Machine Learning for Cataract Classification and Grading on Ophthalmic Imaging Modalities: A Survey

Zhang, Xiaoqing; Fang, Jiansheng; Hu, Yan; Xu, Yanwu; Higashita, Risa; Liu, Jiang

doi:10.48550/arxiv.2012.04830

Cited by 5 publications

(5 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the algorithms employed in the feature extraction or classi cation stages, these techniques are divided into two groups: machine learning (ML)-based and deep learning (DL)-based methods. These techniques have been covered in recent studies [9] - [12]. We quickly review a few of the most important works from both groups in this section.…”

Section: Related Workmentioning

confidence: 99%

“…DCNNs and an optimised Residual NN classi cation model are used. Recent studies by Zhang [12]. According to an attention-based MultiModel Ensemble method for automatically detecting cataracts on ultrasound pictures had "the greatest accuracy (97.5%)" among the various deep learning-based methods in the research works published.…”

Section: B Different Models Using Deeplearningmentioning

confidence: 99%

See 1 more Smart Citation

Cataract Detection Using Deep Learning

Panda¹,

Panjwani²

2023

Preprint

View full text Add to dashboard Cite

In a human life a very common disorder that occurs is, eye disorder named CATARACT, this eye disorder is mostly common in humans within the age group of 40–50 years. If neglected can lead to eye blindness. One can avoid this type of eye disorder from getting worse by detecting it on-time. So we are proposing our model that uses Deep Learning to detect this disorder, using Fundus Images. The model contains fully connected hidden layers with cost function and activation functions to properly train the model and optimize it and to significantly reduce the computational cost compared to other models. Total 1130 affected and 1130 non affected images are feeded to model in order to train model properly so that model doesn’t get overfitted.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: B Different Models Using Deeplearningmentioning

confidence: 99%

Cataract Detection Using Deep Learning

Panda¹,

Panjwani²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, instruments for fundus images and slit-lamp images are not easy to access for people living in rural areas. Comparatively, digital camera images are more available as an alternative for ophthalmic images when cataract detection is performed [29]. Therefore, a cataract detection system based on digital camera images is highly required for early cataract detection that is more popular and user friendly.…”

Section: Related Workmentioning

confidence: 99%

“…Convolutional neural networks with both feature extraction and classification capabilities [29] can cope with classification problems effectively and efficiently. In addition, weight sharing and feature extraction in the convolutional neural network have highly improved the computation efficiency.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

The Use of Convolutional Neural Networks and Digital Camera Images in Cataract Detection

et al. 2022

View full text Add to dashboard Cite

Cataract is one of the major causes of blindness in the world. Its early detection and treatment could greatly reduce the risk of deterioration and blindness. Instruments commonly used to detect cataracts are slit lamps and fundus cameras, which are highly expensive and require domain knowledge. Thus, the problem is that the lack of professional ophthalmologists could result in the delay of cataract detection, where medical treatment is inevitable. Therefore, this study aimed to design a convolutional neural network (CNN) with digital camera images (CNNDCI) system to detect cataracts efficiently and effectively. The designed CNNDCI system can perform the cataract identification process accurately in a user-friendly manner using smartphones to collect digital images. In addition, the existing numerical results provided by the literature were used to demonstrate the performance of the proposed CNNDCI system for cataract detection. Numerical results revealed that the designed CNNDCI system could identify cataracts effectively with satisfying accuracy. Thus, this study concluded that the presented CNNDCI architecture is a feasible and promising alternative for cataract detection.

show abstract

“…Conventional machine learning methods. Literature [20][21][22][23]42] develops an automatic nuclear cataract grading system based on slit lamp images, comprised of lens contour detection, feature extraction, and classification. They used linear regression (LR) as the classifier and achieved a 0.36 mean error in their work.…”

Section: Automatic Cataract Classificationmentioning

confidence: 99%

Nuclear cataract classification in anterior segment OCT based on clinical global–local features

Zhang

Xiao

et al. 2022

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Nuclear cataract (NC) is a priority ocular disease of blindness and vision impairment globally. Early intervention and cataract surgery can improve the vision and life quality of NC patients. Anterior segment coherence tomography (AS-OCT) imaging is a non-invasive way to capture the NC opacity objectively and quantitatively. Recent clinical research has shown that there exists a strong opacity correlation relationship between NC severity levels and the mean density on AS-OCT images. In this paper, we present an effective NC classification framework on AS-OCT images, based on feature extraction and feature importance analysis. Motivated by previous clinical knowledge, our method extracts the clinical global-local features, and then applies Pearson's correlation coefficient and recursive feature elimination methods to analyze the feature importance. Finally, an ensemble logistic regression is employed to distinguish NC, which considers different optimization methods' characteristics. A dataset with 11,442 AS-OCT images is collected to evaluate the method. The results show that the proposed method achieves 86.96% accuracy and 88.70% macro-sensitivity, respectively. The performance comparison analysis also demonstrates that the global-local feature extraction method improves about 2% accuracy than the single region-based feature extraction method.

show abstract

Machine Learning for Cataract Classification and Grading on Ophthalmic Imaging Modalities: A Survey

Cited by 5 publications

References 138 publications

Cataract Detection Using Deep Learning

Cataract Detection Using Deep Learning

The Use of Convolutional Neural Networks and Digital Camera Images in Cataract Detection

Nuclear cataract classification in anterior segment OCT based on clinical global–local features

Contact Info

Product

Resources

About