Diabetic retinopathy classification using VGG16 neural network

Rocha, Douglas Abreu da; Ferreira, Flavia Magalhaes Freitas; Peixoto, Zélia Myriam Assis

doi:10.1007/s42600-022-00200-8

Cited by 36 publications

(19 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our proposed network, MIL-ResNet14, is evaluated against two other networks, Res-Net14 and VGG16. VGG16 was has been demonstratead to be capable of classifying DR before [5]. The weights of VGG16 were initialized with ImageNet weights and only the last 6 layers were retrained with our data.…”

Section: Methodsmentioning

confidence: 99%

Stable detection of diabetic lesions in widefield optical coherence tomography angiography en face images using a multiple instance learning binary classifier

Matten,

Scherer,

Schlegl

et al. 2023

Optical Coherence Imaging Techniques and Imaging in Scattering Media V

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Stable detection of diabetic lesions in widefield optical coherence tomography angiography en face images using a multiple instance learning binary classifier

Matten,

Scherer,

Schlegl

et al. 2023

Optical Coherence Imaging Techniques and Imaging in Scattering Media V

View full text Add to dashboard Cite

“…Since our network utilizes MIL, a supervised learning classification approach, we benchmarked our network against two other proven single instance learning (SIL)-based networks for classification, ResNet14, and VGG16 38 – 40 . Da Rocha et al could show that a pre-trained version of VGG16 is capable of predicting DR from FP 41 . Since it is rather hard for a human to trace what portions of the images a convolutional neural network (CNN) deems important, we implemented a visualization technique called Grad-CAM 42 , highlighting regions contributing strongly to the classification decision, ideally clearly visible biomarkers.…”

Section: Methodsmentioning

confidence: 99%

Multiple instance learning based classification of diabetic retinopathy in weakly-labeled widefield OCTA en face images

Matten

Scherer

Schlegl

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Diabetic retinopathy (DR), a pathologic change of the human retinal vasculature, is the leading cause of blindness in working-age adults with diabetes mellitus. Optical coherence tomography angiography (OCTA), a functional extension of optical coherence tomography, has shown potential as a tool for early diagnosis of DR through its ability to visualize the retinal vasculature in all spatial dimensions. Previously introduced deep learning-based classifiers were able to support the detection of DR in OCTA images, but require expert labeling at the pixel level, a labor-intensive and expensive process. We present a multiple instance learning-based network, MIL-ResNet,14 that is capable of detecting biomarkers in an OCTA dataset with high accuracy, without the need for annotations other than the information whether a scan is from a diabetic patient or not. The dataset we used for this study was acquired with a diagnostic ultra-widefield swept-source OCT device with a MHz A-scan rate. We were able to show that our proposed method outperforms previous state-of-the-art networks for this classification task, ResNet14 and VGG16. In addition, our network pays special attention to clinically relevant biomarkers and is robust against adversarial attacks. Therefore, we believe that it could serve as a powerful diagnostic decision support tool for clinical ophthalmic screening.

show abstract

“…However, the suggested approach faced classification errors while categorizing the complex features of distributed image segments. Da Rocha et al (2022) developed a novel approach of using the VGG16 neural network to address critical issues of diabetic retinopathy. The objective of this study was to create a fifth class (class 5) for low-quality digital retinal images from the DDR, EyePACS/Kaggle, and IDRiD databases in addition to classifying diabetic retinopathy into five categories.…”

Section: Related Workmentioning

confidence: 99%

Level-set based adaptive-active contour segmentation technique with long short-term memory for diabetic retinopathy classification

Bhansali,

Patra,

Abouhawwash

et al. 2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is a major type of eye defect that is caused by abnormalities in the blood vessels within the retinal tissue. Early detection by automatic approach using modern methodologies helps prevent consequences like vision loss. So, this research has developed an effective segmentation approach known as Level-set Based Adaptive-active Contour Segmentation (LBACS) to segment the images by improving the boundary conditions and detecting the edges using Level Set Method with Improved Boundary Indicator Function (LSMIBIF) and Adaptive-Active Counter Model (AACM). For evaluating the DR system, the information is collected from the publically available datasets named as Indian Diabetic Retinopathy Image Dataset (IDRiD) and Diabetic Retinopathy Database 1 (DIARETDB 1). Then the collected images are pre-processed using a Gaussian filter, edge detection sharpening, Contrast enhancement, and Luminosity enhancement to eliminate the noises/interferences, and data imbalance that exists in the available dataset. After that, the noise-free data are processed for segmentation by using the Level set-based active contour segmentation technique. Then, the segmented images are given to the feature extraction stage where Gray Level Co-occurrence Matrix (GLCM), Local ternary, and binary patterns are employed to extract the features from the segmented image. Finally, extracted features are given as input to the classification stage where Long Short-Term Memory (LSTM) is utilized to categorize various classes of DR. The result analysis evidently shows that the proposed LBACS-LSTM achieved better results in overall metrics. The accuracy of the proposed LBACS-LSTM for IDRiD and DIARETDB 1 datasets is 99.43% and 97.39%, respectively which is comparably higher than the existing approaches such as Three-dimensional semantic model, Delimiting Segmentation Approach Using Knowledge Learning (DSA-KL), K-Nearest Neighbor (KNN), Computer aided method and Chronological Tunicate Swarm Algorithm with Stacked Auto Encoder (CTSA-SAE).

show abstract

Diabetic retinopathy classification using VGG16 neural network

Cited by 36 publications

References 31 publications

Stable detection of diabetic lesions in widefield optical coherence tomography angiography en face images using a multiple instance learning binary classifier

Stable detection of diabetic lesions in widefield optical coherence tomography angiography en face images using a multiple instance learning binary classifier

Multiple instance learning based classification of diabetic retinopathy in weakly-labeled widefield OCTA en face images

Level-set based adaptive-active contour segmentation technique with long short-term memory for diabetic retinopathy classification

Contact Info

Product

Resources

About