Detection and Classification of Lung Carcinoma using CT scans

Abstract

Lung carcinoma, generally known as lung cancer, is the most common cause of cancer which is related to mortality worldwide. Lung carcinoma is an extremely complex problem to solve and Lung cancer patients appear to be the most vulnerable to SARS-CoOVID-19 infection early discovery, on the other hand, has a high rate of survivability. Lung carcinoma detection in computed tomography (CT) has emerged as an emerging research subject in the field of medical imaging systems in recent years. The ability to accurately detect the size and location of lung cancer plays a critical role in lung cancer diagnosis. As a result, there is a requirement to rapidly read, detect, classify and evaluate CT scans. In this paper, we suggest a method for detecting and classifying lung nodules (or lesions) using a multi-strategy system. It has two parts: nodule detection (finding nodules) and classification (classifying nodules into Benign / non-cancerous or Malignant / cancerous). Lung CT scan images are utilized to detect and classify lung nodules in this work. U-Net architecture is used to segment CT scans, while VGG Net is tested on 3D images derived from LUNA 16 and LIDC - IDRI. The U-Net and the VGG-Net results are combined in the final findings.

Supervised learning techniques for detection of Lung Carcinoma

“…There several publications made on detection of early stages in cancer [5] [6]. Typically, a lung disease can be detected by performing test on skin, blood test [7], sputum test, chest X-rays technique [3], or Computer Tomography (CT) scan [8][9] [10] . Chest XRAY is usually the first examination carried for supposed lung cancer detection.…”