AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field f...AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field fundus images. METHODS: This study included 237 images from 236 patients with BRVO with a mean±standard deviation of age 66.3±10.6 y and 229 images from 176 non-BRVO healthy subjects with a mean age of 64.9±9.4 y. Training was conducted using a deep convolutional neural network using ultrawide-field fundus images to construct the DL model. The sensitivity, specificity, positive predictive value(PPV), negative predictive value(NPV) and area under the curve(AUC) were calculated to compare the diagnostic abilities of the DL and SVM models. RESULTS: For the DL model, the sensitivity, specificity, PPV, NPV and AUC for diagnosing BRVO was 94.0%(95%CI: 93.8%-98.8%), 97.0%(95%CI: 89.7%-96.4%), 96.5%(95%CI: 94.3%-98.7%), 93.2%(95%CI: 90.5%-96.0%) and 0.976(95%CI: 0.960-0.993), respectively. In contrast, for the SVM model, these values were 80.5%(95%CI: 77.8%-87.9%), 84.3%(95%CI: 75.8%-86.1%), 83.5%(95%CI: 78.4%-88.6%), 75.2%(95%CI: 72.1%-78.3%) and 0.857(95%CI: 0.811-0.903), respectively. The DL model outperformed the SVM model in all the aforementioned parameters(P<0.001). CONCLUSION: These results indicate that the combination of the DL model and ultrawide-field fundus ophthalmoscopy may distinguish between healthy and BRVO eyes with a high level of accuracy. The proposed combination may be used for automatically diagnosing BRVO in patients residing in remote areas lacking access to an ophthalmic medical center.展开更多
AIM： To investigate the changes in the choroidal thickness in healthy pediatric children in a longitudinal study, and to determine the ocular and systemic parameters that were significantly correlated with the change...AIM： To investigate the changes in the choroidal thickness in healthy pediatric children in a longitudinal study, and to determine the ocular and systemic parameters that were significantly correlated with the changes in the choroidal thickness. METHODS： This study included 64 eyes of 34 healthy Japanese children with a mean age（±SD） of 4.4（±0.4）y（range, 3.6-5.8 y） at baseline. Swept-source optical coherence tomography（SS-OCT） was used to record images of the retina and choroid at the baseline and after a mean followup period of about 1.5 y. The 3 D raster scan protocol was used to construct the choroidal thickness map. Mean choroidal thickness was calculated for each of the nine sectors of the Early Treatment Diabetic Retinopathy Study grid. Best-corrected visual acuity, axial length, body height, and weight were also measured. Changes in measurements were defined as the baseline values subtracted from the values at the final visit. A generalized estimating equation was used to eliminate the effect of within-subject intereye correlations. RESULTS： The mean central choroidal thickness was significantly reduced during the follow-up period（baseline, 301.8±8.6 μm; final visit, 286.6±8.0 μm, P〈0.001）. The decrease in the choroidal thickness was greatest in the central sector, followed by the sectors of the inner and outer rings. The inner and outer rings had diameters of 1 to 3 mm and 3 to 6 mm, respectively. The changes in the choroidal thickness in the central, inner ring, and outer ring sectors were significantly and negatively correlated with the age, baseline body height, baseline body weight, and elongation of the axial length. CONCLUSION： These results indicate that the choroidal thickness among preschool-aged Japanese children decreased significantly during the follow-up period. The choroidal thinning is significantly associated with the elongation of axial length. These characteristics should be considered in the evaluation of choroidal thickness in younger children with retinochoroidal disorders.展开更多
Background:To examine the effectiveness of the use of machine learning for adapting an intraocular lens(IOL)power calculation for a patient group.Methods:In this retrospective study,the clinical records of 1,611 eyes ...Background:To examine the effectiveness of the use of machine learning for adapting an intraocular lens(IOL)power calculation for a patient group.Methods:In this retrospective study,the clinical records of 1,611 eyes of 1,169 Japanese patients who received a single model of monofocal IOL(SN60WF,Alcon)at Miyata Eye Hospital were reviewed and analyzed.Using biometric metrics and postoperative refractions of 1211 eyes of 769 patients,constants of the SRK/T and Haigis formulas were optimized.The SRK/T formula was adapted using a support vector regressor.Prediction errors in the use of adapted formulas as well as the SRK/T,Haigis,Hill-RBF and Barrett Universal II formulas were evaluated with data from 395 eyes of 395 distinct patients.Mean prediction errors,median absolute errors,and percentages of eyes within±0.25 D,±0.50 D,and±1.00 D,and over+0.50 D of errors were compared among formulas.Results:The mean prediction errors in the use of the SRT/K and adapted formulas were smaller than the use of other formulas(P<0.001).In the absolute errors,the Hill-RBF and adapted methods were better than others.The performance of the Barrett Universal II was not better than the others for the patient group.There were the least eyes with hyperopic refractive errors(16.5%)in the use of the adapted formula.Conclusions:Adapting IOL power calculations using machine learning technology with data from a particular patient group was effective and promising.展开更多
Background:To examine the effectiveness of the use of machine learning for adapting an intraocular lens(IOL)power calculation for a patient group.Methods:In this retrospective study,the clinical records of 1,611 eyes ...Background:To examine the effectiveness of the use of machine learning for adapting an intraocular lens(IOL)power calculation for a patient group.Methods:In this retrospective study,the clinical records of 1,611 eyes of 1,169 Japanese patients who received a single model of monofocal IOL(SN60WF,Alcon)at Miyata Eye Hospital were reviewed and analyzed.Using biometric metrics and postoperative refractions of 1211 eyes of 769 patients,constants of the SRK/T and Haigis formulas were optimized.The SRK/T formula was adapted using a support vector regressor.Prediction errors in the use of adapted formulas as well as the SRK/T,Haigis,Hill-RBF and Barrett Universal II formulas were evaluated with data from 395 eyes of 395 distinct patients.Mean prediction errors,median absolute errors,and percentages of eyes within±0.25 D,±0.50 D,and±1.00 D,and over+0.50 D of errors were compared among formulas.Results:The mean prediction errors in the use of the SRT/K and adapted formulas were smaller than the use of other formulas(P<0.001).In the absolute errors,the Hill-RBF and adapted methods were better than others.The performance of the Barrett Universal II was not better than the others for the patient group.There were the least eyes with hyperopic refractive errors(16.5%)in the use of the adapted formula.Conclusions:Adapting IOL power calculations using machine learning technology with data from a particular patient group was effective and promising.展开更多
文摘AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field fundus images. METHODS: This study included 237 images from 236 patients with BRVO with a mean±standard deviation of age 66.3±10.6 y and 229 images from 176 non-BRVO healthy subjects with a mean age of 64.9±9.4 y. Training was conducted using a deep convolutional neural network using ultrawide-field fundus images to construct the DL model. The sensitivity, specificity, positive predictive value(PPV), negative predictive value(NPV) and area under the curve(AUC) were calculated to compare the diagnostic abilities of the DL and SVM models. RESULTS: For the DL model, the sensitivity, specificity, PPV, NPV and AUC for diagnosing BRVO was 94.0%(95%CI: 93.8%-98.8%), 97.0%(95%CI: 89.7%-96.4%), 96.5%(95%CI: 94.3%-98.7%), 93.2%(95%CI: 90.5%-96.0%) and 0.976(95%CI: 0.960-0.993), respectively. In contrast, for the SVM model, these values were 80.5%(95%CI: 77.8%-87.9%), 84.3%(95%CI: 75.8%-86.1%), 83.5%(95%CI: 78.4%-88.6%), 75.2%(95%CI: 72.1%-78.3%) and 0.857(95%CI: 0.811-0.903), respectively. The DL model outperformed the SVM model in all the aforementioned parameters(P<0.001). CONCLUSION: These results indicate that the combination of the DL model and ultrawide-field fundus ophthalmoscopy may distinguish between healthy and BRVO eyes with a high level of accuracy. The proposed combination may be used for automatically diagnosing BRVO in patients residing in remote areas lacking access to an ophthalmic medical center.
文摘AIM： To investigate the changes in the choroidal thickness in healthy pediatric children in a longitudinal study, and to determine the ocular and systemic parameters that were significantly correlated with the changes in the choroidal thickness. METHODS： This study included 64 eyes of 34 healthy Japanese children with a mean age（±SD） of 4.4（±0.4）y（range, 3.6-5.8 y） at baseline. Swept-source optical coherence tomography（SS-OCT） was used to record images of the retina and choroid at the baseline and after a mean followup period of about 1.5 y. The 3 D raster scan protocol was used to construct the choroidal thickness map. Mean choroidal thickness was calculated for each of the nine sectors of the Early Treatment Diabetic Retinopathy Study grid. Best-corrected visual acuity, axial length, body height, and weight were also measured. Changes in measurements were defined as the baseline values subtracted from the values at the final visit. A generalized estimating equation was used to eliminate the effect of within-subject intereye correlations. RESULTS： The mean central choroidal thickness was significantly reduced during the follow-up period（baseline, 301.8±8.6 μm; final visit, 286.6±8.0 μm, P〈0.001）. The decrease in the choroidal thickness was greatest in the central sector, followed by the sectors of the inner and outer rings. The inner and outer rings had diameters of 1 to 3 mm and 3 to 6 mm, respectively. The changes in the choroidal thickness in the central, inner ring, and outer ring sectors were significantly and negatively correlated with the age, baseline body height, baseline body weight, and elongation of the axial length. CONCLUSION： These results indicate that the choroidal thickness among preschool-aged Japanese children decreased significantly during the follow-up period. The choroidal thinning is significantly associated with the elongation of axial length. These characteristics should be considered in the evaluation of choroidal thickness in younger children with retinochoroidal disorders.
文摘Background:To examine the effectiveness of the use of machine learning for adapting an intraocular lens(IOL)power calculation for a patient group.Methods:In this retrospective study,the clinical records of 1,611 eyes of 1,169 Japanese patients who received a single model of monofocal IOL(SN60WF,Alcon)at Miyata Eye Hospital were reviewed and analyzed.Using biometric metrics and postoperative refractions of 1211 eyes of 769 patients,constants of the SRK/T and Haigis formulas were optimized.The SRK/T formula was adapted using a support vector regressor.Prediction errors in the use of adapted formulas as well as the SRK/T,Haigis,Hill-RBF and Barrett Universal II formulas were evaluated with data from 395 eyes of 395 distinct patients.Mean prediction errors,median absolute errors,and percentages of eyes within±0.25 D,±0.50 D,and±1.00 D,and over+0.50 D of errors were compared among formulas.Results:The mean prediction errors in the use of the SRT/K and adapted formulas were smaller than the use of other formulas(P<0.001).In the absolute errors,the Hill-RBF and adapted methods were better than others.The performance of the Barrett Universal II was not better than the others for the patient group.There were the least eyes with hyperopic refractive errors(16.5%)in the use of the adapted formula.Conclusions:Adapting IOL power calculations using machine learning technology with data from a particular patient group was effective and promising.
文摘Background:To examine the effectiveness of the use of machine learning for adapting an intraocular lens(IOL)power calculation for a patient group.Methods:In this retrospective study,the clinical records of 1,611 eyes of 1,169 Japanese patients who received a single model of monofocal IOL(SN60WF,Alcon)at Miyata Eye Hospital were reviewed and analyzed.Using biometric metrics and postoperative refractions of 1211 eyes of 769 patients,constants of the SRK/T and Haigis formulas were optimized.The SRK/T formula was adapted using a support vector regressor.Prediction errors in the use of adapted formulas as well as the SRK/T,Haigis,Hill-RBF and Barrett Universal II formulas were evaluated with data from 395 eyes of 395 distinct patients.Mean prediction errors,median absolute errors,and percentages of eyes within±0.25 D,±0.50 D,and±1.00 D,and over+0.50 D of errors were compared among formulas.Results:The mean prediction errors in the use of the SRT/K and adapted formulas were smaller than the use of other formulas(P<0.001).In the absolute errors,the Hill-RBF and adapted methods were better than others.The performance of the Barrett Universal II was not better than the others for the patient group.There were the least eyes with hyperopic refractive errors(16.5%)in the use of the adapted formula.Conclusions:Adapting IOL power calculations using machine learning technology with data from a particular patient group was effective and promising.
