Oncology relies heavily on the process of tumour detection. The broad computer vision issues of image augmentation, segmentation, and classification are of primary significance in medical imaging. Due to its excellent spatial resolution, quick imaging speed, and widespread availability, computed tomography (CT) is one of the most often utilised imaging modalities for tumour detection and diagnosis in particular. Additionally, the most used imaging method for diagnosing lung tumours is computed tomography (CT). With computed tomography, nodules and diseased remnants of various diameters may be easily seen. There are two types of lung nodules: benign and malignant. Solid and unusual nodules may sometimes be diagnosed as malignant during the diagnostic process. However, a solid lump with calcification is often classified as benign in most circumstances. To expedite therapy, it is critical to detect nodules as soon as possible. As a result, computed tomography's complex and hard duties for lung tumour identification and classification in medical image processing. Additionally, an image enhancement method could increase the precision of the procedures for identifying and classifying tumours. The main goal of this study is to provide an effective system for an automated diagnosis of lung tumours.

Computed Tomography Image, Segmentation, Tomography, Tomography Images and Tumour Detection