An innovative strategy for standardized, structured, and interoperable results in ophthalmic examinations.

BACKGROUND: Although ophthalmic devices have made remarkable progress and are widely used, most lack standardization of both image review and results reporting systems, making interoperability unachievable. We developed and validated new software for extracting, transforming, and storing information from report images produced by ophthalmic examination devices to generate standardized, structured, and interoperable information to assist ophthalmologists in eye clinics. RESULTS: We selected report images derived from optical coherence tomography (OCT). The new software consists of three parts: (1) The Area Explorer, which determines whether the designated area in the configuration file contains numeric values or tomographic images; (2) The Value Reader, which converts images to text according to ophthalmic measurements; and (3) The Finding Classifier, which classifies pathologic findings from tomographic images included in the report. After assessment of Value Reader accuracy by human experts, all report images were converted and stored in a database. We applied the Value Reader, which achieved 99.67% accuracy, to a total of 433,175 OCT report images acquired in a single tertiary hospital from 07/04/2006 to 08/31/2019. The Finding Classifier provided pathologic findings (e.g., macular edema and subretinal fluid) and disease activity. Patient longitudinal data could be easily reviewed to document changes in measurements over time. The final results were loaded into a common data model (CDM), and the cropped tomographic images were loaded into the Picture Archive Communication System. CONCLUSIONS: The newly developed software extracts valuable information from OCT images and may be extended to other types of report image files produced by medical devices. Furthermore, powerful databases such as the CDM may be implemented or augmented by adding the information captured through our program.

Effects of Hypertension, Diabetes, and Smoking on Age and Sex Prediction from Retinal Fundus Images.

Retinal fundus images are used to detect organ damage from vascular diseases (e.g. diabetes mellitus and hypertension) and screen ocular diseases. We aimed to assess convolutional neural network (CNN) models that predict age and sex from retinal fundus images in normal participants and in participants with underlying systemic vascular-altered status. In addition, we also tried to investigate clues regarding differences between normal ageing and vascular pathologic changes using the CNN models. In this study, we developed CNN age and sex prediction models using 219,302 fundus images from normal participants without hypertension, diabetes mellitus (DM), and any smoking history. The trained models were assessed in four test-sets with 24,366 images from normal participants, 40,659 images from hypertension participants, 14,189 images from DM participants, and 113,510 images from smokers. The CNN model accurately predicted age in normal participants; the correlation between predicted age and chronologic age was R2 = 0.92, and the mean absolute error (MAE) was 3.06 years. MAEs in test-sets with hypertension (3.46 years), DM (3.55 years), and smoking (2.65 years) were similar to that of normal participants; however, R2 values were relatively low (hypertension, R2 = 0.74; DM, R2 = 0.75; smoking, R2 = 0.86). In subgroups with participants over 60 years, the MAEs increased to above 4.0 years and the accuracies declined for all test-sets. Fundus-predicted sex demonstrated acceptable accuracy (area under curve > 0.96) in all test-sets. Retinal fundus images from participants with underlying vascular-altered conditions (hypertension, DM, or smoking) indicated similar MAEs and low coefficients of determination (R2) between the predicted age and chronologic age, thus suggesting that the ageing process and pathologic vascular changes exhibit different features. Our models demonstrate the most improved performance yet and provided clues to the relationship and difference between ageing and pathologic changes from underlying systemic vascular conditions. In the process of fundus change, systemic vascular diseases are thought to have a different effect from ageing. Research in context. Evidence before this study. The human retina and optic disc continuously change with ageing, and they share physiologic or pathologic characteristics with brain and systemic vascular status. As retinal fundus images provide high-resolution in-vivo images of retinal vessels and parenchyma without any invasive procedure, it has been used to screen ocular diseases and has attracted significant attention as a predictive biomarker for cerebral and systemic vascular diseases. Recently, deep neural networks have revolutionised the field of medical image analysis including retinal fundus images and shown reliable results in predicting age, sex, and presence of cardiovascular diseases. Added value of this study. This is the first study demonstrating how a convolutional neural network (CNN) trained using retinal fundus images from normal participants measures the age of participants with underlying vascular conditions such as hypertension, diabetes mellitus (DM), or history of smoking using a large database, SBRIA, which contains 412,026 retinal fundus images from 155,449 participants. Our results indicated that the model accurately predicted age in normal participants, while correlations (coefficient of determination, R2) in test-sets with hypertension, DM, and smoking were relatively low. Additionally, a subgroup analysis indicated that mean absolute errors (MAEs) increased and accuracies declined significantly in subgroups with participants over 60 years of age in both normal participants and participants with vascular-altered conditions. These results suggest that pathologic retinal vascular changes occurring in systemic vascular diseases are different form the changes in spontaneous ageing process, and the ageing process observed in retinal fundus images may saturate at age about 60 years. Implications of all available evidence. Based on this study and previous reports, the CNN could accurately and reliably predict age and sex using retinal fundus images. The fact that retinal changes caused by ageing and systemic vascular diseases occur differently motivates one to understand the retina deeper. Deep learning-based fundus image reading may be a more useful and beneficial tool for screening and diagnosing systemic and ocular diseases after further development.

A semi-automated volumetric software for segmentation and perfusion parameter quantification of brain tumors using 320-row multidetector computed tomography: a validation study.

PURPOSE: We developed a semi-automated volumetric software, NPerfusion, to segment brain tumors and quantify perfusion parameters on whole-brain CT perfusion (WBCTP) images. The purpose of this study was to assess the feasibility of the software and to validate its performance compared with manual segmentation. METHODS: Twenty-nine patients with pathologically proven brain tumors who underwent preoperative WBCTP between August 2012 and February 2015 were included. Three perfusion parameters, arterial flow (AF), equivalent blood volume (EBV), and Patlak flow (PF, which is a measure of permeability of capillaries), of brain tumors were generated by a commercial software and then quantified volumetrically by NPerfusion, which also semi-automatically segmented tumor boundaries. The quantification was validated by comparison with that of manual segmentation in terms of the concordance correlation coefficient and Bland-Altman analysis. RESULTS: With NPerfusion, we successfully performed segmentation and quantified whole volumetric perfusion parameters of all 29 brain tumors that showed consistent perfusion trends with previous studies. The validation of the perfusion parameter quantification exhibited almost perfect agreement with manual segmentation, with Lin concordance correlation coefficients (ρ c) for AF, EBV, and PF of 0.9988, 0.9994, and 0.9976, respectively. On Bland-Altman analysis, most differences between this software and manual segmentation on the commercial software were within the limit of agreement. CONCLUSIONS: NPerfusion successfully performs segmentation of brain tumors and calculates perfusion parameters of brain tumors. We validated this semi-automated segmentation software by comparing it with manual segmentation. NPerfusion can be used to calculate volumetric perfusion parameters of brain tumors from WBCTP.

Quantitative GFP fluorescence as an indicator of arsenite developmental toxicity in mosaic heat shock protein 70 transgenic zebrafish.

In transgenic zebrafish (Danio rerio), green fluorescent protein (GFP) is a promising marker for environmental pollutants. In using GFP, one of the obstacles which we faced was how to compare toxicity among different toxicants or among a specific toxicant in different model species with the intensity of GFP expression. Using a fluorescence detection method, we first validated our method for estimating the amount of GFP fluorescence present in transgenic fish, which we used as an indicator of developmental toxicity caused by the well-known toxicant, arsenite. To this end, we developed mosaic transgenic zebrafish with the human heat shock response element (HSE) fused to the enhanced GFP (EGFP) reporter gene to indicate exposure to arsenite. We confirmed that EGFP expression sites correlate with gross morphological disruption caused by arsenite exposure. Arsenite (300.0 microM) caused stronger EGFP fluorescence intensity and quantity than 50.0 microM and 10.0 microM arsenite in our transgenic zebrafish. Furthermore, arsenite-induced apoptosis was demonstrated by TUNEL assay. Apoptosis was inhibited by the antioxidant, N-acetyl-cystein (NAC) in this transgenic zebrafish. The distribution of TUNEL-positive cells in embryonic tissues was correlated with the sites of arsenite toxicity and EGFP expression. The EGFP values quantified using the standard curve equation from the known GFP quantity were consistent with the arsenite-induced EGFP expression pattern and arsenite concentration, indicating that this technique can be a reliable and applicable measurement. In conclusion, we propose that fluorescence-based EGFP quantification in transgenic fish containing the hsp70 promoter-EGFP reporter-gene construct is a useful indicator of development toxicity caused by arsenite.

Arsenite-induced apoptosis is prevented by antioxidants in zebrafish liver cell line.

This study evaluated oxidative stress-induced apoptosis as a possible mechanism of arsenite toxicity in zebrafish liver cell line (ZFL cells). The heat shock protein 70 (HSP70), a chaperone protein, appears to provide protection against oxidative stress and apoptosis. Using the MTT assay, we demonstrated that survival of ZFL cells treated with arsenite for 24h decreased in a dose-dependent manner. The possible mechanisms that promote the cytotoxicity of arsenite were addressed. Cell viability assays revealed that arsenite caused a dose-dependent increase in cell death, and pretreatment of the ZFL cells with antioxidants blunted these effects. Antioxidants such as N-acetyl-cysteine (NAC, 5 mM) and dithiothreitol (DTT, 80 microM) significantly prevented ZFL cells from arsenite-induced death. Nuclear staining was performed using 1 microg/ml Hoechst, and cells were analyzed with a fluorescent microscope. Arsenite (30 microM) induced massive apoptosis that was identified by morphology and condensation and fragmentation of the nuclei of the ZFL cells. Pretreatment with NAC or DTT before arsenite insult effectively protected the cells against oxidative stress-induced apoptosis from the arsenite. Using a transfected human hsp 70 promoter-enhanced green fluorescent protein (EGFP) reporter, pHhsp70-EGFP, the induction of HSP70 against oxidative stress-induced apoptosis by arsenite was observed. The induction of HSP70 by arsenite increased in a dose-dependent manner, and pretreatment of transfected ZFL cells with NAC or DTT before arsenite insult reduced EGFP expression. Taken together, our results provide evidence that stimulation of the heat shock response is a sensitive biomarker of arsenic exposure and that arsenite causes oxidative stress-induced apoptosis in ZFL cells.