Multiple Ocular Diseases Classification with Graph Regularized Probabilistic Multi-label Learning
نویسندگان
چکیده
Glaucoma, Pathological Myopia (PM), and Age-related Macular Degeneration (AMD) are three leading ocular diseases in the world. In this paper, we proposed a multiple ocular diseases diagnosis approach for above three diseases, with Entropic Graph regularized Probabilistic Multi-label learning (EGPM). The proposed EGPM exploits the correlations among these three diseases, and simultaneously classifying them for a given fundus image. The EGPM scheme contains two concatenating parts: 1) efficient graph construction based on k-Nearest-Neighbor (kNN) search; 2) entropic multi-label learning based on Kullback-Leibler divergence. In addition, to capture the characteristics of these three leading ocular diseases, we explore the extractions of various effective lowlevel features, including Global Features, Grid-based Features, and Bag of Visual Words. Extensive experiments are conducted to validate the proposed EGPM framework on SiMES dataset. The results show area under curve (AUC) of the receiver operating characteristic curve in multiple ocular diseases detection are much better than the state-of-the-art algorithms.
منابع مشابه
Discriminative Feature Selection for Multiple Ocular Diseases Classification by Sparse Induced Graph Regularized Group Lasso
Glaucoma, Pathological Myopia (PM), and Age-related Macular Degeneration (AMD) are three leading ocular diseases worldwide. Visual features extracted from retinal fundus images have been increasingly used for detecting these three diseases. In this paper, we present a discriminative feature selection model based on multi-task learning, which imposes the exclusive group lasso regularization for ...
متن کاملProbabilistic Multi-Label Classification with Sparse Feature Learning
Multi-label classification is a critical problem in many areas of data analysis such as image labeling and text categorization. In this paper we propose a probabilistic multi-label classification model based on novel sparse feature learning. By employing an individual sparsity inducing l1-norm and a group sparsity inducing l2,1-norm, the proposed model has the capacity of capturing both label i...
متن کاملRegularized Structured Output Learning with Partial Labels
We consider the problem of learning structured output probabilistic models with training examples having partial labels. Partial label scenarios arise commonly in web applications such as taxonomy (hierarchical) classification, multi-label classification and information extraction from web pages. For example, label information may be available only at the internal node level (not at the leaf le...
متن کاملMulti-Label Classification with Cutset Networks
In this work, we tackle the problem of Multi-Label Classification (MLC) by using Cutset Networks (CNets), weighted probabilistic model trees, recently proposed as tractable probabilistic models for discrete distributions. We employ CNets to perform Most Probable Explanation (MPE) inference exactly and efficiently and we improve a state-of-the-art structure learning algorithm for CNets by explic...
متن کاملExploiting Associations between Class Labels in Multi-label Classification
Multi-label classification has many applications in the text categorization, biology and medical diagnosis, in which multiple class labels can be assigned to each training instance simultaneously. As it is often the case that there are relationships between the labels, extracting the existing relationships between the labels and taking advantage of them during the training or prediction phases ...
متن کامل