Diverse lesion detection from retinal images by subspace learning over normal samples

Chen, Benzhi; Wang, Lisheng; Sun, Jian; Chen, Huai; Fu, Yinghua; Lan, Shouren; Huang, Yalin; Zhao, Xu

doi:10.1016/j.neucom.2018.03.023

Cited by 11 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The global prevalence of diabetes is projected to increase from 2.8% in 2000 to 4.4% by 2030, leading to a significant increase in the number of individuals affected, from 171 million to 366 million. Timely identification and immediate intervention are crucial in averting visual impairment in this progressive ocular condition [4].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Feature Selection and Extraction using Metaheuristic Technique for Diabetic Retinopathy

Anamika Raj

2024

jes

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is associated with diabetes, which causes harm to the retina as a result of persistent elevated blood sugar levels, resulting in symptoms such as impaired vision. Regular eye examinations are crucial for the timely identification of any issues. The process of selecting characteristics in DR involves optimizing important features using a combination of Hybridized Weight-Optimized Particle Swarm Optimization and Whale Optimization Algorithm (HWOPSO-WOA). This leads to an enhancement in the accuracy of detection, which is crucial for appropriate diagnosis and therapy. Pre-processing encompasses the utilization of linear filters such as Sobel and Prewitt for image manipulation, mean filters for the reduction of noise, and Gaussian filters for the purpose of smoothing. Feature selection employs an objective function that considers significant performance measure, which utilizes binary encoding and conducts fitness evaluation. The methodology is utilized for the analysis of DR utilizing the Indian Diabetic Retinopathy Image Dataset. The results comprise convergence graphs, and a comparative analysis, which emphasize the greater accuracy and efficiency of the Proposed technique. Visual representations, such as fundus images with selected features, highlight the importance of the chosen features in detecting DR. The proposed HWOPSO-WOA achieves highest accuracy of 97.3% and minimal processing time 98.45seconds that outperforms the state-of-art techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

An Efficient Feature Selection and Extraction using Metaheuristic Technique for Diabetic Retinopathy

Anamika Raj

2024

jes

View full text Add to dashboard Cite

show abstract

“…The pixel-by-pixel comparison is usually sensitive to illumination variations in the image and strongly dependent on the normalization of illumination. Background learning and modelling has attracted much attention 4 , 11 – 13 , which is widely used to detect video sequence anomalies from the beginning. The change regions are modelled as the foreground objects and obtained through subtracting the learned background from the current frames 14 , 15 .…”

Section: Introductionmentioning

confidence: 99%

Change detection based on unsupervised sparse representation for fundus image pair

Zhao

Liang

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Detecting changes is an important issue for ophthalmology to compare longitudinal fundus images at different stages and obtain change regions. Illumination variations bring distractions on the change regions by the pixel-by-pixel comparison. In this paper, a new unsupervised change detection method based on sparse representation classification (SRC) is proposed for the fundus image pair. First, the local neighborhood patches are extracted from the reference image to build a dictionary of the local background. Then the current image patch is represented sparsely and its background is reconstructed by the obtained dictionary. Finally, change regions are given through background subtracting. The SRC method can correct automatically illumination variations through the representation coefficients and filter local contrast and global intensity effectively. In experiments of this paper, the AUC and mAP values of SRC method are 0.9858 and 0.8647 respectively for the image pair with small lesions; the AUC and mAP values of the fusion method of IRHSF and SRC are 0.9892 and 0.9692 separately for the image pair with the big change region. Experiments show that the proposed method in this paper is more robust than RPCA for the illumination variations and can detect change regions more effectively than pixel-wised image differencing.

show abstract

“…SVDD [5] attempts to learn a kernel function, where the given class samples can be mapped into a hypersphere, and samples belonging to the other classes will be mapped out of it. Some work also applies these methods to clinical imaging analysis [7][8][9]. These methods obtain remarkable performance for small-scale datasets because the kernel function can map samples into a separable higher dimensional feature space effectively, but they usually suffer from the "curse of dimensionality" [10].…”

Section: Introductionmentioning

confidence: 99%

Constrained Deep One-Class Feature Learning For Classifying Imbalanced Medical Images

Gao¹,

Liu²,

Arefan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Purpose: Medical image data are usually imbalanced across different classes. One-class classification has attracted increasing attention to address the data imbalance problem by distinguishing the samples of the minority class from the majority class. Previous methods generally aim to either learn a new feature space to map training samples together or to fit training samples by autoencoder-like models. These methods mainly focus on capturing either compact or descriptive features, where the information of the samples of a given one class is not sufficiently utilized. Approach: In this paper, we propose a novel deep learning-based method to learn compact features by adding constraints on the bottleneck features, and to preserve descriptive features by training an autoencoder at the same time. Through jointly optimizing the constraining loss and the autoencoder's reconstruction loss, our method can learn more relevant features associated with the given class, making the majority and minority samples more distinguishable. Results: Experimental results on three clinical datasets (including the MRI breast images, FFDM breast images and chest X-ray images) obtains state-of-art performance compared to previous methods. Conclusions: We propose a novel method to address the data imbalance problem. The proposed method can learn a more compact and descriptive feature space for the one class classification task.

show abstract

Diverse lesion detection from retinal images by subspace learning over normal samples

Cited by 11 publications

References 33 publications

An Efficient Feature Selection and Extraction using Metaheuristic Technique for Diabetic Retinopathy

An Efficient Feature Selection and Extraction using Metaheuristic Technique for Diabetic Retinopathy

Change detection based on unsupervised sparse representation for fundus image pair

Constrained Deep One-Class Feature Learning For Classifying Imbalanced Medical Images

Contact Info

Product

Resources

About