Effective encoder-decoder network for pupil light reflex segmentation in facial photographs of ptosis patients.

Accurate segmentation of pupil light reflexes is essential for the reliable assessment of ptosis severity, a condition characterized by the drooping of the upper eyelid. This study introduces a novel encoder-decoder network specialized in reflex segmentation by focusing on addressing issues related to very small regions of interest from an architectural perspective. Specifically, the proposed network is designed to exploit low-level features effectively by integrating a multi-level skip connection and a 1 × 1 convolution-enhanced initial encoding stage. Assessed using a photograph image dataset from Chung-Ang University Hospital, which includes 87 healthy subjects, 64 with ptosis, and 257 with Graves' orbitopathy (collected between January 2010 and February 2023), the proposed network outperforms five conventional encoder-decoders. Over 30 trials, the proposed network achieved a mean Dice coefficient of 0.767 and an Intersection over Union of 0.653, indicating a statistically significant improvement in the segmentation of reflex. Our findings show that an elaborate design based on the lowest-level skip connection and 1 × 1 convolution at initial stage enhances the segmentation of pupil light reflexes. The source code of the proposed network is available at https://github.com/tkdgur658/ReflexNet .

Agreement between a new fully automatic ocular biometer based on optical low-coherence reflectometry and an optical biometer based on Scheimpflug imaging combined with partial coherence interferometry.

BACKGROUND: To analyze the difference and agreement between measurements obtained by a new fully automatic optical biometer, the SW-9000 µm Plus, based on optical low-coherence reflectometry (OLCR) and a commonly used optical biometer (Pentacam AXL) based on Scheimpflug imaging with partial coherence interferometry (PCI). METHODS: The central corneal thickness (CCT), anterior chamber depth (ACD, from epithelium to anterior lens surface), lens thickness (LT), mean keratometry (Km), corneal astigmatism, corneal diameter (CD), pupil diameter (PD), and axial length (AL) of 74 eyes (from 74 healthy subjects) were measured using the SW-9000 µm Plus and the Pentacam AXL to determine the agreement. Double angle plots were used for astigmatism vector analysis. Bland-Altman and 95% limits of agreement (LoA) were calculated. RESULTS: Statistically significant differences were detected for all parameters but J0 vector. The Bland-Altman analysis of AL, CCT, ACD, Km, CD, J0 and J45 indicated a high level of agreement between the two devices. Among AL, CCT, ACD, Km, J0, J45, CD, and PD, the 95% LoA ranged from -0.07 to 0.05 mm, -9.67 to 7.34 mm, -0.11 to 0.04 mm, -0.25 to 0.50 D, -0.22 to 0.20 D, -0.15 to 0.20 D, -0.23 to 0.35 mm and 1.55 to 3.77 mm, respectively. CONCLUSIONS: The measurements of AL, CCT, ACD, Km, corneal astigmatism, and CD showed a narrow LoA and may be used interchangeably in healthy subjects between the new OLCR optical biometer and the Scheimpflug/PCI biometer; however, a poor agreement was noted for PD values.

Photoanthropometric study: are non-professional photographs suitable for objective and reliable analysis of facial features?

BACKGROUND: The face has been widely investigated using professionally taken frontal and lateral photographs, however, there is a lack of studies of non-professional facial photographs. It is not known if they could be suitable for facial analysis. The analysis of non-professional photographs could allow the performance of cost- effective longitudinal studies. AIM: To determine if non-professional photographs could be used for a reliable analysis of facial features. SUBJECTS AND METHODS: The frontal profiles of 18-21-year-olds (35 males, 39 females) were measured by direct anthropometry, in addition, professional photographs were taken and non-professional photographs were obtained. Anthropometric landmarks were superimposed on those photographs. The indices calculated on the basis of the measurements of direct anthropometry and both types of photographs were compared. RESULTS: The comparison of the measurements of direct anthropometry and professional photographs showed no difference between 14 out of 25 male and 10 out of 25 female facial indices (p > 0.05) after comparing the results of direct anthropometry with those of non-professional photographs, no difference was found in 8 out of 25 male and 7 out of 25 female indices. These indices were mostly composed of vertical parameters and eye measurements. CONCLUSION: Vertical facial dimensions and eye measurements may not only be used interchangeably for both facial photographs and direct anthropometry, but may also be suitable for objective and reliable facial analyses.

Repeatability and agreement of two swept-source optical coherence tomographers and scheimpflug imaging for measurements of corneal curvature.

PURPOSE: To evaluate the repeatability and agreement of two swept-source optical coherence tomographers and Scheimpflug imaging for corneal curvature in healthy subjects to obtain data on the clinical application of a new device. METHODS: This prospective study was conducted in January and February 2021 with 100 healthy subjects at the Eye Hospital of Wenzhou Medical University. Simulated keratometry (Sim-K), posterior keratometry (Kp), total corneal power (TCP), and total corneal astigmatism (TCA) were measured with CASIA2, Anterion, and Pentacam. Within-subject standard deviation (Sw), repeatability coefficient (RC), coefficient of variation (CoV), and intraclass correlation coefficient (ICC) were used to assess inter-device repeatability. Bland-Altman analysis was performed to determine inter-device agreement. RESULTS: The three devices showed good repeatability for Sim-K, Kp, and TCP with all ICC > 0.980. Pentacam showed the highest repeatability (ICC ≥ 0.993; ICC ≥ 0.993) while the CASIA2 demonstrated the lowest repeatability (ICC: ≥ 0.986; ICC: ≥ 0.985) for Sim-K and TCP. Anterion and CASIA2 revealed better repeatability (ICC ≥ 0.998; ICC ≥ 0.981) for Kp than Pentacam (ICC ≥ 0.980). Pentacam and Anterion showed good repeatability for TCA (ICC: 0.935 and 0.916), whereas the CASIA2 showed moderate repeatability (ICC: 0.836). Three instruments demonstrated good agreement with the maximum absolute 95% Limits of agreement (LoA) of 1.00 D for Sim-K, Kp, and TCP. Wide LoA were found for TCA with the maximum absolute 95% LoA ≥ 0.66 D between the three devices. CONCLUSIONS: In healthy subjects, the three devices (Pentacam, Anterion and CASIA2) displayed comparable repeatability and accuracy for SimK, Kp, and TCP, and could be used interchangeably for these parameters. However, TCA measured by the three devices was not interchangeable. TRIAL REGISTRATION: Chinese Clinical Trial Registry Center (10/10/2020, ChiCTR2000038959).

Repeatability of Scheimpflug-Placido camera in mild dry eye versus normal eyes according to the topographical position of the cornea.

We aimed to investigate the repeatability of various corneal measurements according to topographical location in the entire cornea measured by dual rotating Scheimpflug-Placido camera and to explore the differences in repeatability between patients with mild dry eye and those with normal eyes. In both the normal and dry eye groups, divided based on BUT or the height of the tear film, there were no statistically significant differences in the ratio of unacceptable variation (RUV) and ICC. The consistency of the examination of the anterior and posterior refractive values and corneal thickness according to the corneal location, measured three times repeatedly using the Galilei anterior segment camera, was high. There was no difference based on the height of the tear film or the tear film break-up time. However, caution is needed when interpreting the values of the anterior corneal refractive values, as there can be changes of more than 0.5D within 3 mm of the central area.

Oral screening of dental calculus, gingivitis and dental caries through segmentation on intraoral photographic images using deep learning.

OBJECTIVE: Intraoral photographic images are instrumental in the early screening and clinical diagnosis of oral diseases. In addition, people have been trying to apply artificial intelligence to these images. The purpose of this study is to investigate and evaluate a deep learning system designed to segment intraoral photographic images for the detection of dental caries, dental calculus, and gingivitis, and to assess the degree of dental calculus based on the overall features of the tooth surface and gingival margin. MATERIAL AND METHODS: This cross-sectional study collected 3,365 oral endoscopic images, randomly distributed in training datasets (2,019 images), validation dataset (673 images), and test dataset (673 images). The training set and verification set images are manually labeled. An oral endoscopic image segmentation method based on Mamba (Oral-Mamba) and an intelligent evaluation model of dental calculus degree were proposed, achieving the segmentation of two types of oral diseases, namely gingivitis and dental caries, as well as the segmentation of dental calculus regions, and the intelligent evaluation of the degree of dental calculus. RESULTS: Oral-Mamba demonstrated high accuracy in segmentation, with accuracy rates for gingivitis, dental caries, and dental calculus at 0.83, 0.83, and 0.81, respectively. In particular, these rates surpassed those of the U-Net model in IoU, accuracy, and recall metrics. Furthermore, Oral-Mamba runs 25% faster than U-Net.The accuracy of degree classification in the intelligent evaluation model of dental calculus degree is 85%. CONCLUSION: The proposed deep learning system is expected to be used for the detection of two types of oral diseases and dental calculus, and the degree judgment of photographic images from an intraoral camera. This system offers a practical method to assist in the oral screening of dental caries, dental calculus, and gingivitis, providing benefits such as intuitive use, time efficiency, cost-effectiveness, and ease of deployment.

Penguin colony georegistration using camera pose estimation and phototourism.

Satellite-based remote sensing and uncrewed aerial imagery play increasingly important roles in the mapping of wildlife populations and wildlife habitat, but the availability of imagery has been limited in remote areas. At the same time, ecotourism is a rapidly growing industry and can yield a vast catalog of photographs that could be harnessed for monitoring purposes, but the inherently ad-hoc and unstructured nature of these images make them difficult to use. To help address this, a subfield of computer vision known as phototourism has been developed to leverage a diverse collection of unstructured photographs to reconstruct a georeferenced three-dimensional scene capturing the environment at that location. Here we demonstrate the use of phototourism in an application involving Antarctic penguins, sentinel species whose dynamics are closely tracked as a measure of ecosystem functioning, and introduce a semi-automated pipeline for aligning and registering ground photographs using a digital elevation model (DEM) and satellite imagery. We employ the Segment Anything Model (SAM) for the interactive identification and segmentation of penguin colonies in these photographs. By creating a textured 3D mesh from the DEM and satellite imagery, we estimate camera poses to align ground photographs with the mesh and register the segmented penguin colony area to the mesh, achieving a detailed representation of the colony. Our approach has demonstrated promising performance, though challenges persist due to variations in image quality and the dynamic nature of natural landscapes. Nevertheless, our method offers a straightforward and effective tool for the georegistration of ad-hoc photographs in natural landscapes, with additional applications such as monitoring glacial retreat.

"They Need to Feel Non-Judgmental": Results of Participatory Photovoice Research to Inform Lung Cancer Screening Imagery.

INTRODUCTION: Effective communication and messaging strategies are crucial to raise awareness and support participants' efforts to adhere to lung cancer screening (LCS) guidelines. Health messages that incorporate images are processed more efficiently, and given the stigma surrounding lung cancer and cigarette smoking, emphasis must be placed on selecting imagery that is engaging to LCS-eligible individuals. This exploratory study aimed to identify person-centered themes surrounding LCS imagery. MATERIALS AND METHODS: This qualitative study leveraged a modified photovoice approach and interviews to define descriptive themes about LCS imagery. Study participants eligible for annual LCS who had a CT scan within 12 months were asked to select three images and participate in a semi-structured interview about photo selection, likes, and dislikes. Participants were also asked their opinions about images from current LCS communications featuring matches, smoke, and cigarettes. Data were analyzed using an inductive thematic approach. RESULTS: Data saturation was reached after thirteen individuals completed the photovoice activity; each participant selected three pictures resulting in a total of 39 images representing LCS. Over half (54%) of images selected contained lungs and only 4 (10%) contained smoking-related elements. Five main themes emerged: 1) images should focus on good news and early detection; 2) people should be relatable; 3) pictures with lungs can dually support lung health or invoke fear; 4) opportunity for education or awareness; and 5) should not be judgmental and induce stigma. CONCLUSIONS: These findings suggest that LCS imagery should not contain negative or stigmatizing elements but instead be relatable and educational. This information can inform communication and messaging interventions and strategies for future LCS participation, awareness, and educational research.

Visualizing Plant Responses: Novel Insights Possible Through Affordable Imaging Techniques in the Greenhouse.

Efficient and affordable plant phenotyping methods are an essential response to global climatic pressures. This study demonstrates the continued potential of consumer-grade photography to capture plant phenotypic traits in turfgrass and derive new calculations. Yet the effects of image corrections on individual calculations are often unreported. Turfgrass lysimeters were photographed over 8 weeks using a custom lightbox and consumer-grade camera. Subsequent imagery was analyzed for area of cover, color metrics, and sensitivity to image corrections. Findings were compared to active spectral reflectance data and previously reported measurements of visual quality, productivity, and water use. Results confirm that Red-Green-Blue imagery effectively measures plant treatment effects. Notable correlations were observed for corrected imagery, including between yellow fractional area with human visual quality ratings (r = -0.89), dark green color index with clipping productivity (r = 0.61), and an index combination term with water use (r = -0.60). The calculation of green fractional area correlated with Normalized Difference Vegetation Index (r = 0.91), and its RED reflectance spectra (r = -0.87). A new chromatic ratio correlated with Normalized Difference Red-Edge index (r = 0.90) and its Red-Edge reflectance spectra (r = -0.74), while a new calculation correlated strongest to Near-Infrared (r = 0.90). Additionally, the combined index term significantly differentiated between the treatment effects of date, mowing height, deficit irrigation, and their interactions (p < 0.001). Sensitivity and statistical analyses of typical image file formats and corrections that included JPEG, TIFF, geometric lens distortion correction, and color correction were conducted. Findings highlight the need for more standardization in image corrections and to determine the biological relevance of the new image data calculations.

Clinical Utility of Deep Learning Assistance for Detecting Various Abnormal Findings in Color Retinal Fundus Images: A Reader Study.

Purpose: To evaluate the clinical usefulness of a deep learning-based detection device for multiple abnormal findings on retinal fundus photographs for readers with varying expertise. Methods: Fourteen ophthalmologists (six residents, eight specialists) assessed 399 fundus images with respect to 12 major ophthalmologic findings, with or without the assistance of a deep learning algorithm, in two separate reading sessions. Sensitivity, specificity, and reading time per image were compared. Results: With algorithmic assistance, readers significantly improved in sensitivity for all 12 findings (P < 0.05) but tended to be less specific (P < 0.05) for hemorrhage, drusen, membrane, and vascular abnormality, more profoundly so in residents. Sensitivity without algorithmic assistance was significantly lower in residents (23.1%∼75.8%) compared to specialists (55.1%∼97.1%) in nine findings, but it improved to similar levels with algorithmic assistance (67.8%∼99.4% in residents, 83.2%∼99.5% in specialists) with only hemorrhage remaining statistically significantly lower. Variances in sensitivity were significantly reduced for all findings. Reading time per image decreased in images with fewer than three findings per image, more profoundly in residents. When simulated based on images acquired from a health screening center, average reading time was estimated to be reduced by 25.9% (from 16.4 seconds to 12.1 seconds per image) for residents, and by 2.0% (from 9.6 seconds to 9.4 seconds) for specialists. Conclusions: Deep learning-based computer-assisted detection devices increase sensitivity, reduce inter-reader variance in sensitivity, and reduce reading time in less complicated images. Translational Relevance: This study evaluated the influence that algorithmic assistance in detecting abnormal findings on retinal fundus photographs has on clinicians, possibly predicting its influence on clinical application.

Corneal densitometry measurements comparison between anterior segment OCT and scheimpflug imaging.

PURPOSE: To evaluate and compare the repeatability of corneal densitometry (CD) measurements obtained using both an anterior-segment optical coherence tomography (AS-OCT) device and a Scheimpflug camera system, while also assessing the level of agreement. The study also sought to investigate the correlation of CD with age, gender, and central corneal thickness (CCT) in normal eyes. METHODS: CD measurements were obtained using the Casia 2 and the Pentacam AXL Wave. Data were collected on Total Corneal Densitometry and 4 concentric corneal annular areas, these are referred to as zone 1, denoting the central area, through to zone 4, designating the outermost peripheral region. Repeatability was assessed using intra-session test-retest variability, coefficient of variation (CoV), and intraclass correlation coefficient (ICC). The agreement was evaluated using Bland-Altman plots. Correlation analysis was performed between CD, age, gender, and CCT. RESULTS: The study included 96 healthy volunteers. The Casia 2 demonstrated high repeatability with ICC values exceeding 0.9 in all the corneal zones and lower CoV values compared to the Pentacam AXL Wave (ranging from 1.07% to 2.25% for Casia 2 and from 1.91% to 6.89% for Pentacam).95% LoA were within ± 2 standard deviation from the average mean except from zone 1 (± 2.42).However, the measurements showed a consistent bias among all the corneal zones. CD values were positively correlated with age, except for zone 1 with the Pentacam (p = 0.083). CONCLUSIONS: The findings suggest that the Casia 2 can be a reliable tool for assessing corneal transparency in healthy individuals, however its measurements are not interchangeable with those provided by the Pentacam. The AS-OCT device may be more sensitive in detecting subtle age-related changes in CD within the central zone.

Comparison of deep learning models to detect crossbites on 2D intraoral photographs.

BACKGROUND: To support dentists with limited experience, this study trained and compared six convolutional neural networks to detect crossbites and classify non-crossbite, frontal, and lateral crossbites using 2D intraoral photographs. METHODS: Based on 676 photographs from 311 orthodontic patients, six convolutional neural network models were trained and compared to classify (1) non-crossbite vs. crossbite and (2) non-crossbite vs. lateral crossbite vs. frontal crossbite. The trained models comprised DenseNet, EfficientNet, MobileNet, ResNet18, ResNet50, and Xception. FINDINGS: Among the models, Xception showed the highest accuracy (98.57%) in the test dataset for classifying non-crossbite vs. crossbite images. When additionally distinguishing between lateral and frontal crossbites, average accuracy decreased with the DenseNet architecture achieving the highest accuracy among the models with 91.43% in the test dataset. CONCLUSIONS: Convolutional neural networks show high potential in processing clinical photographs and detecting crossbites. This study provides initial insights into how deep learning models can be used for orthodontic diagnosis of malocclusions based on intraoral 2D photographs.

ETDRS grading with CLARUS ultra-widefield images shows agreement with 7-fields colour fundus photography.

BACKGROUND: To analyse and compare the grading of diabetic retinopathy (DR) severity level using standard 35° ETDRS 7-fields photography and CLARUS™ 500 ultra-widefield imaging system. METHODS: A cross-sectional analysis of retinal images of patients with type 2 diabetes (n = 160 eyes) was performed for this study. All patients underwent 7-fields colour fundus photography (CFP) at 35° on a standard Topcon TRC-50DX® camera, and ultra-widefield (UWF) imaging at 200° on a CLARUS™ 500 (ZEISS, Dublin, CA, USA) by an automatic montage of two 133° images (nasal and temporal). 35° 7-fields photographs were graded by two graders, according to the Early Treatment Diabetic Retinopathy Study (ETDRS). For CLARUS UWF images, a prototype 7-fields grid was applied using the CLARUS review software, and the same ETDRS grading procedures were performed inside that area only. Grading of DR severity level was compared between these two methods to evaluate the agreement between both imaging techniques. RESULTS: Images of 160 eyes from 83 diabetic patients were considered for analysis. According to the 35° ETDRS 7-fields images, 22 eyes were evaluated as DR severity level 10-20, 64 eyes were evaluated as DR level 35, 41 eyes level 43, 21 eyes level 47, 7 eyes level 53, and 5 eyes level 61. The same DR severity level was achieved with CLARUS 500 UWF images in 92 eyes (57%), showing a perfect agreement (k > 0.80) with the 7-fields 35° technique. Fifty-seven eyes (36%) showed a higher DR level with CLARUS UWF images, mostly due to a better visualization of haemorrhages and a higher detection rate of intraretinal microvascular abnormalities (IRMA). Only 11 eyes (7%) showed a lower severity level with the CLARUS UWF system, due to the presence of artifacts or media opacities that precluded the correct evaluation of DR lesions. CONCLUSIONS: UWF CLARUS 500 device showed nearly perfect agreement with standard 35° 7-fields images in all ETDRS severity levels. Moreover, CLARUS images showed an increased ability to detect haemorrhages and IRMA helping with finer evaluation of lesions, thus demonstrating that a UWF photograph can be used to grade ETDRS severity level with a better visualization than the standard 7-fields images. TRIAL REGISTRATION: Approved by the AIBILI - Association for Innovation and Biomedical Research on Light and Image Ethics Committee for Health with number CEC/009/17- EYEMARKER.

Error assessment of subjective estimates of linear breast dimensions versus the objective method.

Objective: The study aimed to investigate the subjective method of estimating linear breast dimensions in comparison to the objective method. Methods: The reproducibility and accuracy of the subjective method of estimating linear breast dimensions during a simplified breast shape analysis were examined. Four linear breast dimensions including the distance from the sternal notch to the nipple, distance from the nipple to the inframammary fold, distance from the nipple to the midline and under-breast width were evaluated based on subjective estimates. Images from 100 women with natural breasts and without any history of breast surgery were reviewed by two examiners three times each. The cases were obtained from a large database of breast images captured using the Vectra Camera System (Canfield Scientific Inc., USA). The subjective data were then compared with the objective linear data from the Vectra Camera System in the automated analysis. Statistical evaluation was conducted between the three repeated estimates of each examiner, between the two examiners and between the objective and subjective data. Results: The intra-individual variations of the three subjective estimates were significantly greater in one examiner than in the other. This trend was consistent across all eight parameters in the majority of the comparisons of the standard deviations and variation coefficients, and the differences were significant in 14 out of 16 comparisons (p<0.05). Conversely, in the comparison between the subjective and objective data, the estimates were closer to the measurements in one examiner than the other. In contrast to the reproducibility observed, the assessment of the accuracy revealed that the examiner who previously presented with less reproducibility of the estimated data overall showed better accuracy in comparison to the objective data. The overall differences were inconsistent, with some being positive and others being negative. Regarding the distances from the sternal notch to the nipple and breast width, both examiners underestimated the values. However, the deviations were at different levels, particularly when considering the objective data from the Vectra Camera System as the gold standard data for comparison. Regarding the distance from the nipple to the inframammary fold, one examiner underestimated the distance, while the other overestimated it. An opposite trend was noted for the distance from the nipple to the midline. There were no differences in the estimates between the right and left sides of the breasts. The correlations between the measured and estimated distances were positive: as the objective distances increased, the subjective distances also increased. In all cases, the correlations were significant. However, the correlation for the breast width was notably weaker than that for the other distances. Conclusions: The error assessment of the subjective method reveals that it varies significantly and unsystematically between examiners. This is true when assessing the reproducibility as well as the accuracy of the method in comparison to the objective data obtained with an automated system.

Promoting smartphone-based keratitis screening using meta-learning: A multicenter study.

OBJECTIVE: Keratitis is the primary cause of corneal blindness worldwide. Prompt identification and referral of patients with keratitis are fundamental measures to improve patient prognosis. Although deep learning can assist ophthalmologists in automatically detecting keratitis through a slit lamp camera, remote and underserved areas often lack this professional equipment. Smartphones, a widely available device, have recently been found to have potential in keratitis screening. However, given the limited data available from smartphones, employing traditional deep learning algorithms to construct a robust intelligent system presents a significant challenge. This study aimed to propose a meta-learning framework, cosine nearest centroid-based metric learning (CNCML), for developing a smartphone-based keratitis screening model in the case of insufficient smartphone data by leveraging the prior knowledge acquired from slit-lamp photographs. METHODS: We developed and assessed CNCML based on 13,009 slit-lamp photographs and 4,075 smartphone photographs that were obtained from 3 independent clinical centers. To mimic real-world scenarios with various degrees of sample scarcity, we used training sets of different sizes (0 to 20 photographs per class) from the HUAWEI smartphone to train CNCML. We evaluated the performance of CNCML not only on an internal test dataset but also on two external datasets that were collected by two different brands of smartphones (VIVO and XIAOMI) in another clinical center. Furthermore, we compared the performance of CNCML with that of traditional deep learning models on these smartphone datasets. The accuracy and macro-average area under the curve (macro-AUC) were utilized to evaluate the performance of models. RESULTS: With merely 15 smartphone photographs per class used for training, CNCML reached accuracies of 84.59%, 83.15%, and 89.99% on three smartphone datasets, with corresponding macro-AUCs of 0.96, 0.95, and 0.98, respectively. The accuracies of CNCML on these datasets were 0.56% to 9.65% higher than those of the most competitive traditional deep learning models. CONCLUSIONS: CNCML exhibited fast learning capabilities, attaining remarkable performance with a small number of training samples. This approach presents a potential solution for transitioning intelligent keratitis detection from professional devices (e.g., slit-lamp cameras) to more ubiquitous devices (e.g., smartphones), making keratitis screening more convenient and effective.

About Research - Qualitative Data Collection: Photo Elicitation.

Photo elicitation is a qualitative data collection technique in which the researcher includes photographs or other visual images as part of participant interviews. The researcher might provide the photographs or might ask the participants to bring photographs to the interview. This technique enhances the breadth and depth of verbal qualitative interviews. The use of photo elicitation can enhance the rigor of a qualitative study. There are both advantages and disadvantages of this data collection technique. Ethical issues warrant special consideration.

Evaluation of AI-enhanced non-mydriatic fundus photography for diabetic retinopathy screening.

OBJECTIVE: To assess the feasibility of using non-mydriatic fundus photography in conjunction with an artificial intelligence (AI) reading platform for large-scale screening of diabetic retinopathy (DR). METHODS: In this study, we selected 120 patients with diabetes hospitalized in our institution from December 2019 to April 2021. Retinal imaging of 240 eyes was obtained using non-mydriatic fundus photography. The fundus images of these patients were divided into two groups based on different interpretation methods. In Experiment Group 1, the images were analyzed and graded for DR diagnosis using an AI reading platform. In Experiment Group 2, the images were analyzed and graded for DR diagnosis by an associate chief physician in ophthalmology, specializing in fundus diseases. Concurrently, all patients underwent the gold standard for DR diagnosis and grading-fundus fluorescein angiography (FFA)-with the outcomes serving as the Control Group. The diagnostic value of the two methods was assessed by comparing the results of Experiment Groups 1 and 2 with those of the Control Group. RESULTS: Keeping the control group (FFA results) as the gold standard, no significant differences were observed between the two experimental groups regarding diagnostic sensitivity, specificity, false positive rate, false negative rate, positive predictive value, negative predictive value, Youden's index, Kappa value, and diagnostic accuracy (X2 = 0.371, P > 0.05). CONCLUSION: Compared with the manual reading group, the AI reading group revealed no significant differences across all diagnostic indicators, exhibiting high sensitivity and specificity, as well as a relatively high positive predictive value. Additionally, it demonstrated a high level of diagnostic consistency with the gold standard. This technology holds potential for suitability in large-scale screening of DR.

A parafoveal retinal cones analysis using adaptive-optics retinal camera in patients with primary open angle glaucoma.

OBJECTIVES: To study the density, spacing, and regularity of retinal cone photoreceptors using an Adaptive Optics (AO) retinal camera (Rtx1TM, Imagine Eyes, Orsay, France) in patients with Primary Open Angle Glaucoma (POAG) and to compare the outcomes with those of healthy age-matched control subjects. METHODS: The study included 43 eyes with POAG and 31 eyes of normal subjects. POAG patients were divided into three groups according to the severity of the visual field defect. The AO Rtx1TM was used to obtain images of the parafoveal cone mosaic to calculate cone values. Analysis was performed at two and four degrees of eccentricity from the fovea along the four meridians (nasal, temporal, superior, inferior). RESULTS: In POAG eyes, the mean ± standard deviation (SD) cone density at 2° considering all meridians was significantly lower than in normal controls (23,058.6 ± 3532.0 cones/mm2, and 25,511.7 ± 3157.5 cones/mm2, respectively; p = 0.003). Cone spacing was 7.3 ± 0.5 µm in POAG and 7.0 ± 0.4 µm in normal controls (p = 0.005), and cone regularity was 90.5 ± 4.9% and 93.5 ± 1.9% in POAG and normal controls, respectively (p < 0.001). At 4° similar trends were observed. However, no significant differences were found among patients with different severity of POAG (p > 0.05). CONCLUSIONS: Using AO Rtx1TM, significant differences in retinal photoreceptors mosaic pattern were found between POAG eyes and age-matched controls, indicating a reduction in photoreceptors in POAG. No significant differences in retinal photoreceptor values were found among the three POAG groups.

[Prevalence of diabetic retinopathy assessed using two-field mydriatic fundus photography]. / Otsenka rasprostranennosti diabeticheskoi retinopatii s pomoshch'yu dvukhpol'nogo midriaticheskogo fundus-fotografirovaniya.

Early detection of diabetic retinopathy (DR) is an urgent ophthalmological problem in Russia and globally. PURPOSE: This study assesses the prevalence of asymptomatic retinopathy and attempts to identify risk groups for its development in patients with type 1 and 2 diabetes mellitus (T1DM and T2DM). MATERIAL AND METHODS: The study involved clinics from 5 cities in the Russian Federation and it included 367 patients with DM, 34.88% men and 65.12% women, aged 50.88±20.55 years. 34.88% of patients suffered from T1DM, 65.12% suffered from T2DM, the average duration of the disease was 9.02±7.22 years. 58.31% of patients had a history of arterial hypertension, 13.08% had a history of smoking. The primary endpoint was the frequency of detection of diabetic changes in the eye fundus of patients with T1DM and T2DM in general; the secondary endpoint - same but separately, and for T2DM patients depending on the duration of the disease. The exploratory endpoint was the assessment of the influence of various factors on the development of DR. The patients underwent visometry (modified ETDRS table), biomicroscopy, mydriatic fundus photography according to the «2 fields¼ protocol. RESULTS: The average detection rate of DR was 12.26%, primarily observed in patients with T2DM (13.81%), women (9.26%), in both eyes (8.17%). Among patients with DR, 26 (19.55%) had glycated hemoglobin (HbA1c) level exceeding 7.5% (p=0.002), indicating a direct relationship between this indicator and the incidence of DR. Logistic regression analysis showed that the duration of diabetes of more than 10 years has a statistically significant effect on the development of DR. In the modified model for odds estimation, the likelihood of developing DR is increased by the duration of DM for more than 10 years; increased blood pressure; HbA1c level >7.5%. CONCLUSION: The obtained results, some of which will be presented in subsequent publications, highlight the effectiveness of using two-field mydriatic fundus photography as a screening for DR.

Concurrent Validity of Motion Parameters Measured With an RGB-D Camera-Based Markerless 3D Motion Tracking Method in Children and Young Adults.

OBJECTIVE: Low-cost, portable RGB-D cameras with integrated motion tracking functionality enable easy-to-use 3D motion analysis without requiring expensive facilities and specialized personnel. However, the accuracy of existing systems is insufficient for most clinical applications, particularly when applied to children. In previous work, we developed an RGB-D camera-based motion tracking method and showed that it accurately captures body joint positions of children and young adults in 3D. In this study, the validity and accuracy of clinically relevant motion parameters that were computed from kinematics of our motion tracking method are evaluated in children and young adults. METHODS: Twenty-three typically developing children and healthy young adults (5-29 years, 110-189 cm) performed five movement tasks while being recorded simultaneously with a marker-based Vicon system and an Azure Kinect RGB-D camera. Motion parameters were computed from the extracted kinematics of both methods: time series measurements, i.e., measurements over time, peak measurements, i.e., measurements at a single time instant, and movement smoothness. The agreement of these parameter values was evaluated using Pearson's correlation coefficients r for time series data, and mean absolute error (MAE) and Bland-Altman plots with limits of agreement for peak measurements and smoothness. RESULTS: Time series measurements showed strong to excellent correlations (r-values between 0.8 and 1.0), MAE for angles ranged from 1.5 to 5 degrees and for smoothness parameters (SPARC) from 0.02-0.09, while MAE for distance-related parameters ranged from 9 to 15 mm. CONCLUSION: Extracted motion parameters are valid and accurate for various movement tasks in children and young adults, demonstrating the suitability of our tracking method for clinical motion analysis. CLINICAL IMPACT: The low-cost portable hardware in combination with our tracking method enables motion analysis outside of specialized facilities while providing measurements that are close to those of the clinical gold-standard.