The Optimisation of Thresholding Techniques for the Identification of Choroidal Neovascular Membranes in Exudative Age-Related Macular Degeneration

Brankin, E.; McCuIlagh, P.; Black, ND; Patton, W. P.; Muldrew, Alyson

doi:10.1109/cbms.2006.157

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Berger and Yoken 17 applied the same technique for CNV segmentation on two semiautomatically registered image frames for study of changes in CNV area and integrated lesion intensity measurements among visits. Brankin et al 19 applied a similar segmentation technique for delineation of CNV, but the operation was performed on only one angiographic image frame without any support of temporal information. The same research group later proposed a system for segmenting hyperfluorescent regions with the combination of manual initialization and automatic refinement using also one image frame.…”

Section: Discussionmentioning

confidence: 99%

Automatic Characterization of Classic Choroidal Neovascularization by Using AdaBoost for Supervised Learning

Tsai

Yang

Chen

et al. 2011

Invest. Ophthalmol. Vis. Sci.

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Characterization of Classic Choroidal Neovascularization by Using AdaBoost for Supervised Learning

Tsai

Yang

Chen

et al. 2011

Invest. Ophthalmol. Vis. Sci.

View full text Add to dashboard Cite

show abstract

“…where ℎ is the threshold level, $ is the radon space and (%, &)are the radon value indexes. We noted that the optimal threshold is adopted experimentally to 0.9, where the drusens having peaks greater than ℎ were examined, as proceeded in previous research [63]. This experimental approach allowed us to deduce that if such threshold is applied with a value below 0.9, some noise peaks or light leakage of the smartphone capture some noises has been identified as lesions.…”

Section: Intensity Growth: Dynamic Threshold Based Intensity Ratementioning

confidence: 99%

“…Thus, a full appreciable gap between the and values is produced, as presented in Fig 9b and Fig. 10d.The idea is to deduce, the drusens presence based upon the image background, as proceeded in [63,64]. To achieve this aim , we proceed to compute the ratio intensity growth feature #$ % #& between the average of peaks and the average of the radon space , as highlighted in Eq.…”

Section: Intensity Growth: Dynamic Threshold Based Intensity Ratementioning

confidence: 99%

Automated method for real-time AMD screening of fundus images dedicated for mobile devices

Sayadia

Elloumi

Kachouri

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

Aged Macular Degeneration (AMD) leads to a progressive decline in visual acuity until reaching blindness. It is considered as an irreversible pathology where an early diagnosis remains crucial. However, the lack of ophthalmologists, the permanent increase in elderly people and their limited mobility involves a delay in AMD diagnosis.In this paper, we propose an automated method for AMD screening. The proposed processing pipeline consists in applying the well-known radon transform to the macula region in order to model the AMD lesions even with a moderate quality of smartphone captured fundus images. Thereby, the relevant features are carefully selected, related to the main proprieties of drusens, and then provided to an SVM classifier. The implementation of the method into a smartphone associated to a fundus image capturing device leads to a mobile CAD system that performs higher performance AMD screening. Within this framework and, to achieve a real time implementation, an optimization approach is suggested in order to reduce the processing workload.The evaluation of our method is carried out through the three public STARE, REFUGE and RFMID databases. A 4-fold cross validation approach is used to evaluate the method performance where accuracies of 100%, 95.2%, 94.3% are respectively obtained with STARE, REFUGE and RFMID databases. Comparisons with the state-of-the-art methods in the literature are done. Thereafter, the robustness of the proposed method was evaluated and proved. We note that 100% accuracy was preserved despite the use of degraded quality fundus images as noisy and blurred. Moreover, the propounded method was implemented in S7-Edge and S9 Smartphone devices, where the execution times of 19 and 15 milliseconds were respectively achieved, which proves the AMD real time detection.Taking advantage of its mobility, cost-effective, detection performance and reduced execution time, our proposed method seems a good solution for real time AMD screening on mobile devices.

show abstract

“…Lesions were detected from low contrast, digital images with non-dilated pupils by Fuzzy C-Means (FCM) clustering [3]. The Sobel edge detector is combined with threshold to produce best qualitative segmentation for detecting choroidal neovascularization from retinal fluorescein angiograms in exudative age-related macular degeneration [4]. The motion pattern technique is introduced to detect abnormalities in macula.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Severity Level for Diabetic Macular Oedema Using Machine Learning Algorithms

Murugeswari¹,

Sukanesh²

2016

View full text Add to dashboard Cite

The macula is an imperative part present in our human visual system which is most responsible for clear and colour vision. For the people suffering from diabetes, the various parts of the body including the retina of the eye are affected. These retinal damages cause swelling and other abnormalities nearby macula. The pathologies in macula due to diabetes are called Diabetic Macular oEdema (DME). It affects patients' vision that may lead to vision loss. It can be overcome by advance identification of causes for swelling. The major causes for the swelling are neovascularization and other abnormalities occurring in the blood vessels nearby the macula. The aim of this work is to avoid vision loss by detecting the presence of abnormalities in macula in advance. The pathologies present in the abnormal images are detected by image segmentation technique viz. Fuzzy K-means algorithm. The classification is done by two different classifiers namely Cascade Neural Network and Partial Least Square which are employed to identify whether the image is normal or abnormal. The results of both the classifiers are compared with respect to classifier accuracy, sensitivity and specificity. The classifier accuracies of Cascade Neural Network and Partial Least Square are 96.84% and 94.36%, respectively. The information about the severity of the disease and the localization of pathologies are very useful to the ophthalmologist for diagnosing the disease and apply proper treatments to the patients to avoid the formation of any lesion and prevent vision loss.

show abstract

The Optimisation of Thresholding Techniques for the Identification of Choroidal Neovascular Membranes in Exudative Age-Related Macular Degeneration

Cited by 7 publications

References 13 publications

Automatic Characterization of Classic Choroidal Neovascularization by Using AdaBoost for Supervised Learning

Automatic Characterization of Classic Choroidal Neovascularization by Using AdaBoost for Supervised Learning

Automated method for real-time AMD screening of fundus images dedicated for mobile devices

Assessment of Severity Level for Diabetic Macular Oedema Using Machine Learning Algorithms

Contact Info

Product

Resources

About