were constructed for the classification on hard nuclear cataract.ResultsThe AND and MND from SS-ASOCT images were significantly correlated with nuclear colour scores (AND: r=0.716; MND: r=0.660; p<0.001) and nuclear opalescence scores (AND: r=0.712; MND: r=0.655; p<0.001). The AND by SS-ASOCT images had the highest values of Spearman’s r for preoperative corrected distance visual acuity (r=0.3131), total ultrasonic time (r=0.3481) and cumulative dissipated energy (r=0.4265). The nuclear density had good performance in classifying hard nuclear cataract, with area under the curves of 0.859 (0.831–0.886) for AND and 0.796 (0.768–0.823) for MND.ConclusionObjective and quantitative evaluation of the lens nuclear density using SS-ASOCT images enable accurate diagnosis of hard nuclear cataract.

Relevance of Swept-Source Anterior Segment Optical Coherence Tomography for Corneal Imaging in Patients With Flap-Related Complications After LASIK

Cornea ◽  
2019 ◽  
Vol 38 (1) ◽  
pp. 93-97 ◽  
Author(s):  
Khaled Abdelazeem ◽  
Mohamed Sharaf ◽  
Mohamed G. A. Saleh ◽  
Ahmed M. Fathalla ◽  
Wael Soliman
Keyword(s):  
Optical Coherence Tomography ◽  
Anterior Segment ◽  
Optical Coherence ◽  
Swept Source ◽  
Corneal Imaging

Morphometric Measurement of Schlemm′s Canal Using Anterior Segment Swept Source Optical Coherence Tomography

2013 ◽  
Vol 50 (8) ◽  
pp. 080014
Author(s):  
史国华 Shi Guohua ◽  
王飞 Wang Fei ◽  
李喜琪 Li Xiqi ◽  
孙兴怀 Sun Xinghuai ◽  
姜春晖 Jiang Chunhui ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Anterior Segment ◽  
Optical Coherence ◽  
Morphometric Measurement ◽  
Swept Source

Impact of Cataract Surgery on Filtering Bleb Morphology Identified Via Swept-source 3-dimensional Anterior Segment Optical Coherence Tomography

2019 ◽  
Vol 28 (5) ◽  
pp. 433-439
Author(s):  
Akiko Narita ◽  
Yuki Morizane ◽  
Tomoe Miyake ◽  
Kae Sugihara ◽  
Tomoko Ishikawa ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Cataract Surgery ◽  
Anterior Segment ◽  
Optical Coherence ◽  
Swept Source ◽  
3 Dimensional ◽  
Filtering Bleb

scholarly journals Comparison of two different optical coherence tomography angiography devices in detecting healthy versus glaucomatous eyes – an observational cross-sectional study

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
A. R. Kee ◽  
V. C. H. Yip ◽  
E. L. T. Tay ◽  
C. W. Lim ◽  
J. Cheng ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Diagnostic Accuracy ◽  
Optic Disc ◽  
Optical Coherence Tomography Angiography ◽  
Optical Coherence ◽  
Cross Sectional ◽  
Swept Source ◽  
Retest Reliability ◽  
Significant Difference ◽  
Test Retest Reliability

Abstract Background To understand the differences between two different optical coherence tomography angiography (OCTA) devices in detecting glaucomatous from healthy eyes by comparing their vascular parameters, diagnostic accuracy and test-retest reliability. Methods A cross-sectional observational study was performed on healthy and glaucoma subjects, on whom two sets of OCTA images of optic disc and macula were acquired using both AngioVue (Optovue, USA) and Swept Source (Topcon, Japan) OCTA devices during one visit. A novel in-house software was used to calculate the vessel densities. Diagnostic accuracy of the machines in differentiating healthy versus glaucomatous eyes was determined using area under the receiver operating characteristic curve (AUROC) and test-retest repeatability of the machines was also evaluated. Results A total of 80 healthy and 38 glaucomatous eyes were evaluated. Glaucomatous eyes had reduced mean vessel density compared to healthy controls in all segmented layers of the optic disc and macula using AngioVue (p ≤ 0.001). However, glaucomatous eyes had higher mean vessel density on optic disc scans using Swept Source, with lack of statistically significant difference between healthy and glaucomatous eyes. The AUROC showed better diagnostic accuracy of AngioVue (0.761–1.000) compared to Swept Source (0.113–0.644). The test-retest reliability indices were generally better using AngioVue than Swept Source. Conclusions AngioVue showed better diagnostic capability and test-retest reliability compared to Swept Source. Further studies need to be undertaken to evaluate if there is any significant difference between the various machines in diagnosing and monitoring glaucoma.

Sign in / Sign up

Export Citation Format

Share Document