Approximating Sparse Semi-nonnegative Matrix Factorization for X-Ray Covid-19 Image Classification

ABSTRACT

Medical imaging has been intensively used to help the radiologists do the correct diagnosis for the COVID-19 disease. In particular, chest X-ray imaging is one of the prevalent information sources for COVID-19 diagnosis. The obtained images can be viewed as numerical data and processed by non-negative matrix factorization (NMF) algorithms, one of the available numerical data analysis tools. In this work, we propose a new sparse semi-NMF algorithm that can classify the patients into COVID-19 and normal patients, based on chest X-ray images. We show that the huge volume of data resulting from X-ray images can be significantly reduced without significant loss of classification accuracy. Then, we evaluate our algorithm by carrying out an experiment on a publicly available dataset, having a known chest X-ray image bi-partition. Experimental results demonstrate that the proposed sparse semi-NMF algorithm can predict COVID-19 patients with high accuracy,compared to state-of-the-art algorithms.