Multi-Comparison of Different Ocular Imaging Modality-based Deep Learning Models for Visually Significant Cataract Detection.

With the rapidly aging population, the burden of visual impairment (VI) and cognitive decline is expected to increase. Previous cross-sectional studies suggest an association between these 2 health outcomes. However, few longitudinal reports have examined this association, and to our knowledge, no studies have been performed in Asian populations. Further investigation on this association may help to better identify individuals at risk of cognitive decline. To examine the longitudinal association between VI and decline in cognitive function in a multiethnic Asian population. In this longitudinal, population-based, prospective cohort study, Chinese, Indian, and Malay adults 60 years or older at baseline were recruited from the Singapore Epidemiology of Eye Diseases (SEED) study. At baseline, participants from the SEED study were recruited under 3 studies: the Singapore Malay Eye Study (SiMES; 2004-2006), the Singapore Indian Eye Study (SINDI; 2007-2009), and the Singapore Chinese Eye Study (SCES; 2009-2011). Eligible participants were reexamined after 6 years (2011-2013 for SiMES, 2013-2015 for SINDI, and 2015-2017 for SCES). Data analysis was performed from November 1 to 24, 2019. Visual impariment was defined as presenting visual acuity worse than 20/40 based on the better-seeing eye. Cognitive function was assessed using a locally validated Abbreviated Mental Test (AMT). The association between baseline VI and change in AMT score was determined using the multivariable linear regression model adjusting for baseline age; sex; race/ethnicity; presence of diabetes, hyperlipidemia, hypertension, and chronic kidney disease; history of cardiovascular disease; smoking status; alcohol intake; body mass index; educational status; and AMT score. A total of 2478 individuals (1256 [50.7%] male; 1073 Chinese, 768 Indian, and 637 Malay adults) with mean (SD) age of 67.6 (5.6) years were evaluated, of whom 489 (19.7%) had reduction in AMT scores over 6 years. Baseline VI was associated with a decrease in AMT score over 6 years (β = -0.27; 95% CI, -0.37 to -0.17; P < .001). When change in vision over 6 years was evaluated, unchanged or deteriorated VI was associated with a decrease in AMT score over 6 years (β = -0.29; 95% CI, -0.40 to -0.18; P < .001). Among individuals with baseline VI and a substantial decrease in AMT score of 3 units or more over 6 years, the leading causes of VI were undercorrected refractive error (14 [45.2%]) and cataract (11 [35.5%]). In this study, poor vision was independently associated with a decline in cognitive function. Causes of visual loss in these cases were mostly preventable, further suggesting that preserving good vision may be an important interventional strategy for mitigating cognitive decline.

Manejo anestésico en el paciente sometido a MEI en neurocirugía de extracción de tumor de columna

Diabetic retinopathy (DR) is a microvascular complication of diabetes with a prevalence of ~35%, and is one of the leading causes of visual impairment in people of working age in most developed countries. The earliest stage of DR, non-proliferative DR (NPDR), may progress to sight-threatening DR (STDR). Thus, early detection of DR and active regular screening of patients with diabetes are necessary for earlier intervention to prevent sight loss. While some countries offer systematic DR screening, most nations are reliant on opportunistic screening or do not offer any screening owing to limited healthcare resources and infrastructure. Currently, retinal imaging approaches for DR screening include those with and without mydriasis, imaging in single or multiple fields, and the use of conventional or ultra-wide-field imaging. Advances in telescreening and automated detection facilitate screening in previously hard-to-reach communities. Despite the heterogeneity in approaches to fit local needs, an evidence base must be created for each model to inform practice. In this review, we appraise different aspects of DR screening, including technological advances, identify evidence gaps, and propose several studies to improve DR screening globally, with a view to identifying patients with moderate-to-severe NPDR who would benefit if a convenient treatment option to delay progression to STDR became available.

The World Health Organization glioma classification highlights genetic profiles, such as isocitrate dehydrogenase (IDH) mutation. This study developed an uncertainty-aware deep learning model to predict IDH mutations in glioma patients, employing conformal prediction (CP) for uncertainty quantification (UQ). The UCSF dataset split into training (70%) and validation (30%) sets, and the UPENN dataset divided into calibration (30%) and external test (70%) sets. We developed various 3D convolutional neural network models and selected the best based on the validation set area under the precision-recall curve (AUPRC). Also, we trained a logistic regression (LR) ensemble classifier on the training set and selected the best ensemble model based on the validation set AUPRC. Finally, we employed CP, with nonconformity thresholds set at the error rate of 0.01. The conformal model was calibrated on the calibration set and was evaluated on the external test set using the AUPRC and the area under the receiver operating characteristic (AUROC). 3D convolutional models achieved a mean AUROC and AUPRC of 0.9004 and 0.8102 on the validation set, and a mean AUROC and AUPRC of 0.7340 and 0.2139 on the external test set, respectively. Using the LR ensemble model, the model achieved an AUROC and AUPRC of 0.79820 and 0.2583 on the external test set, respectively. CP with a 0.01 nonconformity threshold with 0.9917 coverage reached an AUROC and AUPRC of 0.8592 and 0.5217, respectively. Integrating CP for UQ improves the performance of deep learning models for predicting IDH mutation in glioma patients.

To assess prevalence of mild vision impairment (MVI; best corrected visual acuity (BCVA) < 6/12 to 6/18 in the better eye), moderate-to-severe vision impairment (MSVI; BCVA < 6/18 but ≥ 3/60) and blindness (BCVA < 3/60) in a local population in Russia, we conducted the population-based Ural Eye and Medical Study. Out of 7,328 eligible individuals aged 40 + years, 5,899 (80.5%) individuals participated. MVI was present in 184 (3.1%; 95% confidence interval (CI) 2.7, 3.6) individuals, MSVI in 182 (3.1%; 95% CI 2.7, 3.5) individuals, and 11 individuals (0.19%; 95% CI 0.008, 0.30) were blind. Causes for MSVI were cataract (n = 109; 59.9%), late stage of age-related macular degeneration (n = 14; 7.7%; geographic atrophy and neovascular AMD in 7 (3.8%) individuals) each), myopic maculopathy (n = 11; 6.0%), glaucoma (n = 9; 4.9%), non-glaucomatous optic nerve damage (n = 5; 2.7%), and diabetic retinopathy (n = 4; 2.2%). Causes for blindness were cataract (n = 3; 27.3%), myopic maculopathy (n = 2; 18.2%), retinal dystrophies (n = 2; 18.2%), glaucoma (n = 1; 9.1%), and corneal scars (n = 1; 9.1%). Higher prevalence of MSVI/blindness was associated with age (P < 0.001; odds ratio (OR)1.10; 95% CI 1.08, 1.12), male gender (P < 0.001; OR 2.32; 95% CI 1.47, 3.66), educational level (P < 0.001; OR 0.83; 95% CI 0.76,0.92), manual grip force (P < 0.001; OR 0.94; 95% CI 0.92, 0.96), diabetes prevalence (P = 0.006; OR 1.67; 95% CI 1.08, 2.56) and axial length (P < 0.001; OR 1.43; 95% CI 1.26,1.62). In this population from Bashkortostan/Russia, prevalence of MVI, MSVI and blindness was 3.1%, 3.1% and 0.19%, respectively. Cataract was the most frequent cause of reversible vision impairment, while AMD, myopic maculopathy and glaucoma were the most common reasons for irreversible vision impairment.

Radiologists often face challenges in differentiating benign from malignant sacral bone lesions due to their similar imaging characteristics. This study aimed to develop an ensemble deep learning (DL) model that can preoperatively distinguish between benign and malignant sacral tumors using noncontrast computed tomography images. Preoperative sacral CT scans from 569 patients with confirmed sacral lesions were analyzed. Data from Center 1 were utilized in model development and internal test via fivefold cross-validation, and those from Centers 2 and 3 were employed in external test. Various ensemble models combining human-readable interpretation and DL were developed. The diagnostic performance of the models and radiologists was assessed using metrics such as precision, recall, accuracy, area under the curve (AUC), F1 score, and confusion matrix. Furthermore, the clinical benefits derived from radiologists' interpretations and supported by the DL model were evaluated. The ensemble model, which integrates 3D-DenseNet121 with human interpretation, exhibited the most robust performance. The ensemble model demonstrated high performance on the internal and external test sets and achieved AUCs of 0.9139 and 0.8713, F1 scores of 0.9054 and 0.8571, precision of 0.9041 and 0.8824, recall of 0.9136 and 0.8333, and accuracy of 0.8630 and 0.8182, respectively. Across the external test cohort, all radiologists experienced improvements in AUC, accuracy, sensitivity, and specificity. Notably, junior radiologists demonstrated significant improvements compared with senior radiologists. The potential clinical application of the DL model lies in its capacity to considerably enhance the diagnostic efficiency of radiologists. This study presents the first ensemble deep learning model integrating 3D-DenseNet121 with radiologists' interpretation for preoperative differentiation of sacral tumors on noncontrast CT that improved diagnostic performance across all experience levels, particularly for junior radiologists. First artificial intelligence-radiologist ensemble for noncontrast computed tomography (NCCT)-based sacral tumor classification. Boosts all radiologists' performance, with the greatest gains for juniors, potentially reducing referrals. Enables reliable NCCT diagnosis, overcoming contrast/magnetic resonance imaging dependency in musculoskeletal oncology.

The Effect of Testing Reliability on Visual Field Sensitivity in Normal Eyes: The Singapore Chinese Eye Study

Deep Learning-based Quantification of Anterior Segment OCT Parameters

Determinants of Anterior Chamber Depth: The Singapore Chinese Eye Study

흡수, 분포, 대사, 배설 특성 및 독성을 예측하기 위한 효과적인 툴을 개발하는 것은 신약개발의 초기단계에서 NCE(new chemical entity)에 대한 가장 중요한 업무 중의 하나이다. 최근에 이런 시도중의 하나로서 ADME/T(absorption, distribution, metabolism, excretion, toxicity)관련 성질들의 예측에 support vector machine(SVM)을 이용하고 있다. 그리고 SVM은 ADME/T 성질들을 정확하게 예측하는데 많이 사용 되고 있다. 그러나 SVM 모델링에 두 가지 문제가 있다. 특성 선택(feature selection) 과 매개변수 설정(parameter setting)은 여전히 해결해야 할 과제이다. 이 두 가지 문제들은 SVM 분류의 효율성과 정확도에 결정적인 영향을 끼친다. 특히 특성 선택과 최적화된 SVM 변수의 설정은 서로 영향을 주기 때문에 동시에 다루어져야 한다. 여기서 우리는 genetic algorithm(GA) – 특성 선택에 사용 – 과 grid search(GS) method– 변수최적화에 사용 – 두 가지를 통합하는 효과적인 해결책을 제시하였다. ADME/T관련 성질 중 하나인 심장부정맥을 야기시키는 hERG 이온채널 저해제 분류 모델이 여기서 제안된 GA-GS-SVM을 위해 할당되고 테스트 되었다. 1891개의 화합물을 가지는 트레이닝 셋으로 단일 모델 3개, 앙상블 모델 3개, 총 6개의 모델을 만들었고 175개의 외부 데이터를 테스트 셋으로 사용하여 검증하였다. 데이터의 불균형 문제를 해결하기 위하여 GA-GS-SVM 단일 모델에 의한 예측 정확도와 GA-GS-SVM 앙상블 모델 예측 정확도를 비교하였으며, 앙상블모델을 사용하여 예측의 정확도를 높일 수 있었다. Developing effective tools for predicting absorption, distribution, metabolism, excretion properties and toxicity (ADME/T) of new chemical entities in the early stage of drug design is one of the most important tasks in drug discovery and development today. As one of these attempts, support vector machines (SVM) has recently been exploited for the prediction of ADME/T related properties. However, two problems in SVM modeling, i.e. feature selection and parameters setting, are still far from solved. The two problems have been shown to be crucial to the efficiency and accuracy of SVM classification. In particular, the feature selection and optimal SVM parameters setting influence each other, which indicates that they should be dealt with simultaneously. In this account, we present an integrated practical solution, in which genetic-based algorithm (GA) is used for feature selection and grid search (GS) method for parameters optimization. hERG ion-channel inhibitor classification models of ADME/T related properties has been built for assessing and testing the proposed GA-GS-SVM. We generated 6 different models that are 3 different single models and 3 different ensemble models using training set - 1891 compounds and validated with external test set - 175 compounds. We compared single model with ensemble model to solve data imbalance problems. It was able to improve accuracy of prediction to use ensemble model.

ObjectiveTo determine the prevalence of cataract surgery and factors associated with post-surgical visual outcomes in migrant Indians living in Singapore.Research Design and MethodsWe conducted a population-based study in 3,400 Indian immigrants residing in Singapore−the Singapore Indian Eye Study (SINDI). All participants underwent comprehensive medical eye examination and a standardized interview. Post-operative visual impairment (VI) was defined as best-corrected or presenting visual acuity (BCVA or PVA) of 20/60 or worse.ResultsThe age- and gender-standardized prevalence of cataract surgery was 9.7% (95% confidence interval [CI]: 8.9%, 10.7%) in Singapore resident Indians. Post-operative VI defined by BCVA occurred in 10.9% eyes (87/795). The main causes of post-operative VI were diabetic retinopathy (20.7%), posterior capsular opacification (18.4%), and age-related macular degeneration (12.6%). Undercorrected refractive error doubled the prevalence of post-operative VI when PVA was used.ConclusionsThe rate of cataract surgery is about 10% in Indian residents in Singapore. Socioeconomic variables and migration had no significant impact on the prevalence of cataract surgery. Diabetic retinopathy was a major cause of post-operative VI in migrant Indians living in Singapore. Uncorrected postoperative refractive error remains an efficient way to improve vision.

Age-related cataract (ARC) is one of the leading causes of visual impairment and blindness worldwide among the elderly. Here, we used sodium selenite-induced cataract mouse model, which shares with similarities with human senile cataract to investigate whether the extracts of Phellinus linteus (PLE) could have the potential protective effects of ARC or not. The mice pups were randomly divided into 4 treatment groups (n = 7): (1) normal saline on postpartum day 26; (2) Na selenite injected s.c on day 26; (3) Na selenite s.c on day 26+ gavaged PLE (40 mg/kg) on days 26–47; and (4) Na selenite s.c on day 26 + resveratrol on days 26–47. On day 47, encapsulated lenses and plasma were analyzed for the levels of glutathione (GSH), superoxide dismutase (SOD), and malondialdehyde (MDA), a marker of lipid peroxidation. Lens epithelial cells (LECs) were also analyzed for the mRNA and protein expressions of glutathione S-transferase Mu (GSTM3). We demonstrated that PLE could prevent selenite-induced oxidative stress and cataract formation in mice by higher GSH and SOD and lower MDA in LECs, plasma, and liver tissues and the increases in the mRNA and protein expressions of GSTM3 in LECs. Our data show the increasing oxidative stress in selenite-induced cataract mice. Our data reveal the benefits of PLE for preventive activity in selenite-induced cataract in mice and there is a good possibility that PLE could ameliorate human senile cataract.

Myopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings. To evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists. The Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024. DL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation. MM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE). The 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P < .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P < .001). In this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

To describe the causes of 5-year incident visual impairment and doubling of the visual angle in a population-based cohort. Of the 3654 participants aged older than 50 years who participated in the Blue Mountains Eye Study (BMES I, 1992-1994), 543 died and 2335 were reexamined between 1997 and 1999 (BMES II). Visual acuity was measured using a logMAR chart before and after refraction. Pupils were dilated, and a detailed eye examination was performed. For participants with incident visual impairment or doubling of the visual angle, an ophthalmologist attributed and proportioned causes. Primary causes were defined as those responsible for 50% or more of the impairment. After refractive correction, the proportion of incident bilateral impairment worse than 20/40, worse than 20/70, and worse than 20/200 that were caused primarily by cataract decreased from 51.4% (n = 19) to 40.0% (n = 6) to 0%; while the proportion of cases caused primarily by age-related maculopathy increased from 24.3% (n = 9) to 33.3% (n = 5) to 100.0% (n = 2). Similarly, the corresponding proportions of incident unilateral impairment caused primarily by cataract decreased from 53.7% (n = 72) to 36.9% (n = 31) to 13.6% (n = 6); meanwhile, the proportion of cases caused primarily by age-related maculopathy increased from 19.4% (n = 26) to 32.1% (n = 27) to 54.5% (n = 24). The proportions of persons with incident bilateral impairment worse than 20/40, worse than 20/70, and worse than 20/200 that could be improved with refraction were 79.4% (n = 143), 73.6% (n = 42), and 0%, respectively. The corresponding proportions of incident unilateral impairment improved by refraction were 66.7% (n = 269), 59.0% (n = 121), and 21.4% (n = 12). This study has documented the 5-year incidence and causes of visual impairment in an older Australian population.

To investigate the prevalence and causes of visual impairment in elderly Amis aborigines in Eastern Taiwan. Population-based cross-sectional study of visual impairment of elderly Amis (65 years of age or older). We conducted ocular examinations on 2,316 participants, which represent 61.2 % of the elderly population. We used WHO criteria to identify visual impaired subjects, and the causes were analyzed. Ninety-four subjects were identified with low vision and nineteen were blind. The prevalence of low vision was 4.06 % (95 % confidence interval, 3.26, 4.56 %); that of blindness was 0.82 % (95 % confidence interval, 0.45, 1.19 %). Cataracts (47.79 %) were the main cause of visual impairment, followed by age-related macular degeneration (15.93 %), corneal opacity (7.96 %), optic neuropathy (7.96 %), diabetic retinopathy (5.31 %), and retinitis pigmentosa (2.65 %). Glaucoma was a minor cause of visual impairment. There were no significant gender differences in the prevalence and specific causes of visual impairment. The prevalence of treatable causes of vision impairment, for example cataracts and corneal opacity, is high among the elderly Amis aborigines. They would, therefore, benefit from a more aggressive and in-depth eye-care program as a blindness-prevention strategy.