Detection And Classification of Lung Cancer CT Images Using Mask R-CNN Based Generated Mask Method

In the medical field, computer vision systems, and especially image diagnostics, provide a wide range of useful tools. Computed tomography (CT) scans are the gold standard for identifying a wide variety of medical disorders, from bone fractures to lung cancer to heart disease (CT). One of the top four mortality rate disease in the world is lung cancer. The lung areas are divided up for clinical diagnostics after being defined. This study suggests combining supervised and unsupervised machine learning techniques with the CNN and model specialization using R-CNN for lung area mapping to separate the lungs in CT images automatically. Accuracy of 99.21%, sensitivity of 99.33%, and specificity of 98.97% were achieved by our approach to lung tissue classification using a combination of a Mask Region - Convolutional Neural Network (MR-CNN) and a support vector machine. We checked our results against the work of other scientists to be sure we weren't missing anything. Our solution outperformed other state-of-the-art methods in terms of accuracy and speed.