RESUMEN
ABSTRACT Purpose: This study aimed to evaluate the classification performance of pretrained convolutional neural network models or architectures using fundus image dataset containing eight disease labels. Methods: A publicly available ocular disease intelligent recognition database has been used for the diagnosis of eight diseases. This ocular disease intelligent recognition database has a total of 10,000 fundus images from both eyes of 5,000 patients for the following eight diseases: healthy, diabetic retinopathy, glaucoma, cataract, age-related macular degeneration, hypertension, myopia, and others. Ocular disease classification performances were investigated by constructing three pretrained convolutional neural network architectures including VGG16, Inceptionv3, and ResNet50 models with adaptive moment optimizer. These models were implemented in Google Colab, which made the task straight-forward without spending hours installing the environment and supporting libraries. To evaluate the effectiveness of the models, the dataset was divided into 70%, 10%, and 20% for training, validation, and testing, respectively. For each classification, the training images were augmented to 10,000 fundus images. Results: ResNet50 achieved an accuracy of 97.1%; sensitivity, 78.5%; specificity, 98.5%; and precision, 79.7%, and had the best area under the curve and final score to classify cataract (area under the curve = 0.964, final score = 0.903). By contrast, VGG16 achieved an accuracy of 96.2%; sensitivity, 56.9%; specificity, 99.2%; precision, 84.1%; area under the curve, 0.949; and final score, 0.857. Conclusions: These results demonstrate the ability of the pretrained convolutional neural network architectures to identify ophthalmological diseases from fundus images. ResNet50 can be a good architecture to solve problems in disease detection and classification of glaucoma, cataract, hypertension, and myopia; Inceptionv3 for age-related macular degeneration, and other disease; and VGG16 for normal and diabetic retinopathy.
RESUMO Objetivo: Avaliar o desempenho de classificação de modelos ou arquiteturas de rede neural convolucional pré--treinadas usando um conjunto de dados de imagem de fundo de olho contendo oito rótulos de doenças diferentes. Métodos: Neste artigo, o conjunto de dados de reconhecimento inteligente de doenças oculares publicamente disponível foi usado para o diagnóstico de oito rótulos de doenças diferentes. O banco de dados de reconhecimento inteligente de doenças oculares tem um total de 10.000 imagens de fundo de olho de ambos os olhos de 5.000 pacientes para oito categorias que contêm rótulos saudáveis, retinopatia diabética, glaucoma, catarata, degeneração macular relacionada à idade, hipertensão, miopia, outros. Investigamos o desempenho da classificação de doenças oculares construindo três arquiteturas de rede neural convolucional pré-treinadas diferentes, incluindo os modelos VGG16, Inceptionv3 e ResNet50 com otimizador de Momento Adaptativo. Esses modelos foram implementados no Google Colab o que facilitou a tarefa sem gastar horas instalando o ambiente e suportando bibliotecas. Para avaliar a eficácia dos modelos, o conjunto de dados é dividido em 70% para treinamento, 10% para validação e os 20% restantes utilizados para teste. As imagens de treinamento foram expandidas para 10.000 imagens de fundo de olho para cada tal. Resultados: Observou-se que o modelo ResNet50 alcançou acurácia de 97,1%, sensibilidade de 78,5%, especificidade de 98,5% e precisão de 79,7% e teve a melhor área sob a curva e pontuação final para classificar a categoria da catarata (área sob a curva=0,964, final=0,903). Em contraste, o modelo VGG16 alcançou uma precisão de 96,2%, sensibilidade de 56,9%, especificidade de 99,2% e precisão de 84,1%, área sob a curva 0,949 e pontuação final de 0,857. Conclusão: Esses resultados demonstram a capacidade das arquiteturas de rede neural convolucional pré-treinadas em identificar doenças oftalmológicas a partir de imagens de fundo de olho. ResNet50 pode ser uma boa solução para resolver problemas na detecção e classificação de doenças como glaucoma, catarata, hipertensão e miopia; Inceptionv3 para degeneração macular relacionada à idade e outras doenças; e VGG16 para retinopatia normal e diabética.
RESUMEN
SUMMARY OBJECTIVE: This study aimed to compare the serum samples found reactive (≥1-≤20 signal-to-cutoff ratio) with Elecsys antibodies to hepatitis C virus screening test with innogenetics-line immunassay hepatitis C Virus Score test and to determine the most appropriate threshold value for our country, since positive results close to the cutoff value cause serious problems in routine diagnostic laboratories. METHODS: Antibodies to hepatitis C virus-positive samples from 687 different patients were included in the study. Antibodies to hepatitis C virus antibody detection was performed using Elecsys antibodies to hepatitis C virus II kits (Roche Diagnostics, Germany), an electrochemiluminescence method based on the double-antigen sandwich principle, on the Cobas e601 analyzer (Roche Diagnostics) in accordance with the recommendations of the manufacturer. Samples that were initially identified as reactive were studied again. Samples with ≥1-≤20 signal-to-cutoff ratio reagents as a result of retest were included in the study to be validated with the third-Generation Line immunassay kit (innogenetics-line immunassay hepatitis C Virus, Belgium). RESULTS: A total of 687 samples with antibodies to hepatitis C virus positive and levels between 1-20 S/Co were found to be 56.1% negative, 14.8% indeterminate, and 29.1% positive by innogenetics-line immunassay hepatitis C Virus confirmation test. When the cases with indeterminate innogenetics-line immunassay hepatitis C Virus test results were accepted as positive, the signal-to-cutoff ratio value for antibodies to hepatitis C virus was determined as 5.8 (95% confidence interval) in distinguishing the innogenetics-line immunassay hepatitis C Virus negative and positive groups. CONCLUSION: It was concluded that with further studies on this subject, each country should determine the most appropriate S/Co value for its population, and thus it would be beneficial to reduce the problems such as test repetition and cost increase.