Dataset Information

An AI model to estimate visual acuity based solely on cross-sectional OCT imaging of various diseases.

ABSTRACT:

Purpose

To develop an artificial intelligence (AI) model for estimating best-corrected visual acuity (BCVA) using horizontal and vertical optical coherence tomography (OCT) scans of various retinal diseases and examine factors associated with its accuracy.

Methods

OCT images and associated BCVA measurements from 2,700 OCT images (accrued from 2004 to 2018 with an Atlantis, Triton; Topcon, Tokyo, Japan) of 756 eyes of 469 patients and their BCVA were retrospectively analysed. For each eye, one horizontal and one vertical OCT scan in cross-line mode were used. The GoogLeNet architecture was implemented. The coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE) were computed to evaluate the performance of the trained network.

Results

R², RMSE, and MAE were 0.512, 0.350, and 0.321, respectively. R² was higher in phakic eyes than in pseudophakic eyes. Multivariable regression analysis showed that a higher R² was significantly associated with better BCVA (p < 0.001) and a higher standard deviation of BCVA (p < 0.001). However, the performance was worse in an external validation, with R² of 0.19. R² values for retinal vein occlusion and age-related macular degeneration were 0.961 and 0.373 in the internal validation but 0.20 and 0.22 in the external validation.

Conclusion

Although underspecification appears to be a fundamental problem to be addressed in AI models for predicting visual acuity, the present results suggest that AI models might have potential for estimating BCVA from OCT in AMD and RVO. Further research is needed to improve the utility of BCVA estimation for these diseases.

SUBMITTER: Inoda S

PROVIDER: S-EPMC10543844 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An AI model to estimate visual acuity based solely on cross-sectional OCT imaging of various diseases.

Inoda Satoru S Takahashi Hidenori H Arai Yusuke Y Tampo Hironobu H Matsui Yoshitsugu Y Kawashima Hidetoshi H Yanagi Yasuo Y

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie 20230511 10

<h4>Purpose</h4>To develop an artificial intelligence (AI) model for estimating best-corrected visual acuity (BCVA) using horizontal and vertical optical coherence tomography (OCT) scans of various retinal diseases and examine factors associated with its accuracy.<h4>Methods</h4>OCT images and associated BCVA measurements from 2,700 OCT images (accrued from 2004 to 2018 with an Atlantis, Triton; Topcon, Tokyo, Japan) of 756 eyes of 469 patients and their BCVA were retrospectively analysed. For e ...[more]

PMID: 37166519

Similar Datasets

Project description:Background/aimsTo investigate the association of macular optical coherence tomography (OCT)/OCT angiography (OCTA) parameters with visual acuity (VA) in glaucoma.Methods144 pseudophakic primary open-angle glaucoma eyes were included. Foveal (fVD), parafoveal (pf), perifoveal (perifVD) and whole-image vessel densities (wiVD) of superficial and deep layers, and their corresponding ganglion cell complex (GCC) thicknesses were obtained from OCTA 6×6 mm2 macula scans. Foveal avascular zone (FAZ) area, FAZ circumference and foveal density-300 (FD300) were measured. Correlation between OCT/OCTA parameters and Logarithm of the Minimum Angle of Resolution VA (logMAR VA) in early and moderate-advanced glaucoma was evaluated with age and Signal Strength Index-adjusted mixed models. Area under receiver operating characteristic (AUC) was used to evaluate discriminative power of OCT/OCTA for decreased VA (<20/25).ResultsIn early glaucoma (80 eyes), no parameter correlated with VA. In moderate-advanced glaucoma (64 eyes), greater FAZ area (β=0.228) and circumference (β=0.063) correlated with worse VA (p<0.05), but not FD300. fThinner sectoral and global GCC was associated with worse VA (β=0.002-0.003, p<0.05), except for inferior hemifield perifGCC and wiGCC. For VD, lower superior hemifield superficial perifVD and wiVD (β=0.007-0.008) and deep fVD (β=0.004) correlated with worse VA (p<0.05). OCT/OCTA parameters showed modest ability to discriminate decreased VA, with the superior hemifield performing better than the inferior hemifield. In early glaucoma, GCC and VD showed similar discrimination (AUC=0.67-0.77). In moderate-advanced glaucoma, fGCC and pfGCC yielded higher AUC (0.75-0.81) than VD (AUC=0.63-0.72).ConclusionsSome macular OCT/OCTA parameters were associated with VA in moderate-advanced, but not early glaucoma. These structural parameters may help identify glaucoma patients with impaired vision and reduced quality of life.Trial registration numberNCT00221897.

Project description:To predict visual acuity (VA) and post-therapeutic optical coherence tomography (OCT) images 1, 3, and 6 months after laser treatment in patients with central serous chorioretinopathy (CSC) by artificial intelligence (AI). Real-world clinical and imaging data were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The data obtained from ZOC (416 eyes of 401 patients) were used as the training set; the data obtained from XEC (64 eyes of 60 patients) were used as the test set. Six different machine learning algorithms and a blending algorithm were used to predict VA, and a pix2pixHD method was adopted to predict post-therapeutic OCT images in patients after laser treatment. The data for VA predictions included clinical features obtained from electronic medical records (20 features) and measured features obtained from fundus fluorescein angiography, indocyanine green angiography, and OCT (145 features). The data for OCT predictions included 480 pairs of pre- and post-therapeutic OCT images. The VA and OCT images predicted by AI were compared with the ground truth. In the VA predictions of XEC dataset, the mean absolute errors (MAEs) were 0.074-0.098 logMAR (within four to five letters), and the root mean square errors were 0.096-0.127 logMAR (within five to seven letters) for the 1-, 3-, and 6-month predictions, respectively; in the post-therapeutic OCT predictions, only about 5.15% (5 of 97) of synthetic OCT images could be accurately identified as synthetic images. The MAEs of central macular thickness of synthetic OCT images were 30.15 ± 13.28 μm and 22.46 ± 9.71 μm for the 1- and 3-month predictions, respectively. This is the first study to apply AI to predict VA and post-therapeutic OCT of patients with CSC. This work establishes a reliable method of predicting prognosis 6 months in advance; the application of AI has the potential to help reduce patient anxiety and serve as a reference for ophthalmologists when choosing optimal laser treatments.

Project description:PurposeTo assess clinical applicability of automatic image analysis in microbial keratitis (MK) by evaluating the relationship between biomarker measurements on slit-lamp photography (SLP) and best-corrected visual acuity (BCVA).MethodsSeventy-six patients with MK with SLP images and same-day logarithm of the minimum angle of resolution (logMAR) BCVA were evaluated. MK biomarkers (stromal infiltrate, white blood cell infiltration, corneal edema, hypopyon, epithelial defect) were segmented manually by ophthalmologists and automatically by a novel, open-source, deep learning-based segmentation algorithm. Five measurements (presence, maximum width, total area, proportion of the corneal limbus area affected, centrality) were calculated. Correlations between the measurements and BCVA were calculated. An automatic regression model estimated BCVA from the measurements. Differences in performance between using manual and automatic measurements were evaluated using William's test (for correlation) and the paired-sample t-test (for absolute error).ResultsMeasurements had high correlations of 0.86 (manual) and 0.84 (automatic) with true BCVA. Estimated BCVA had average (mean ± SD) absolute errors of 0.39 ± 0.27 logMAR (manual, median: 0.30) and 0.35 ± 0.28 logMAR (automatic, median: 0.30) and high correlations of 0.76 (manual) and 0.80 (automatic) with true BCVA. Differences between using manual and automatic measurements were not statistically significant for correlations of measurements with true BCVA (P = .66), absolute errors of estimated BCVA (P = .15), or correlations of estimated BCVA with true BCVA (P = .60).ConclusionsThe proposed algorithm measured MK biomarkers as accurately as ophthalmologists. Measurements were highly correlated with and estimative of visual acuity.Translational relevanceThis study demonstrates the potential of developing fully automatic objective and standardized strategies to aid ophthalmologists in the clinical assessment of MK.

Project description:PurposeTo explore the correlation between radiomics features extracted from OCT angiography (OCTA) of epiretinal membranes (ERMs) and baseline best-corrected visual acuity (BCVA).DesignRetrospective observational monocentric study.ParticipantsEighty-three eyes affected by idiopathic ERMs, categorized into low (≤70 letters) and high (70 letters) BCVA groups.MethodsThe central 3 × 3 mm2 crop of structural and vascular en-face OCTA scans of superficial and deep retina slab, and choriocapillaris of each eye was selected. PyRadiomics was used to extract 86 features belonging to 2 different families: intensity-based statistical features describing the gray-level distribution, and textural features capturing the spatial arrangement of pixels. By employing a greedy strategy, 4 radiomic features were selected to build the final logistic regression model. The ability of the model to discriminate between low and high baseline BCVA was quantified in terms of area under the receiver operating characteristics curve (AUC).Main outcome measuresThe 4 selected informative radiomic features were as follows: the difference average (glcm_DifferenceAverage), quantifying the average difference in gray-level between neighboring pixels; the informational measure of correlation (glcm_Imc1), giving information about the spatial correlation of pixel intensities inside the image; the long run low gray-level emphasis (glrlm_LongRunLowGrayLevelEmphasis), highlighting long segments of low gray-level values within the image; and the large area emphasis (glszm_LargeAreaEmphasis), which quantifies the tendency for larger zones of uniform intensity to occur.ResultsNo features exhibited a statistically significant difference between low and high BCVA values for the superficial and deep retinal slabs. Conversely, in the choriocapillaris layer, the glcm_DifferenceAverage and glcm_Imc1 features were significantly higher in the high BCVA group (P = 0.047), whereas higher values for the glrlm_LongRunLowGrayLevelEmphasis and glszm_LargeAreaEmphasis were associated with the low BCVA group (P = 0.047). Overall, these radiomic features predicted BCVA with an AUC (95% confidence interval) of 0.74 (0.63-0.85) and sensitivity/specificity of 0.67/0.75. During the cross-validation, the metrics remained stable.ConclusionsRadiomics features of the choriocapillaris in idiopathic ERMs showed a correlation with BCVA, with lower structural complexity and higher homogeneity, together with the presence of homogeneous areas with low-intensity pixel values, reflecting flow voids due to reduced microvascular perfusion, and were correlated with lower visual acuity.Financial disclosuresThe author(s) have no proprietary or commercial interest in any materials discussed in this article.

Project description:ObjectiveTo evaluate visual acuity (VA) and factors influencing VA using new multimodal imaging-based classification of central serous chorioretinopathy (CSCR).MethodsRetrospective, observational and cross-sectional study on 229 naïve eyes diagnosed as CSCR with available baseline data and multimodal imaging. Each case was classified into (i) simple/complex/atypical; (ii) primary/recurrent/resolved; (iii) persistent or not; (iv) outer retinal atrophy(ORA) present/absent; (v) foveal involvement present/absent; and (vi) macular neovascularization(MNV) present/absent. Best corrected visual acuity (BCVA) was correlated to the classification as well as every parameter of the classification.ResultsMedian BCVA was 0.18 logMAR [95% Confidence Interval (CI)0.16-0.18] with median duration of complaints of one month (95% CI,6.14-13.0 months). Age of the patient (r = -0.24, p = 0.002) and duration of the disease (r = -0.32, p < 0.001) correlated significantly with BCVA. Logistic regression model showed that older age [odds ratio (OR) = 0.96, p = 0.05], female gender (OR = 2.45, p = 0.046), presence of ORA(OR = 0.34, p = 0.012),and foveal involvement(OR = 0.18, p = 0.007) were statistically significantly associated with poorer BCVA. Eyes classified as complex, persistent CSCR, with ORA or foveal involvement demonstrated lower BCVA compared to those with simple, non-persistent CSCR, without ORA or without foveal involvement (p < 0.05). Eyes with complex CSCR (p < 0.001), atypical CSCR(p = 0.025), persistent subretinal fluid (SRF) (p = 0.001) and those with ORA (p < 0.001) demonstrated a trend towards severe visual loss. Prevalence of persistent SRF, recurrent episodes and ORA was significantly higher among eyes with complex CSCR (p < 0.001) while there was no difference in prevalence of resolved cases (p = 0.07), foveal involvement (p = 0.28) and MNV (p = 0.45) between simple and complex cases.ConclusionThere is a strong correlation between VA and foveal involvement and ORA using the new classification. Thus, the objective parameters of the classification can be incorporated in establishing the treatment guidelines for CSCR.

Dataset Information

An AI model to estimate visual acuity based solely on cross-sectional OCT imaging of various diseases.

Purpose

Methods

Results

Conclusion

Publications

An AI model to estimate visual acuity based solely on cross-sectional OCT imaging of various diseases.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets