Redundancy reduced depthwise separable convolution for glaucoma classification using OCT images

Sunija, A.P.; Gopi, Varun P.; Palanisamy, P.

doi:10.1016/j.bspc.2021.103192

Cited by 23 publications

(7 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing classification methods for multitype retinal diseases based on CNN were computationally intensive, restricting memory potency and training, which affected the optimization of hyperparameters. 32 Thus, we designed a shallow CNN to reduce computing load, memory requirements, and hyperparameter scale as the backbone of our multilabel classification network, which can learn multilabel lesion features for multitype retinal disease classification. The shallow CNN consisted of four convolution layers, three max-pooling layers, and three FC layers.…”

Section: Methodsmentioning

confidence: 99%

Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention

Miao

Dong

et al. 2023

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Purpose Automatic multilabel classification of multiple fundus diseases is of importance for ophthalmologists. This study aims to design an effective multilabel classification model that can automatically classify multiple fundus diseases based on color fundus images. Methods We proposed a multilabel fundus disease classification model based on a convolutional neural network to classify normal and seven categories of common fundus diseases. Specifically, an attention mechanism was introduced into the network to further extract information features from color fundus images. The fundus images with eight categories of labels were applied to train, validate, and test our model. We employed the validation accuracy, area under the receiver operating characteristic curve (AUC), and F1-score as performance metrics to evaluate our model. Results Our proposed model achieved better performance with a validation accuracy of 94.27%, an AUC of 85.80%, and an F1-score of 86.08%, compared to two state-of-the-art models. Most important, the number of training parameters has dramatically dropped by three and eight times compared to the two state-of-the-art models. Conclusions This model can automatically classify multiple fundus diseases with not only excellent accuracy, AUC, and F1-score but also significantly fewer training parameters and lower computational cost, providing a reliable assistant in clinical screening. Translational Relevance The proposed model can be widely applied in large-scale multiple fundus disease screening, helping to create more efficient diagnostics in primary care settings.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention

Miao

Dong

et al. 2023

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…The first depthwise convolution, which is responsible for the filtering stage, is currently being performed. The combining stage, which involves the execution of the second pointwise convolution [ 18 ]. When it comes to the number of input channels, depthwise convolution only put on to a solo convolution for one time.…”

Section: Methodsmentioning

confidence: 99%

A Novel Approach for Prediction of Lung Disease Using Chest X-ray Images Based on DenseNet and MobileNet

Tekerek

Al-Rawe

2023

Wireless Pers Commun

View full text Add to dashboard Cite

Covid19 corona virus has caused widespread disruption across the world, in terms of the health, economy, and society problems. X-ray images of the chest can be helpful in making an accurate diagnosis because the corona virus typically first manifests its symptoms in patients' lungs. In this study, a classification method based on deep learning is proposed as a means of identifying lung disease from chest X-ray images. In the proposed study, the detection of covid19 corona virus disease from chest X-ray images was made with MobileNet and Densenet models, which are deep learning methods. Several different use cases can be built with the help of MobileNet model and case modelling approach is utilized to achieve 96% accuracy and an Area Under Curve (AUC) value of 94%. According to the result, the proposed method may be able to more accurately identify the signs of an impurity from dataset of chest X-ray images. This research also compares various performance parameters such as precision, recall and F1-Score.

show abstract

“…Sunija et al. [30] proposed an SD‐OCT‐based depthwise separable convolution model to classify glaucoma. Li et al.…”

Section: Related Workmentioning

confidence: 99%

Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition

Xiao-qing

Xiao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Eye health has become a global health concern and attracted broad attention. Over the years, researchers have proposed many state‐of‐the‐art convolutional neural networks (CNNs) to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely. However, most existing methods were dedicated to constructing sophisticated CNNs, inevitably ignoring the trade‐off between performance and model complexity. To alleviate this paradox, this paper proposes a lightweight yet efficient network architecture, mixed‐decomposed convolutional network (MDNet), to recognise ocular diseases. In MDNet, we introduce a novel mixed‐decomposed depthwise convolution method, which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low‐resolution and high‐resolution patterns by using fewer computations and fewer parameters. We conduct extensive experiments on the clinical anterior segment optical coherence tomography (AS‐OCT), LAG, University of California San Diego, and CIFAR‐100 datasets. The results show our MDNet achieves a better trade‐off between the performance and model complexity than efficient CNNs including MobileNets and MixNets. Specifically, our MDNet outperforms MobileNets by 2.5% of accuracy by using 22% fewer parameters and 30% fewer computations on the AS‐OCT dataset.

show abstract

Redundancy reduced depthwise separable convolution for glaucoma classification using OCT images

Cited by 23 publications

References 49 publications

Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention

Automatic Multilabel Classification of Multiple Fundus Diseases Based on Convolutional Neural Network With Squeeze-and-Excitation Attention

A Novel Approach for Prediction of Lung Disease Using Chest X-ray Images Based on DenseNet and MobileNet

Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition

Contact Info

Product

Resources

About