2021/01/20 by Mustafa Hajij, Hajij, Mustafa, Ghada Zamzmi +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Bioinformatics and Genomic Networks #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Topological and Geometric Data Analysis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2101.08398
openalex publication_date 2021/01/20 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Topological Data Analysis (TDA) has emerged recently as a robust tool to\nextract and compare the structure of datasets. TDA identifies features in data\nsuch as connected components and holes and assigns a quantitative measure to\nthese features. Several studies reported that topological features extracted by\nTDA tools provide unique information about the data, discover new insights, and\ndetermine which feature is more related to the outcome. On the other hand, the\noverwhelming success of deep neural networks in learning patterns and\nrelationships has been proven on a vast array of data applications, images in\nparticular. To capture the characteristics of both powerful tools, we propose\n\TDA-Net, a novel ensemble network that fuses topological and deep\nfeatures for the purpose of enhancing model generalizability and accuracy. We\napply the proposed \TDA-Net to a critical application, which is the\nautomated detection of COVID-19 from CXR images. The experimental results\nshowed that the proposed network achieved excellent performance and suggests\nthe applicability of our method in practice.\n