Automated detection of fovea in fundus images based on vessel-free zone and adaptive Gaussian template

Kao, E-Fong; Lin, Pi-Chen; Chou, Ming-Dah; Jaw, Twei-Shiun; Liu, Gin-Chung

doi:10.1016/j.cmpb.2014.08.003

Cited by 32 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, the approaches utilized for OD segmentation are based on level set (Yu et al, 2012), thresholding (Marin et al, 2015), active contour (Mary et al, 2015) and shape modeling (Cheng et al, 2015), clustering (Thakur and Juneja, 2017), and hybrid (Bai et al, 2014) approaches. Similarly, the fovea is detected mostly using the geometric relationship with OD and vessels through morphological (Welfer et al, 2011), thresholding (Gegundez-Arias et al, 2013), template (Kao et al, 2014) and intensity profile analysis (Kamble et al, 2017) techniques. Poor performance on detection of the normal anatomical structures could adversely affect lesion detection and screening accuracy.…”

Section: Non-deep Learning Methodsmentioning

confidence: 99%

IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

Porwal

Pachade

Kokare³

et al. 2020

Medical Image Analysis

214

113

View full text Add to dashboard Cite

challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top performing participating solutions. We observe that the top performing approaches utilize a blend of clinical information, data augmentation, and the ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

show abstract

Section: Non-deep Learning Methodsmentioning

confidence: 99%

IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

Porwal

Pachade

Kokare³

et al. 2020

Medical Image Analysis

214

113

View full text Add to dashboard Cite

show abstract

“…Therefore, the H-max transform is carried out on the reconstructed image to eliminate all the connected peaks and retrieve a group of OD candidate regions as shown in Figure 5(c) . Finally, the maximum coefficient criterion is used to obtain the gravity center of the OD region [ 31 ], which is shown in Figure 5(d) . In order to detect the OD region more accurately, a square region with a size of 400 × 400 is extracted according to the gravity center of OD, as shown in Figure 5(e) .…”

Section: The Proposed Methodsmentioning

confidence: 99%

Fully Convolutional Network and Visual Saliency-Based Automatic Optic Disc Detection in Retinal Fundus Images

Wang

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

We present in this paper a novel optic disc detection method based on a fully convolutional network and visual saliency in retinal fundus images. Firstly, we employ the morphological reconstruction-based object detection method to locate the optic disc region roughly. According to the location result, a 400 × 400 image patch that covers the whole optic disc is obtained by cropping the original retinal fundus image. Secondly, the Simple Linear Iterative Cluster approach is utilized to segment such an image patch into many smaller superpixels. Thirdly, each superpixel is assigned a uniform initial saliency value according to the background prior information based on the assumption that the superpixels located on the boundary of the image belong to the background. Meanwhile, we use a pretrained fully convolutional network to extract the deep features from different layers of the network and design the strategy to represent each superpixel by the deep features. Finally, both the background prior information and the deep features are integrated into the single-layer cellular automata framework to gain the accurate optic disc detection result. We utilize the DRISHTI-GS dataset and RIM-ONE r3 dataset to evaluate the performance of our method. The experimental results demonstrate that the proposed method can overcome the influence of intensity inhomogeneity, weak contrast, and the complex surroundings of the optic disc effectively and has superior performance in terms of accuracy and robustness.

show abstract

“…Successful optic disc center localization is considered to be that the distance between the estimated optic disc center and the manually selected center is less than the optic disc radius [41,42]. Compared with the state-of-the-art OD detection approaches, our approach is more robust to the image quality, contrast, brightness, and different lesions.…”

Section: Our Approachmentioning

confidence: 99%

Unsupervised Anomaly Detection for Glaucoma Diagnosis

Zhou

Yuan²,

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the rapid development of high tech, Internet of Things (IoT) and artificial intelligence (AI) achieve a series of achievements in the healthcare industry. Among them, automatic glaucoma diagnosis is one of them. Glaucoma is second leading cause of blindness in the world. Although many automatic glaucoma diagnosis approaches have been proposed, they still face the following two challenges. First, the data acquisition of diseased images is extremely expensive, especially for disease with low occurrence, leading to the class imbalance. Second, large-scale labeled data are hard to obtain in medical image domain. The aforementioned challenges limit the practical application of these approaches in glaucoma diagnosis. To address these disadvantages, this paper proposes an unsupervised anomaly detection framework based on sparse principal component analysis (SPCA) for glaucoma diagnosis. In the proposed approach, we just employ the one-class normal (nonglaucoma) images for training, so the class imbalance problem can be avoided. Then, to distinguish the glaucoma (abnormal) images from the normal images, a feature set consisting of segmentation-based features and image-based features is extracted, which can capture the shape and textural changes. Next, SPCA is adopted to select the effective features from the feature set. Finally, with the usage of the extracted effective features, glaucoma diagnosis can be automatically accomplished via introducing the T 2 statistic and the control limit, overcoming the issue of insufficient labeled samples. Extensive experiments are carried out on the two public databases, and the experimental results verify the effectiveness of the proposed approach.

show abstract

Automated detection of fovea in fundus images based on vessel-free zone and adaptive Gaussian template

Cited by 32 publications

References 11 publications

IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

Fully Convolutional Network and Visual Saliency-Based Automatic Optic Disc Detection in Retinal Fundus Images

Unsupervised Anomaly Detection for Glaucoma Diagnosis

Contact Info

Product

Resources

About