Automatic segmentation of optic disc in retinal fundus images using semi-supervised deep learning

Bengani, Shaleen; Jothi, J. Angel Arul; Vadivel, S.

doi:10.1007/s11042-020-09778-6

Cited by 28 publications

(20 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[121] Designing a semi-supervised deep learning approach, high accuracy, acceptable runtime Insufficient experiments to evaluate the final model, not considering the effect of different parameters on the final learning model, not using different deep learning algorithms to evaluate the learning model [122] Evaluating the performance of the learning model based on different datasets, evaluating the performance of the learning model based on different conditions Not considering runtime, not using different deep learning algorithms to evaluate the learning model, not considering a suitable pre-processing scheme [123] High accuracy, designing a classifier with different classes, using a semi-supervised learning to update the predicted label Not considering runtime, not using different artificial neural networks to evaluate the learning model, not considering a suitable pre-processing scheme, insufficient experiments to evaluate the final model [124] Evaluating the learning model based on different datasets, considering various conditions to evaluate the learning model, high accuracy, accepted runtime Not using different deep learning algorithms to evaluate the learning model, not considering a suitable pre-processing scheme, needing high time for the training process [125] Evaluating the learning model based on different datasets, high accuracy Not using different basic learning algorithms to evaluate the learning model, not mentioning any reason to use SVM and KNN as basic classifiers, not designing a suitable pre-processing scheme, not describing the feature selection process…”

Section: Scheme Strengths Weaknessesmentioning

confidence: 99%

“…Bengani et al [124] offered a deep learning model for segmenting the optic disk in retinal images. This method uses two learning techniques, including semi-supervised learning and transfer learning.…”

Section: A Deep Learning Model For Segmenting Retinal Fundus Imagesmentioning

confidence: 99%

“…On the other hand, the databases available for deep retinal images are very small. In [124], the authors attempt to overcome these problems using semi-supervised learning and transfer learning.…”

Section: A Deep Learning Model For Segmenting Retinal Fundus Imagesmentioning

confidence: 99%

“…Dataset. In [124], the authors use various databases. These databases are: Data pre-processing method.…”

Section: A Deep Learning Model For Segmenting Retinal Fundus Imagesmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning (ML) in Medicine: Review, Applications, and Challenges

Rahmani

Yousefpoor

et al. 2021

Mathematics

View full text Add to dashboard Cite

Today, artificial intelligence (AI) and machine learning (ML) have dramatically advanced in various industries, especially medicine. AI describes computational programs that mimic and simulate human intelligence, for example, a person’s behavior in solving problems or his ability for learning. Furthermore, ML is a subset of artificial intelligence. It extracts patterns from raw data automatically. The purpose of this paper is to help researchers gain a proper understanding of machine learning and its applications in healthcare. In this paper, we first present a classification of machine learning-based schemes in healthcare. According to our proposed taxonomy, machine learning-based schemes in healthcare are categorized based on data pre-processing methods (data cleaning methods, data reduction methods), learning methods (unsupervised learning, supervised learning, semi-supervised learning, and reinforcement learning), evaluation methods (simulation-based evaluation and practical implementation-based evaluation in real environment) and applications (diagnosis, treatment). According to our proposed classification, we review some studies presented in machine learning applications for healthcare. We believe that this review paper helps researchers to familiarize themselves with the newest research on ML applications in medicine, recognize their challenges and limitations in this area, and identify future research directions.

show abstract

Section: Scheme Strengths Weaknessesmentioning

confidence: 99%

Section: A Deep Learning Model For Segmenting Retinal Fundus Imagesmentioning

confidence: 99%

Section: A Deep Learning Model For Segmenting Retinal Fundus Imagesmentioning

confidence: 99%

“…Dataset. In [124], the authors use various databases. These databases are: Data pre-processing method.…”

Section: A Deep Learning Model For Segmenting Retinal Fundus Imagesmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning (ML) in Medicine: Review, Applications, and Challenges

Rahmani

Yousefpoor

et al. 2021

Mathematics

View full text Add to dashboard Cite

show abstract

“…A convolutional autoencoder-(CAE-) based segmentation network for OD segmentation is proposed in [56]. Initially, the CAE is trained to learn the significant features from unlabeled fundus images by unsupervised learning, and it is transformed into a segmentation network by adding a convolutional layer with a 3 × 3 filter after the final 4…”

Section: Related Workmentioning

confidence: 99%

A Novel Context Aware Joint Segmentation and Classification Framework for Glaucoma Detection

Ganesh

Kannayeram

Karthick

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Glaucoma is a chronic ocular disease characterized by damage to the optic nerve resulting in progressive and irreversible visual loss. Early detection and timely clinical interventions are critical in improving glaucoma-related outcomes. As a typical and complicated ocular disease, glaucoma detection presents a unique challenge due to its insidious onset and high intra- and interpatient variabilities. Recent studies have demonstrated that robust glaucoma detection systems can be realized with deep learning approaches. The optic disc (OD) is the most commonly studied retinal structure for screening and diagnosing glaucoma. This paper proposes a novel context aware deep learning framework called GD-YNet, for OD segmentation and glaucoma detection. It leverages the potential of aggregated transformations and the simplicity of the YNet architecture in context aware OD segmentation and binary classification for glaucoma detection. Trained with the RIGA and RIMOne-V2 datasets, this model achieves glaucoma detection accuracies of 99.72%, 98.02%, 99.50%, and 99.41% with the ACRIMA, Drishti-gs, REFUGE, and RIMOne-V1 datasets. Further, the proposed model can be extended to a multiclass segmentation and classification model for glaucoma staging and severity assessment.

show abstract

Blood vessel detection using enhanced DeepJoint fuzzy clustering algorithm with deep Maxout network for glaucoma detection

Rajeswari¹,

Prabhakar

Padmapriya

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

Glaucoma became a leading reason for losing vision as it progresses in a gradual manner without any symptoms. The discovery of glaucoma at an earlier phase is imperative as it can help to accelerate the progress. The fundus images are an option for screening glaucoma and help to enable the observation of optic disc. The classical techniques are less accurate and time-consuming. In this way, a highly accurate automatic glaucoma diagnosis is developed in this research. The noise in the images is eliminated during pre-processing. Additionally, the DeepJoint model and improved fuzzy clustering technique are combined to develop the proposed Enhanced DeepJoint fuzzy clustering algorithm, which is used to segment blood vessels. The optic disc is additionally divided using black hole entropic fuzzy clustering (BHEFC). In order to identify glaucoma, the acquired segments are fed into a deep Maxout network that has been trained using the multi-verse water rider optimization (MVRWO) algorithm. By combining the rider optimization algorithm, multi-verse optimizer, and water wave optimization (WWO), the MVRWO is produced (ROA). The developed model has the greatest accuracy, sensitivity, and specificity scores, coming in at 93.91%, 95.61%, and 92.57% respectively.

show abstract

Automatic segmentation of optic disc in retinal fundus images using semi-supervised deep learning

Cited by 28 publications

References 57 publications

Machine Learning (ML) in Medicine: Review, Applications, and Challenges

Machine Learning (ML) in Medicine: Review, Applications, and Challenges

A Novel Context Aware Joint Segmentation and Classification Framework for Glaucoma Detection

Blood vessel detection using enhanced DeepJoint fuzzy clustering algorithm with deep Maxout network for glaucoma detection

Contact Info

Product

Resources

About