A novel automatic segmentation of healthy and diseased retinal layers from OCT scans

Tanboly, A. El; Ismail, Marwa; Switala, Andrew E.; Mahmoud, Mohammad; Soliman, Ahmed; Neyer, Thomas; Palacio, Agustina; Hadayer, Amir; El–Azab, M. S.; Schaal, Shlomit; El-Baz, Ayman

doi:10.1109/icip.2016.7532330

Cited by 16 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The review indicates many types of preprocessing techniques: dilation and erosion [5], median filter [27,107,111], gaussian filter [11,100,101], wiener filter [11,81,99], binary image [26,100], gradient image [26,114], anisotropic difusion filter [5,97,99], image aligment [19,98,103], attenuation coefficient [101], enhanced contrast [1,105], image flattenig [106,114], resize the image [1,107], edge flow [112], sparse filter [112], normalization [81], green channel [81], greyscale [1], morphological operations [1] and others. In Figure 2 is shown the improvements of preprocessing applied to OCT image.…”

Section: Preprocessingmentioning

confidence: 99%

“…Other techniques are: multi-scale spatial pyramid (MSSP), it captures the geometry of retina at multiple scales [19]; geodesic distance method (GDM), it can locate pixels in boundaries of layers [43]; convolutional neural network (CNN), it is pooling, which is a non-linear down-sampling [28,108,120]; dynamic programming (DP), it is a method that divide problems and solves each one separately [65,100,102]; canny edge detection, it is an algorithm that detects edges [97,99,104]; markov gibbs random field (MGRF), it allows to derive a global texture description by specifying local properties of textures [98]; loosely coupled level sets (LCLS), it is a technique that uses local intensity variations to segment layers [101]; structure tensor, it utilizes the gradient of a point with neighborhood to get directions of segmentation [102,104]; Randon Forest (RF), that train the data to estimate boundary probabilities [111,121,122]; and OTSU algorithm, it is used to perform automatic image thresholding [102,107,112]. In Figure 3 is shown an example of segmentation approach applied to an OCT image, in which the top boundary of the ILM and RPE layers are highlighted.…”

Section: Segmentationmentioning

confidence: 99%

“…The results in % were: accuracy of 88.72 ± 0.84, recall of 91.21 ± 0.53 and precision of 92.83 ± 0.74. [98] sugested the segmentation of the largest number of retinal layers, twelve, considering healthy and deseased subjects. The methods used were LCDG and MGRF.…”

Section: Selected Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Segmentation of Macular Holes in Optical Coherence Tomography Images: A review

Mendes¹,

Lucena²,

Lucena³

et al. 2020

AIS

View full text Add to dashboard Cite

Macular holes are a blinding condition that occur due to overuse of the fovea, in which a hole alters the natural retinal structure. Optical Coherence Tomography (OCT) is a way of mapping and shaping retinal sections without physical contact and has become a powerful tool for diagnosing pathologies. This paper deals with a review of automated segmentation of macular holes in OCT images, detailing its varied possibilities. It may be considered something new, no reviews were made about the topic. The purpose of this review is to show the latest trends, through the approaches in preprocessing and segmentation. Recent studies were used to validate the research, 2011 onwards, from the Science Direct, IEEE, PubMed and Google scholar bases. The objectives, methodology, tools, database, advantages, disadvantages, validation metrics and results of the selected material are analyzed and mentioned. Based on this, techniques and their results are compared. From this, future outlook scenarios of automated segmentation of macular holes in OCT images are mentioned.

show abstract

Section: Preprocessingmentioning

confidence: 99%

Section: Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Segmentation of Macular Holes in Optical Coherence Tomography Images: A review

Mendes¹,

Lucena²,

Lucena³

et al. 2020

AIS

View full text Add to dashboard Cite

show abstract

“…The proposed system is composed of a preprocessing stage where appropriate 79 sized patches are detected and extracted, a CNN training stage, and finally investigation 80 of various fusion or combination schema for improved performance of the proposed 81 system. The preprocessing stage starts with segmentation of the original OCT scan into 82 twelve different layers with the application of an unsupervised parametric mixture model 83 and Markov Gibbs Random Fields [31]. The location of the fovea is also simultaneously 84 detected.…”

mentioning

confidence: 99%

“…When computing these distances, it is important to correct for the 146 non-square pixel aspect ratio of typical OCT scanners. The preprocessing algorithm is 147 described in detail in [31]. Finally, it is noteworthy to mention that each of the 148 grayscale images was concatenated as three different channels for the required 3-channel 149 input of the AlexNet.…”

mentioning

confidence: 99%

Accurate detection of non-proliferative diabetic retinopathy in optical coherence tomography images using convolutional neural networks

Ghazal

Ali

Mahmoud

et al. 2019

Preprint

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a disease that forms as a complication of diabetes, It is particularly dangerous since it often goes unnoticed and can lead to blindness if not detected early. Despite the clear importance and urgency of such an illness, there is no precise system for the early detection of DR so far. Fortunately, such system could be achieved using deep learning including convolutional neural networks (CNNs), which gained momentum in the field of medical imaging due to its capability of being effectively integrated into various systems in a manner that significantly improves the performance. This paper proposes a computer aided diagnostic (CAD) system for the early detection of non-proliferative DR (NPDR) using CNNs. The proposed system is developed for the optical coherence tomography (OCT) imaging modality. Throughout this paper, all aspects of deployment of the proposed system are studied starting from the preprocessing stage required to extract input data to train the CNN without resizing the image, to the use of transfer learning principals and how best to combine features in order to optimize performance. A novel patch extraction framework for preprocessing is presented, followed by fovea detection algorithm, in addition to investigating the various CNN parameters for optimal deployment. Optimum CNN parameters and promising results are achieved. To the best of our knowledge, this is the first CNN-based DR early detection CAD system for OCT images. It achieves a promising accuracy of 94% with transfer learning. 4 recently emerged in the medical field, there is a continuous flux of interest in the 5 development of such systems due to their capability of improving the medical services 6 provided to the community in terms of accuracy and reliability in the diagnosis of 7 diseases. Meanwhile, machine learning is paving the way for breakthroughs in the 8 PLOS1/14 different areas of medical imaging such as in classification [1], segmentation [2], disease 9 detection [3], and image registration [4]. The application of deep learning, a subset of 10 machine learning algorithms, has made tremendous impact in the area of medical image 11 processing research [5, 6]. Deep learning is the latest emerging machine learning lead 12 technology in computer vision and image processing domains, particularly convolutional 13 neural networks (CNNs) [7]. They are especially powerful in solving problems that are 14 computationally difficult or with a high error rate such as medical image recognition 15with outstanding performance results [8]. For this reason, we got inspired to use CNNs 16 for the early detection of one of the most serious ophthalmological problems, which is 17 the diabetic retinopathy (DR). 18Blindness resulting from diabetes is turning to be an increasingly alarming issue, 19 which is due to the associated eye disease: DR. Such disease which develops as a 20 complication of diabetes, particularly type II [9, 10] occurs specifically from the chronic 21 high levels of sugar in the blood associated with ...

show abstract

Comparative Analysis of the Fuzzy C-Means and Neuro-Fuzzy Systems for Detecting Retinal Disease

Kumar¹,

Kumutha²

2019

Circuits Syst Signal Process

View full text Add to dashboard Cite

A novel automatic segmentation of healthy and diseased retinal layers from OCT scans

Cited by 16 publications

References 23 publications

Automatic Segmentation of Macular Holes in Optical Coherence Tomography Images: A review

Automatic Segmentation of Macular Holes in Optical Coherence Tomography Images: A review

Accurate detection of non-proliferative diabetic retinopathy in optical coherence tomography images using convolutional neural networks

Comparative Analysis of the Fuzzy C-Means and Neuro-Fuzzy Systems for Detecting Retinal Disease

Contact Info

Product

Resources

About