Lung Cancer Diagnosis based on Ultrasound image processing

Abstract

Cancer represents one of the leading causes of mortality in this century. Patients suffering from lung cancer (LC) have an average of 5 years life expectancy after diagnosis. This is due usually to late detection. The most common methods to detect lung cancer are computed tomography (CT) and magnetic resonance imaging (MRI). These investigations are invasive to the human body and are performed only based on a doctor’s recommendation, which comes usually after patients develop symptoms – hence the late detection of cancer. Nowadays transthoracic ultrasonography (TUS) and US-guided biopsy have gained a larger field in the management of patients with peripheral pulmonary nodules or masses. From the multiple ultrasonography (US) advantages which made it a wellestablished solution in the management of tumoral and nontumoral abdominal pathology, few stand out: it’s non-invasive and has reduced costs. However, until now transthoracic US is underused for lung cancer diagnosis because it can be hard to interpret to determine an accurate diagnosis. In this paper we aim to develop a software application for lung mass classification based on ultrasound image processing. This could be an important step in towards early detection of lung cancer, by introducing the transthoracic ultrasonography in the regular annual check-up, improving the life expectancy of patients or even complete recuperation.