LUNG CANCER DETECTION USING U-NET MODEL AND INTEGRATION OF CONVOLUTIONAL AND RECURRENT NEURAL NETWORK

Abstract

With a high death rate, lung cancer is one of the most serious and widespread illnesses, presenting a serious public health concern. In this sense, a fully automated diagnosis technique for lung tumor identification is achieved by appropriately segmenting lung tumors utilizing Computed Tomography (CT) scans, Magnetic Resonance Imaging (MRI), and X-rays. As technology develops and data becomes more accessible, radiologists might employ computer tools for tumor segmentation to save valuable time. This work's main goal is to use the U-Net model and the combination of convolutional and recurrent neural networks to detect lung tumor segmentation from CT scans. We used the 260-patient LUNA 16 dataset to train and assess our model. With this proposed approach, we establish a deep.