A novel optic disc and optic cup segmentation technique to diagnose glaucoma using deep learning convolutional neural network over retinal fundus images

Veena, H.N.; Muruganandham, A.; Kumaran, T. Senthil

doi:10.1016/j.jksuci.2021.02.003

Cited by 61 publications

(32 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, the interest in DL applications using medical images has been risen [ 25 ]. CNNs has demonstrated superior performance in solving many medical image segmentation problems and achieved satisfactory results for different segmentation tasks include mandible segmentation [ 26 ], sinonasal cavity and pharyngeal airway segmentation [ 27 ], brain segmentation [ 28 ], optic disc segmentation [ 29 ], liver segmentation [ 30 ], lung segmentation [ 31 ], etc. Among all different deep learning models, U-net [ 32 ] was developed for the segmentation of neuron structure in microscopy images.…”

Section: Introductionmentioning

confidence: 99%

Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

2022

View full text Add to dashboard Cite

In the medical sector, three-dimensional (3D) images are commonly used like computed tomography (CT) and magnetic resonance imaging (MRI). The 3D MRI is a non-invasive method of studying the soft-tissue structures in a knee joint for osteoarthritis studies. It can greatly improve the accuracy of segmenting structures such as cartilage, bone marrow lesion, and meniscus by identifying the bone structure first. U-net is a convolutional neural network that was originally designed to segment the biological images with limited training data. The input of the original U-net is a single 2D image and the output is a binary 2D image. In this study, we modified the U-net model to identify the knee bone structures using 3D MRI, which is a sequence of 2D slices. A fully automatic model has been proposed to detect and segment knee bones. The proposed model was trained, tested, and validated using 99 knee MRI cases where each case consists of 160 2D slices for a single knee scan. To evaluate the model’s performance, the similarity, dice coefficient (DICE), and area error metrics were calculated. Separate models were trained using different knee bone components including tibia, femur, patella, as well as a combined model for segmenting all the knee bones. Using the whole MRI sequence (160 slices), the method was able to detect the beginning and ending bone slices first, and then segment the bone structures for all the slices in between. On the testing set, the detection model accomplished 98.79% accuracy and the segmentation model achieved DICE 96.94% and similarity 93.98%. The proposed method outperforms several state-of-the-art methods, i.e., it outperforms U-net by 3.68%, SegNet by 14.45%, and FCN-8 by 2.34%, in terms of DICE score using the same dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

2022

View full text Add to dashboard Cite

show abstract

“…Reference [30] proposed the deep learning enhanced CNN. The rst process was to preprocess the image with the Gaussian lter and image normalization.…”

Section: Review Of Methodsmentioning

confidence: 99%

Segmentation and Classification of Retinal Fundus Images using Convolutional Neural Networks: A systematic review of methods and latest trends

Ilesanmi

Idowu

et al. 2022

Preprint

View full text Add to dashboard Cite

The retina fundus images are critical diagnostic tools for the early detection of ophthalmic problems. Prompt diagnosis and treatment of eye-related problems are important to prevent blindness or vision loss. Recently, CNN algorithms have become effective in tasks relating to recognition, delineation, and classification. Therefore we propose a review to summarize different CNN algorithms for segmenting and classifying retinal fundus images. This review systematically searches different repositories for methods that use CNN for the segmentation and classification of retinal fundus images. A thorough screening of abstracts and titles to ascertain their relevance was done. A total of fifty-two studies were included in our review, with content such as database usage, disadvantages, and advantages. A comparison of two accuracies was also carried out with a graph depicting database usage. Important insights, limitations, observations, and future directions were elucidated. Finally, findings suggest that CNN algorithms produce good accuracies despite their limitations.

show abstract

“…Automated computer analysis, a well-established research topic in medical imaging, is an approach that is entirely reliant on computer algorithms. The automated detection technique usually consists of image pre-processing, feature extraction, feature selection, segmentation, and classification [11]. Significant advances in computing and artificial intelligence (AI) technology, such as machine learning (ML) and deep learning (DL), as well as big data analytics, enable radiologists and ophthalmologists to gain a level of clinical decision support that significantly reduces diagnostic errors.…”

Section: Introductionmentioning

confidence: 99%

Towards a Connected Mobile Cataract Screening System: A Future Approach

et al. 2022

View full text Add to dashboard Cite

Advances in computing and AI technology have promoted the development of connected health systems, indirectly influencing approaches to cataract treatment. In addition, thanks to the development of methods for cataract detection and grading using different imaging modalities, ophthalmologists can make diagnoses with significant objectivity. This paper aims to review the development and limitations of published methods for cataract detection and grading using different imaging modalities. Over the years, the proposed methods have shown significant improvement and reasonable effort towards automated cataract detection and grading systems that utilise various imaging modalities, such as optical coherence tomography (OCT), fundus, and slit-lamp images. However, more robust and fully automated cataract detection and grading systems are still needed. In addition, imaging modalities such as fundus, slit-lamps, and OCT images require medical equipment that is expensive and not portable. Therefore, the use of digital images from a smartphone as the future of cataract screening tools could be a practical and helpful solution for ophthalmologists, especially in rural areas with limited healthcare facilities.

show abstract

A novel optic disc and optic cup segmentation technique to diagnose glaucoma using deep learning convolutional neural network over retinal fundus images

Cited by 61 publications

References 37 publications

Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

Segmentation and Classification of Retinal Fundus Images using Convolutional Neural Networks: A systematic review of methods and latest trends

Towards a Connected Mobile Cataract Screening System: A Future Approach

Contact Info

Product

Resources

About