A robust framework for glaucoma detection using CLAHE and EfficientNet

Gupta, Neeraj; Garg, Hitendra; Agarwal, Rohit

doi:10.1007/s00371-021-02114-5

Cited by 30 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although many algorithms, such as [ 52 , 53 ], have shown a high accuracy rate in segmenting these structures, this method can only be considered an indication of glaucoma and the need for a more detailed evaluation, since the diagnosis of this neuropathy is made by examination of the entire structure of the optic disc and not just excavation. Furthermore, although increased cupping suggests glaucoma, not all optic nerve cupping is related to this disease, as there are other conditions that can cause increased cupping of the optic nerve, such as neuritis, tumors, multiple sclerosis, etc.…”

Section: Related Workmentioning

confidence: 99%

Advancements in Glaucoma Diagnosis: The Role of AI in Medical Imaging

Bragança,

Torres,

Macedo

et al. 2024

Diagnostics

View full text Add to dashboard Cite

The progress of artificial intelligence algorithms in digital image processing and automatic diagnosis studies of the eye disease glaucoma has been growing and presenting essential advances to guarantee better clinical care for the population. Given the context, this article describes the main types of glaucoma, traditional forms of diagnosis, and presents the global epidemiology of the disease. Furthermore, it explores how studies using artificial intelligence algorithms have been investigated as possible tools to aid in the early diagnosis of this pathology through population screening. Therefore, the related work section presents the main studies and methodologies used in the automatic classification of glaucoma from digital fundus images and artificial intelligence algorithms, as well as the main databases containing images labeled for glaucoma and publicly available for the training of machine learning algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Advancements in Glaucoma Diagnosis: The Role of AI in Medical Imaging

Bragança,

Torres,

Macedo

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Images Related Studies RIM-ONE [12] 942 [41], [42], [43], [44], [45], [46], [47], [48], [49] ACRIMA [50] 705 [41], [42] ORIGA [11] 650 [51], [41],…”

Section: Datasetmentioning

confidence: 99%

“…101 [51], [41], [44], [46], [48] The Retinal Image database for Optic Nerve Evaluation process, first, we used the brush tool to annotate the masks in the region. We segmented the mask for both optic disk 2.…”

Section: Datasetmentioning

confidence: 99%

Automated Tool Support for Glaucoma Identification With Explainability Using Fundus Images

Shyamalee,

Meedeniya,

Lim

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Glaucoma is a progressive eye condition that causes irreversible vision loss due to damage to the optic nerve. Recent developments in deep learning and the accessibility of computing resources have provided tool support for automated glaucoma diagnosis. Despite deep learning's advances in disease diagnosis using medical images, generic convolutional neural networks are still not widely used in medical practices due to the limited trustworthiness of these models. Although deep learning-based glaucoma classification has gained popularity in recent years, only a few of them have addressed the explainability and interpretability of the models, which increases confidence in using such applications. This study presents state-of-the-art deep learning techniques to segment and classify fundus images to predict glaucoma conditions and applies visualization techniques to explain the results to ease understandability. Our predictions are based on U-Net with attention mechanisms with ResNet50 for the segmentation process and a modified Inception V3 architecture for the classification. Attention U-Net with modified ResNet50 backbone obtained 99.58% and 98.05% accuracies for optic disc segmentation and optic cup segmentation, respectively for the RIM-ONE dataset. Additionally, we generate heatmaps that highlight the regions that impacted the glaucoma diagnosis using both Gradient-weighted Class Activation Mapping (Grad-CAM) and Grad-CAM++. Our model that classifies the segmented images achieves accuracy, sensitivity, and specificity values of 98.97%, 99.42%, and 95.59%, respectively, with the RIM-ONE dataset. This model can be used as a support tool for automated glaucoma identification using fundus images.24 manually review fundus images to identify the signs that lead 25 to glaucoma conditions. However, the entire image-capturing 26

show abstract

“…EfficientNet B0 [32] is the only architecture that is more accurate than UNAS but it is also 48% slower on the GPU. Although EfficientNet B0 has a low number of mathematical operations, it is not so efficient on TPU/GPU due to the heavy usage of depth-wise separable convolutions [9]. The architectures that are faster than UNAS including ShuffleNet v2 [19], MnasNet B1 [31] and MobileNetV2 1.0x [28] are also less accurate.…”

Section: Architecturementioning

confidence: 99%

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

Vahdat¹,

Mallya²,

Li³

et al. 2019

Preprint

View full text Add to dashboard Cite

Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost orders of magnitude lower than reinforcement learning (RL) based NAS. However, DNAS models can only optimize differentiable loss functions in search, and they require an accurate differentiable approximation of non-differentiable criteria. In this work, we present UNAS, a unified framework for NAS, that encapsulates recent DNAS and RL-based approaches under one framework. Our framework brings the best of both worlds, and it enables us to search for architectures with both differentiable and non-differentiable criteria in one unified framework while maintaining a low search cost. Further, we introduce a new objective function for search based on the generalization gap that prevents the selection of architectures prone to overfitting. We present extensive experiments on the CIFAR-10, CIFAR-100 and ImageNet datasets and we perform search in two fundamentally different search spaces. We show that UNAS obtains the state-of-the-art average accuracy on all three datasets when compared to the architectures searched in the DARTS [18] space. Moreover, we show that UNAS can find an efficient and accurate architecture in the ProxylessNAS [28] search space, that outperforms existing MobileNetV2 [28] based architectures.

show abstract

A robust framework for glaucoma detection using CLAHE and EfficientNet

Cited by 30 publications

References 40 publications

Advancements in Glaucoma Diagnosis: The Role of AI in Medical Imaging

Advancements in Glaucoma Diagnosis: The Role of AI in Medical Imaging

Automated Tool Support for Glaucoma Identification With Explainability Using Fundus Images

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

Contact Info

Product

Resources

About