Lung Cancer Detection using Image Processing

Abstract

One of the common diseases related to cancer which have high rate is lung cancer, which is largely due to the slow capture of the malignant tumor. Again, the commonly used methods for diagnosing lung cancer have several drawbacks. Despite the effectivity of computed tomography of identifying this malignancy, the need for radiologists to process vast amounts of data not only makes their job more difficult but can also delay the detection of lung cancer in time enough for treatment to begin. In this context, computer-aided diagnostic (CAD) systems were developed. A convolutional neural network is one of the ways that can be used to describe an alternate method of applying a set of deep learning algorithms with filtering. These algorithms can be learned by performing local pooling operations on CT images in order to generate a set of hierarchical complicated functions. The convolutional neural network is the method that is considered to be the most effective. In order to properly segment lung nodules, one stage that cannot be skipped while attempting to design a reliable system for detection called for the application of data-driven methodologies. This stage is essential. Lung nodule identification has been effectively achieved using models and variants of convolutional neural networks. Since it has been utilized in the medical sector for some time, the 2D Convolution layer has demonstrated both many strengths and numerous limitations. The 3D model is currently rapidly gaining popularity as it addresses these shortcomings and improves the convolutional neural network’s detection skills. The accuracy and specificity of 3D models were already found to be high for lung nodule detection, implementing a a 3D model for the medical industry can be challenging due to time requirements, training difficulties, and hardware memory requirements. See this study for developments in the use of a 3D CNN model for lung cancer diagnosis.

Topics & Concepts