Lung Cancer Detection with Prediction Employing Machine Learning Algorithms: A Recent Study | Chapter 9 | New Approaches in Engineering Research Vol. 14

Lung cancer claims the lives of more people every year around the world. It is the second most common cancer in the world's population. The capacity to predict when a patient may develop cancer can help clinicians make pharmacological and therapy selections. This research proposes a new method for detecting and predicting the presence of malignant nodules in patients' lungs. The proposed method employs a machine learning approach known as support vector machine (SVM), a deep learning algorithm known as convolutional neural network (CNN), and a large lung cancer repository database known as the UCI repository to conduct the classification. In the first step of cleaning, images are pre-processed and then post-processed. The RGB to greyscale conversion is incorporated in the pre-processing step, and noise is reduced in the post-processing step using the Non-Local Means (NLM) filter. In the second stage of development, Otsu's approach was used to segment images, and Grey Level Co-occurrence Matrix was used to extract features (GLCM). Finally, the two classifiers are employed to categorise lung malignant pictures, and their classification accuracy is compared and recorded.

Author (S) Details

S. J. Krishna Prasad
Department of Electronics and Telecommunication, Ramaiah Institute of Technology, Bangalore, India.

Aneesha Johnson
Department of Electronics and Telecommunication, Ramaiah Institute of Technology, Bangalore, India.

S. Mohana Kumar
Department of Computer Science, Ramaiah Institute of Technology, Bangalore, India.

View Book:-  https://stm.bookpi.org/NAER-V14/article/view/3528