Attention Based Glaucoma Detection: A Large-Scale Database and CNN Model

Li, Liu; Xu, Mai; Wang, Xiaofei; Jiang, Lai; Liu, Hanruo

doi:10.1109/cvpr.2019.01082

Cited by 204 publications

(91 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine-learning algorithms are appropriate for various complicated image classification problems such as glaucoma disease classification from retinal images [ 7 , 8 , 9 ]. Glaucoma is a chronic eye disease caused by eye retinal changes [ 10 ] which leads to gradual vision loss and, finally, complete blindness occurs if not diagnosed timely [ 11 , 12 ]. Glaucoma-Deep, a feature-based learning framework was proposed which contains four phases: identification, extraction, optimization, and classification.…”

Section: Methodsmentioning

confidence: 99%

An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification

et al. 2020

View full text Add to dashboard Cite

Glaucoma, an eye disease, occurs due to Retinal damages and it is an ordinary cause of blindness. Most of the available examining procedures are too long and require manual instructions to use them. In this work, we proposed a multi-level deep convolutional neural network (ML-DCNN) architecture on retinal fundus images to diagnose glaucoma. We collected a retinal fundus images database from the local hospital. The fundus images are pre-processed by an adaptive histogram equalizer to reduce the noise of images. The ML-DCNN architecture is used for features extraction and classification into two phases, one for glaucoma detection known as detection-net and the second one is classification-net used for classification of affected retinal glaucoma images into three different categories: Advanced, Moderate and Early. The proposed model is tested on 1338 retinal glaucoma images and performance is measured in the form of different statistical terms known as sensitivity (SE), specificity (SP), accuracy (ACC), and precision (PRE). On average, SE of 97.04%, SP of 98.99%, ACC of 99.39%, and PRC of 98.2% are achieved. The obtained outcomes are comparable to the state-of-the-art systems and achieved competitive results to solve the glaucoma eye disease problems for complex glaucoma eye disease cases.

show abstract

Section: Methodsmentioning

confidence: 99%

An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Zhang et al [48] introduced an attention enhancement module (AAS) to assist an attention module in generating a more efficient attention map. The authors of [49] proposed an attention-based CNN for glaucoma detection. Tang et al [50] proposed an attention mechanism for 3D medical image segmentation, in which a cascaded detection module followed by a segmentation module was applied to produce a set of object region candidates.…”

Section: Methodsmentioning

confidence: 99%

Detection of Microaneurysms in Fundus Images Based on an Attention Mechanism

Zhang

Feng

Duan

et al. 2019

Genes

View full text Add to dashboard Cite

Microaneurysms (MAs) are the earliest detectable diabetic retinopathy (DR) lesions. Thus, the ability to automatically detect MAs is critical for the early diagnosis of DR. However, achieving the accurate and reliable detection of MAs remains a significant challenge due to the size and complexity of retinal fundus images. Therefore, this paper presents a novel MA detection method based on a deep neural network with a multilayer attention mechanism for retinal fundus images. First, a series of equalization operations are performed to improve the quality of the fundus images. Then, based on the attention mechanism, multiple feature layers with obvious target features are fused to achieve preliminary MA detection. Finally, the spatial relationships between MAs and blood vessels are utilized to perform a secondary screening of the preliminary test results to obtain the final MA detection results. We evaluated the method on the IDRiD_VOC dataset, which was collected from the open IDRiD dataset. The results show that our method effectively improves the average accuracy and sensitivity of MA detection.

show abstract

“…An external-attention mechanism allows the network to learn to generate an attention map during the training process by conducting ROI supervision externally so that the region activated by the network can accurately diagnose disease changes. One study [23], [38] applied this mechanism to the diagnosis of COVID-19 and glaucoma, and the sensitivity was greatly improved. In contrast, a self-attention mechanism does not rely on external ROI supervision but rather exploits the intrinsic self-attention ability of CNN.…”

Section: Related Workmentioning

confidence: 99%

SCOAT-Net: A Novel Network for Segmenting COVID-19 Lung Opacification from CT Images

Zhao

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

The new coronavirus disease 2019 (COVID19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread worldwide at a rapid rate. There is no clinically automated tool to quantify the infection of COVID-19 patients. Automatic segmentation of lung opacification from computed tomography (CT) images provides excellent potential, which is of great significance for judging the disease development and treatment response of the patients. However, the segmentation of lung opacification from CT slices still faces some challenges, including the complexity and variability features of the opacity regions, the small difference between the infected and healthy tissues, and the noise of CT images. Besides, due to the limited medical resources, it is impractical to obtain a large amount of data in a short time, which further hinders the training of deep learning models. To answer these challenges, we proposed a novel spatial and channel-wise coarse-to-fine attention network (CAT-Net) inspired by the biological vision mechanism, which is for the segmentation of COVID-19 lung opacification from CT Images. CAT-Net has the spatial-wise attention module and the channel-wise attention module to attract the self-attention learning of the network, which serves to extract the practical features at the pixel and channel level successfully. Experiments show that our proposed CAT-Net achieves better results compared to state-of-the-art image segmentation networks.

show abstract

Attention Based Glaucoma Detection: A Large-Scale Database and CNN Model

Cited by 204 publications

References 31 publications

An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification

An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification

Detection of Microaneurysms in Fundus Images Based on an Attention Mechanism

SCOAT-Net: A Novel Network for Segmenting COVID-19 Lung Opacification from CT Images

Contact Info

Product

Resources

About