Abstract
The accurate detection of abnormalities in medical images (like X-ray and CT scans) is a challenging problem due to images’ blurred boundary contours, different sizes, variable shapes, and uneven density. In this paper, we tackle this problem via a new effective online variational learning model for both mixtures of finite and infinite Gamma distributions. The proposed approach takes advantage of the Gamma distribution flexibility, the online learning scalability, and the variational inference efficiency. Three different batch and online learning methods based on robust texture-based feature extraction are proposed. Our work is evaluated and validated on several real challenging data sets for different kinds of pneumonia infection detection. The obtained results are very promising given that we approach the classification problem in an unsupervised manner. They also confirm the superiority of the Gamma mixture model compared to the Gaussian mixture model for medical images’ classification.
Highlights
Among the many existing unsupervised learning methods, mixture models have gained increasing interest and have been exploited with success especially for non-Gaussian data modeling [1,2,3,4,5]
We propose an extension of the finite Gamma mixture model to the infinite multi-dimensional case, which is more effective than the finite model, and we investigate this infinite model for medical image classification
We ran the three learning approaches for the finite. We evaluated their performance in terms of overall accuracy (Acc), detection rate (DR), and false positive rate (FPR)
Summary
Among the many existing unsupervised learning methods, mixture models have gained increasing interest and have been exploited with success especially for non-Gaussian data modeling [1,2,3,4,5]. Given that Gaussian density is not the suitable approximation for complex data modeling like for biomedical images, as stated in [6], other alternatives such as the Gamma distribution perform significantly better than the majority of parametric models [7]. Our work here is motivated by the interesting results obtained with the finite Gamma mixture in the case of data clustering and segmentation. This model has proven to be more competitive than several earlier developed parametric models like the Gaussian model. We propose here to develop three different unsupervised learning methods based on mixtures of the
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
