Enhanced 3D-OTSU Algorithm for Robust Tuberculosis and COVID-19 CT Scans Segmentation

Alebiosu David Olayemi, Chern Hong Lim, Anuja T. Dharmarathne

Abstract: While tuberculosis (TB) is a deadly disease, the coronavirus (COVID-19) has caused more rapid death since its discovery in 2019. Studies have shown that the recovery rate of COVID-19 patients with TB has been discovered to be extremely low. With this, analyzing lung Computed Tomography (CT) images of patients with TB or COVID-19 disease is a considerable way of assisting in diagnosing and treating. However, previous segmentation methods have challenges segmenting noisy images such as CT scans. This study proposed a novel technique, namely an enhanced 3-dimensional OTSU (E3D-OTSU) algorithm for segmenting TB and COVID-19-infected areas in lung CT images. It is experimentally proven to be efficient on TB and COVID-19 datasets. The evaluation results using dice co-efficient, accuracy, and sensitivity metrics showed that the proposed E3D-OTSU outperformed two previously employed OTSU algorithms on both datasets. Nonetheless, it achieved the highest dice co-efficient values of 97.78% and 98.58% on TB and COVID-19 datasets respectively.