Microaneurysm detection in color eye fundus images for diabetic retinopathy screening

Melo, Tânia; Mendonça, Ana Maria; Campilho, Aurélio

doi:10.1016/j.compbiomed.2020.103995

Cited by 43 publications

(15 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wankhede, K. B. Khanchandani [ 193 ] 2020 DIARETDB1 E-optha MA Pixel Intensity Rank Transform DIARETDB1 98.79%, E-optha MA 94.59% DIARETDB1 83.33% E-optha MA 96.56% DIARETDB1 97.75% E-optha MA 95.80% – D. Jeba Derwin et al [ 42 ] 2020 ROC Single real- time, AGAR300 Local Neighborhood Differential Coherence Pattern (LNDCP) For ROC and AGAR300, FROC scores of 0.481 and 0.442 were attained, respectively. – Tania Melo et al [ 119 ] 2020 ROC e-ophtha SCREEN-DR Messidor Sliding band filter (SBF) At the lesion level, e-ophtha- 64% SCREEN-DR- 81% – – Train dataset ROC- 0.716 e-ophtha MA- 0.792 SCREEN-DR- 0.831 Shengchun Long et al [ 110 ] 2019 e-ophtha MA and DIARETDB1 Directional Local Contrast (DLC) FROC Score e-ophtha MA 0.374 DIARETDB1 0.210 e-ophtha MA 0.87 and DIARETDB1 0.86 Amrita Roy Chowdhury et al [ 35 ] 2019 DIARETDB1, Teleoptha, Messidor Naïve Bayes classifier, Random Forest classifier, K-means clustering – – Random Forest classifier- 93.58% Naïve Bayes classifier- 83.63% – Shailesh Kumar, Basant Kumar [ 96 ] 2018 DIARETDB1 PCA, CLAHE, Averaging filter, SVM 96% 92% – – Jose Ignacio Orlando et al [ 134 ] 2018 DIARETDB1, e-optha, Messidor CNN using handcrafted elements, Random Forest classifier 97.2% – – 93.4% Diana Veiga et al [ 183 ] ...…”

Section: Dr Screening Methodsmentioning

confidence: 99%

Recent developments on computer aided systems for diagnosis of diabetic retinopathy: a review

Dubey

Dixit

2022

Multimed Tools Appl

View full text Add to dashboard Cite

Diabetes is a long-term condition in which the pancreas quits producing insulin or the body’s insulin isn’t utilised properly. One of the signs of diabetes is Diabetic Retinopathy. Diabetic retinopathy is the most prevalent type of diabetes, if remains unaddressed, diabetic retinopathy can affect all diabetics and become very serious, raising the chances of blindness. It is a chronic systemic condition that affects up to 80% of patients for more than ten years. Many researchers believe that if diabetes individuals are diagnosed early enough, they can be rescued from the condition in 90% of cases. Diabetes damages the capillaries, which are microscopic blood vessels in the retina. On images, blood vessel damage is usually noticeable. Therefore, in this study, several traditional, as well as deep learning-based approaches, are reviewed for the classification and detection of this particular diabetic-based eye disease known as diabetic retinopathy, and also the advantage of one approach over the other is also described. Along with the approaches, the dataset and the evaluation metrics useful for DR detection and classification are also discussed. The main finding of this study is to aware researchers about the different challenges occurs while detecting diabetic retinopathy using computer vision, deep learning techniques. Therefore, a purpose of this review paper is to sum up all the major aspects while detecting DR like lesion identification, classification and segmentation, security attacks on the deep learning models, proper categorization of datasets and evaluation metrics. As deep learning models are quite expensive and more prone to security attacks thus, in future it is advisable to develop a refined, reliable and robust model which overcomes all these aspects which are commonly found while designing deep learning models.

show abstract

Section: Dr Screening Methodsmentioning

confidence: 99%

Recent developments on computer aided systems for diagnosis of diabetic retinopathy: a review

Dubey

Dixit

2022

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Melo et al [ 5 ] used a sliding band filter for MA enhancement and they also used the filter response and the salience of the candidate area for classification. Antal and Hajdu [ 6 ] proposed an ensemble-based framework for MA detection; they selected the optimal results under different preprocessing and candidate extraction methods.…”

Section: Related Workmentioning

confidence: 99%

“…The current mainstream MA detection algorithm [ 3 , 4 , 5 , 6 , 7 ] can be briefly summarized as the following three steps: preprocessing, candidate extraction, and candidate classification. The preprocessing methods mainly include color correction, contrast enhancement, reflective elimination, and other image enhancement operations.…”

Section: Introductionmentioning

confidence: 99%

Local Structure Awareness-Based Retinal Microaneurysm Detection with Multi-Feature Combination

et al. 2022

View full text Add to dashboard Cite

Retinal microaneurysm (MA) is the initial symptom of diabetic retinopathy (DR). The automatic detection of MA is helpful to assist doctors in diagnosis and treatment. Previous algorithms focused on the features of the target itself; however, the local structural features of the target and background are also worth exploring. To achieve MA detection, an efficient local structure awareness-based retinal MA detection with the multi-feature combination (LSAMFC) is proposed in this paper. We propose a novel local structure feature called a ring gradient descriptor (RGD) to describe the structural differences between an object and its surrounding area. Then, a combination of RGD with the salience and texture features is used by a Gradient Boosting Decision Tree (GBDT) for candidate classification. We evaluate our algorithm on two public datasets, i.e., the e-ophtha MA dataset and retinopathy online challenge (ROC) dataset. The experimental results show that the performance of the trained model significantly improved after combining traditional features with RGD, and the area under the receiver operating characteristic curve (AUC) values in the test results of the datasets e-ophtha MA and ROC increased from 0.9615 to 0.9751 and from 0.9066 to 0.9409, respectively.

show abstract

“…Los trabajos desarrollados por Chenxi, Huang, et al [26], Melo, Tania, et al [27], Adem, K. [28], Tsiknakis, Nikos, et al [17] y P. Xiangji, et al [29], todos clasificados en el cuartil Q1 como estudios de alta calidad usaron las mentiras de exactitud, sensibilidad, especificidad, precisión, recuperación y puntuación-F1 para medir el resultado de sus trabajos, y, por este motivo, validamos que son estas las más idóneas para los estudios de patologías como la RD en imágenes.…”

Section: Métricasunclassified

“…Tania Melo et al (2020) [27] propusieron un algoritmo para la detección de microaneurismas en imágenes de fondo de ojo, comenzando con el pre-pocesamiendo de las imágenes tomando el canal verde de estas, aplicando un filtro gaussiano de paso bajo para eliminar el ruido de las imágenes y un SBF a la imagen ya filtrada. Para la clasificación de las imágenes utilizaron técnicas de supresión no máxima para obtener sólo un candidato por lesión, crecimiento de regiones con un límite de tamaño de 315 píxeles que definieron en función del radio máximo esperado de los MA y usaron la respuesta máxima del SBF y la desviación estándar de los valores de intensidad en la imagen preprocesada para definir a los candidatos.…”

Section: Xiangji Et Al (2020)unclassified

Revisión de técnicas de Deep Learning y Machine Learning para la detección y localización de micro aneurismas, exudados y hemorragias en imágenes de fondo de ojo

et al. 2022

View full text Add to dashboard Cite

La pérdida de la visión ha sido uno de los casos más desafortunados de pérdida de los sentidos. Es sabido que la perdida de la visión disminuye considerablemente la calidad de vida de una persona, sin importar la edad. De acuerdo con la OMS, el deterioro de la visión impacta negativamente a niños pequeños en etapa escolar, dado que afecta en gran medida su etapa de desarrollo; en cuanto a los adultos, el deterioro de la visión se ve reflejado a partir de las tasas de participación en el mercado laboral y de productividad de esta población, no obstante, suele ser más baja. Una de las causas de la pérdida de la visión es la retinopatía diabética, que consiste en una enfermedad ocular producto de la diabetes mellitus por un prolongado periodo de tiempo que causa la pérdida parcial o total de la visión. En ese orden de ideas, el objetivo de la presente investigación consiste en recopilar y analizar los diferentes estudios sobre el tema en cuestión; tal información fue tomada de diversas bases de datos especializadas, teniendo en cuenta una clasificación de los cuartiles Q1 y Q2, y cuyo factor de impacto estuvo por encima 2,5 para su selección. Estos en torno a la detección y localización de las tres más importantes anomalías que hacen presencia en personas que sufren de RD, estas son micro aneurismas, exudados y hemorragias. Para ello se necesitaron imágenes de fondo de ojo de pacientes que padecen o están propensos a padecer retinopatía diabética, haciendo uso de algoritmos con técnicas de deep learning y machine. Dichos algoritmos estuvieron guiados por métricas tales como exactitud, sensibilidad y especificad con el fin de medir la eficiencia de algoritmo desarrollado.

show abstract

Microaneurysm detection in color eye fundus images for diabetic retinopathy screening

Cited by 43 publications

References 41 publications

Recent developments on computer aided systems for diagnosis of diabetic retinopathy: a review

Recent developments on computer aided systems for diagnosis of diabetic retinopathy: a review

Local Structure Awareness-Based Retinal Microaneurysm Detection with Multi-Feature Combination

Revisión de técnicas de Deep Learning y Machine Learning para la detección y localización de micro aneurismas, exudados y hemorragias en imágenes de fondo de ojo

Contact Info

Product

Resources

About