RESUMO
BACKGROUND: Diabetic retinopathy (DR) is a leading cause of blindness. Our objective was to evaluate the performance of an artificial intelligence (AI) system integrated into a handheld smartphone-based retinal camera for DR screening using a single retinal image per eye. METHODS: Images were obtained from individuals with diabetes during a mass screening program for DR in Blumenau, Southern Brazil, conducted by trained operators. Automatic analysis was conducted using an AI system (EyerMaps™, Phelcom Technologies LLC, Boston, USA) with one macula-centered, 45-degree field of view retinal image per eye. The results were compared to the assessment by a retinal specialist, considered as the ground truth, using two images per eye. Patients with ungradable images were excluded from the analysis. RESULTS: A total of 686 individuals (average age 59.2 ± 13.3 years, 56.7% women, diabetes duration 12.1 ± 9.4 years) were included in the analysis. The rates of insulin use, daily glycemic monitoring, and systemic hypertension treatment were 68.4%, 70.2%, and 70.2%, respectively. Although 97.3% of patients were aware of the risk of blindness associated with diabetes, more than half of them underwent their first retinal examination during the event. The majority (82.5%) relied exclusively on the public health system. Approximately 43.4% of individuals were either illiterate or had not completed elementary school. DR classification based on the ground truth was as follows: absent or nonproliferative mild DR 86.9%, more than mild (mtm) DR 13.1%. The AI system achieved sensitivity, specificity, positive predictive value, and negative predictive value percentages (95% CI) for mtmDR as follows: 93.6% (87.8-97.2), 71.7% (67.8-75.4), 42.7% (39.3-46.2), and 98.0% (96.2-98.9), respectively. The area under the ROC curve was 86.4%. CONCLUSION: The portable retinal camera combined with AI demonstrated high sensitivity for DR screening using only one image per eye, offering a simpler protocol compared to the traditional approach of two images per eye. Simplifying the DR screening process could enhance adherence rates and overall program coverage.
RESUMO
BACKGROUND: Portable retinal cameras and deep learning (DL) algorithms are novel tools adopted by diabetic retinopathy (DR) screening programs. Our objective is to evaluate the diagnostic accuracy of a DL algorithm and the performance of portable handheld retinal cameras in the detection of DR in a large and heterogenous type 2 diabetes population in a real-world, high burden setting. METHOD: Participants underwent fundus photographs of both eyes with a portable retinal camera (Phelcom Eyer). Classification of DR was performed by human reading and a DL algorithm (PhelcomNet), consisting of a convolutional neural network trained on a dataset of fundus images captured exclusively with the portable device; both methods were compared. We calculated the area under the curve (AUC), sensitivity, and specificity for more than mild DR. RESULTS: A total of 824 individuals with type 2 diabetes were enrolled at Itabuna Diabetes Campaign, a subset of 679 (82.4%) of whom could be fully assessed. The algorithm sensitivity/specificity was 97.8 % (95% CI 96.7-98.9)/61.4 % (95% CI 57.7-65.1); AUC was 0·89. All false negative cases were classified as moderate non-proliferative diabetic retinopathy (NPDR) by human grading. CONCLUSIONS: The DL algorithm reached a good diagnostic accuracy for more than mild DR in a real-world, high burden setting. The performance of the handheld portable retinal camera was adequate, with over 80% of individuals presenting with images of sufficient quality. Portable devices and artificial intelligence tools may increase coverage of DR screening programs.
Assuntos
Diabetes Mellitus Tipo 2 , Retinopatia Diabética , Inteligência Artificial , Diabetes Mellitus Tipo 2/complicações , Retinopatia Diabética/diagnóstico por imagem , Humanos , Programas de Rastreamento/métodos , Fotografação , SmartphoneRESUMO
ABSTRACT Purpose: To compare the quality of retinal images captured with a smartphone-based, handheld fundus camera with that of retinal images captured with a commercial fundus camera and to analyze their agreement in determining the cup-to-disc ratio for a cohort of ophthalmological patients. Methods: A total of 50 patients from a secondary ophthalmic outpatient service center underwent a bilateral fundus examination under mydriasis with a smartphone-based, handheld fundus camera and with a commercial fundus camera (4 images/patient by each). Two experienced ophthalmologists evaluated all the fundus images and graded them on the Likert 1-5 scale for quality. Multivariate regression analyses was then performed to evaluate the factors associated with the image quality. Two masked ophthalmologists determined the vertical cup-to-disc ratio of each fundus image, and both the intraobserver (between devices) and interobserver agreement between them was calculated. Results: Ninety-eight images from 49 patients were processed in this study for their quality analysis. Ten images from five patients (four from commercial fundus camera and one from smartphone-based, handheld fundus camera) were not included in the analyses due to their extremely poor quality. The medians [interquartile interval] of the image quality were not significantly different between those from the smartphone-based, handheld fundus camera and from the commercial fundus camera (4 [4-5] versus 4 [3-4] respectively, p=0.06); however, both the images captured with the commercial fundus camera and the presence of media opacity presented a significant negative correlation with the image quality. Both the intraobserver [intraclass correlation coefficient (ICC)=0.82, p<0.001 and 0.83, p<0.001, for examiners 1 and 2, respectively] and interobserver (ICC=0.70, p=0.001 and 0.81; p<0.001, for smartphone-based handheld fundus camera and commercial fundus camera, respectively) agreements were excellent and statistically significant. Conclusions: Our results thus indicate that the smartphone-based, handheld fundus camera yields an image quality similar to that from a commercial fundus camera, with significant agreement in the cup-to-disc ratios between them. In addition to the good outcomes recorded, the smartphone-based, handheld fundus camera offers the advantages of portability and low-cost to serve as an alternative for fundus documentation for future telemedicine approaches in medical interventions.
RESUMO Objetivo: Comparar a qualidade das imagens da retina capturadas com um retinógrafo portátil acoplado a um smartphone com aquelas adquiridas com um retinógrafo comercial padrão e analisar a concordância na determinação da relação escavação/ cabeça do nervo óptico em um coorte de pacientes de um serviço oftalmológico. Métodos: Cinquenta pacientes de um serviço oftalmológico secundário foram submetidos a uma avaliação do fundo de olho bilateral, sob midríase, utilizando o retinógrafo portátil acoplado a um smartphone e o retinógrafo comercial padrão (4 imagens por paciente). Dois oftalmologistas experientes avaliaram a qualidade de todas as imagens e atribuíram a elas uma pontuação entre 1 e 5, de acordo com a escala Likert. Os fatores relacionados a qualidade das imagens foram avaliados utilizando uma análise de regressão multivariada. Dois oftalmologistas determinaram de forma mascarada a relação da escavação/ cabeça do nervo óptico de cada imagem e a concordância intra e interobservador foi calculada. Resultados: Noventa e oito imagens de 49 pacientes foram utilizadas neste estudo para análise de qualidade. Dez imagens de cinco pacientes (quatro do retinógrafo comercial padrão e um do retinógrafo portátil acoplado a um smartphone) foram excluídas das análises de concordância devido à baixa qualidade das mesmas, mas foram considerados nas análises de qualidade. Dos cinco pacientes com imagens excluídas, quatro foram capturadas pelo retinógrafo comercial padrão e uma pelo retinógrafo portátil acoplado a um smartphone. As medianas (intervalo interquartil) da qualidade das imagens não apresentaram diferença estatística entre o retinógrafo portátil acoplado a um smartphone e o retinógrafo comercial padrão (4 [4-5] versus 4 [3-4] respectivamente, p=0.06). As imagens obtidas com o retinógrafo comercial padrão e o diagnóstico de opacidade de meios apresentou uma correlação negativa com a qualidade da imagem. As concordâncias intraobservador (ICC=0,82, p<0,001 e 0,83, p<0,001, para o examinador 1 e 2, respectivamente) e interobservador (ICC = 0,70, p=0,001 e 0,81, p<0.001, para o retinógrafo portátil acoplado a um smartphone e retinógrafo comercial padrão, respectivamente) foram excelentes e estatisticamente significativas. Conclusões: Nossos resultados sugerem que o retinógrafo portátil acoplado a um smartphone apresenta uma qualidade de imagem semelhante ao retinógrafo comercial padrão, com concordância significativa na análise da relação escavação-cabeça do nervo óptico. Além dos bons resultados apresentados, o retinógrafo portátil acoplado a um smartphone pode ser considerado uma alternativa portátil de baixo custo para documentação de retina em cenários futuros de telemedicina.
RESUMO
PURPOSE: To compare the quality of retinal images captured with a smartphone-based, handheld fundus camera with that of retinal images captured with a commercial fundus camera and to analyze their agreement in determining the cup-to-disc ratio for a cohort of ophthalmological patients. METHODS: A total of 50 patients from a secondary ophthalmic outpatient service center underwent a bilateral fundus examination under mydriasis with a smartphone-based, handheld fundus camera and with a commercial fundus camera (4 images/patient by each). Two experienced ophthalmologists evaluated all the fundus images and graded them on the Likert 1-5 scale for quality. Multivariate regression analyses was then performed to evaluate the factors associated with the image quality. Two masked ophthalmologists determined the vertical cup-to-disc ratio of each fundus image, and both the intraobserver (between devices) and interobserver agreement between them was calculated. RESULTS: Ninety-eight images from 49 patients were processed in this study for their quality analysis. Ten images from five patients (four from commercial fundus camera and one from smartphone-based, handheld fundus camera) were not included in the analyses due to their extremely poor quality. The medians [interquartile interval] of the image quality were not significantly different between those from the smartphone-based, handheld fundus camera and from the commercial fundus camera (4 [4-5] versus 4 [3-4] respectively, p=0.06); however, both the images captured with the commercial fundus camera and the presence of media opacity presented a significant negative correlation with the image quality. Both the intraobserver [intraclass correlation coefficient (ICC)=0.82, p<0.001 and 0.83, p<0.001, for examiners 1 and 2, respectively] and interobserver (ICC=0.70, p=0.001 and 0.81; p<0.001, for smartphone-based handheld fundus camera and commercial fundus camera, respectively) agreements were excellent and statistically significant. CONCLUSIONS: Our results thus indicate that the smartphone-based, handheld fundus camera yields an image quality similar to that from a commercial fundus camera, with significant agreement in the cup-to-disc ratios between them. In addition to the good outcomes recorded, the smartphone-based, handheld fundus camera offers the advantages of portability and low-cost to serve as an alternative for fundus documentation for future telemedicine approaches in medical interventions.