The relationship between Fully Connected Layers and number of classes for the analysis of retinal images

Ram, Ajna; Reyes-Aldasoro, Constantino Carlos

doi:10.48550/arxiv.2004.03624

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) We eliminated a few images that were marked as low image quality, however, these images are unavoidable in practical situations. (4) It was found out that the effect of increasing the number of fully-connected layers of a neural networks depends on the type of data set being used 42 , in our experiments, we found that in the convolution stage, the number of hidden dimensions also has a great impact on the recognition accuracy of fundus diseases, which is worth further study.…”

Section: Discussionmentioning

confidence: 69%

Combining convolutional neural networks and self-attention for fundus diseases identification

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Early detection of lesions is of great significance for treating fundus diseases. Fundus photography is an effective and convenient screening technique by which common fundus diseases can be detected. In this study, we use color fundus images to distinguish among multiple fundus diseases. Existing research on fundus disease classification has achieved some success through deep learning techniques, but there is still much room for improvement in model evaluation metrics using only deep convolutional neural network (CNN) architectures with limited global modeling ability; the simultaneous diagnosis of multiple fundus diseases still faces great challenges. Therefore, given that the self-attention (SA) model with a global receptive field may have robust global-level feature modeling ability, we propose a multistage fundus image classification model MBSaNet which combines CNN and SA mechanism. The convolution block extracts the local information of the fundus image, and the SA module further captures the complex relationships between different spatial positions, thereby directly detecting one or more fundus diseases in retinal fundus image. In the initial stage of feature extraction, we propose a multiscale feature fusion stem, which uses convolutional kernels of different scales to extract low-level features of the input image and fuse them to improve recognition accuracy. The training and testing were performed based on the ODIR-5k dataset. The experimental results show that MBSaNet achieves state-of-the-art performance with fewer parameters. The wide range of diseases and different fundus image collection conditions confirmed the applicability of MBSaNet.

show abstract

Section: Discussionmentioning

confidence: 69%

Combining convolutional neural networks and self-attention for fundus diseases identification

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…(3) We eliminated a few images that were marked as low image quality, however, these images are unavoidable in practical situations. (4) It was found out that the effect of increasing the number of fully-connected layers of a neural networks depends on the type of data set being used 28 , in our experiments, we found that in the convolution stage, the number of hidden dimensions also has a great impact on the recognition accuracy of fundus diseases, which is worth further study.…”

Section: Ablation Studymentioning

confidence: 69%

MBSaNet : A combination of convolutional neural networks and self-attention for the identification of fundus diseases

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Early detection of lesions is of great significance for treating fundus diseases. Fundus photography is an effective and convenient screening technique by which common fundus diseases can be detected. In this study, we use color fundus images to distinguish among multiple fundus diseases. Existing research on fundus disease classification has achieved some success through deep learning techniques, but there is still much room for improvement in model evaluation metrics using only deep convolutional neural network (CNN) architectures with limited global modeling ability; the simultaneous diagnosis of multiple fundus diseases still faces great challenges. Therefore, given that the self-attention (SA) model with a global receptive field may have robust global-level feature modeling ability, we propose a multistage fundus image classification model —MBSaNet —which combines CNN and SA mechanism. The convolution block extracts the local information of the fundus image, and the SA module further captures the complex relationships between different spatial positions, thereby directly detecting one or more fundus diseases in retinal fundus image. In the initial stage of feature extraction, we propose a multiscale feature fusion stem, which uses convolutional kernels of different scales to extract low-level features of the input image and fuse them to improve recognition accuracy. The training and testing were performed based on the ODIR-5k dataset. The experimental results show that MBSaNet achieves state-of-the-art performance with fewer parameters. The wide range of diseases and different fundus image collection conditions confirmed the applicability of MBSaNet.

show abstract

“…According to the statistics of 2019, over 2.2 billion people suffer from different eye diseases that result in serious vision impairment and partial or full blindness [1]. One of the main reasons for vision impairment is age-related macular degeneration (AMD).…”

Section: Introductionmentioning

confidence: 99%

Conv-ViT: A Convolution and Vision Transformer-Based Hybrid Feature Extraction Method for Retinal Disease Detection

et al. 2023

View full text Add to dashboard Cite

The current advancement towards retinal disease detection mainly focused on distinct feature extraction using either a convolutional neural network (CNN) or a transformer-based end-to-end deep learning (DL) model. The individual end-to-end DL models are capable of only processing texture or shape-based information for performing detection tasks. However, extraction of only texture- or shape-based features does not provide the model robustness needed to classify different types of retinal diseases. Therefore, concerning these two features, this paper developed a fusion model called ‘Conv-ViT’ to detect retinal diseases from foveal cut optical coherence tomography (OCT) images. The transfer learning-based CNN models, such as Inception-V3 and ResNet-50, are utilized to process texture information by calculating the correlation of the nearby pixel. Additionally, the vision transformer model is fused to process shape-based features by determining the correlation between long-distance pixels. The hybridization of these three models results in shape-based texture feature learning during the classification of retinal diseases into its four classes, including choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL. The weighted average classification accuracy, precision, recall, and F1 score of the model are found to be approximately 94%. The results indicate that the fusion of both texture and shape features assisted the proposed Conv-ViT model to outperform the state-of-the-art retinal disease classification models.

show abstract

The relationship between Fully Connected Layers and number of classes for the analysis of retinal images

Cited by 3 publications

References 11 publications

Combining convolutional neural networks and self-attention for fundus diseases identification

Combining convolutional neural networks and self-attention for fundus diseases identification

MBSaNet : A combination of convolutional neural networks and self-attention for the identification of fundus diseases

Conv-ViT: A Convolution and Vision Transformer-Based Hybrid Feature Extraction Method for Retinal Disease Detection

Contact Info

Product

Resources

About