Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images
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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/10/1/6 |
| id |
doaj-bf18174ddf754c168ada30568a76ae1c |
|---|---|
| record_format |
Article |
| spelling |
doaj-bf18174ddf754c168ada30568a76ae1c2020-12-28T00:00:31ZengMDPI AGComputers2073-431X2021-12-01106610.3390/computers10010006Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical ImagesHassen Sallay0Sami Bourouis1Nizar Bouguila2College of Computer and Information Systems, Umm AlQura University, P.O. Box 715, Makkah 24382, Saudi ArabiaDepartment of Information Technology, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi ArabiaThe Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, QC H3G 1T7, CanadaThe 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.https://www.mdpi.com/2073-431X/10/1/6Gamma distributionmachine learningfinite and infinite mixture modelsvariational inferenceonline learningdiagnoses and biomedical applications |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Hassen Sallay Sami Bourouis Nizar Bouguila |
| spellingShingle |
Hassen Sallay Sami Bourouis Nizar Bouguila Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images Computers Gamma distribution machine learning finite and infinite mixture models variational inference online learning diagnoses and biomedical applications |
| author_facet |
Hassen Sallay Sami Bourouis Nizar Bouguila |
| author_sort |
Hassen Sallay |
| title |
Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images |
| title_short |
Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images |
| title_full |
Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images |
| title_fullStr |
Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images |
| title_full_unstemmed |
Online Learning of Finite and Infinite Gamma Mixture Models for COVID-19 Detection in Medical Images |
| title_sort |
online learning of finite and infinite gamma mixture models for covid-19 detection in medical images |
| publisher |
MDPI AG |
| series |
Computers |
| issn |
2073-431X |
| publishDate |
2021-12-01 |
| description |
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. |
| topic |
Gamma distribution machine learning finite and infinite mixture models variational inference online learning diagnoses and biomedical applications |
| url |
https://www.mdpi.com/2073-431X/10/1/6 |
| work_keys_str_mv |
AT hassensallay onlinelearningoffiniteandinfinitegammamixturemodelsforcovid19detectioninmedicalimages AT samibourouis onlinelearningoffiniteandinfinitegammamixturemodelsforcovid19detectioninmedicalimages AT nizarbouguila onlinelearningoffiniteandinfinitegammamixturemodelsforcovid19detectioninmedicalimages |
| _version_ |
1724369087569592320 |