Lung Nodules Classification Using Convolutional Neural Network with Transfer Learning

Abstract

Healthcare industry plays a vital role in improving daily life. Machine learning and deep neural networks have contributed a lot to benefit various industries nowadays. Agriculture, healthcare, machinery, aviation, management, and even education have all benefited from the development and implementation of machine learning. Deep neural networks provide insight and assistance in improving daily activities. Convolutional neural network (CNN), one of the deep neural network methods, has had a significant impact in the field of computer vision. CNN has long been known for its ability to improve detection and classification in images. With the implementation of deep learning, more deep knowledge can be gathered and help healthcare workers to know more about a patient's disease. Deep neural networks and machine learning are increasingly being used in healthcare. The benefit they provide in terms of improved detection and classification has a positive impact on healthcare. CNNs are widely used in the detection and classification of imaging tasks like CT and MRI scans. Although CNN has advantages in this industry, the algorithm must be trained with a large number of data sets in order to achieve high accuracy and performance. Large medical datasets are always unavailable due to a variety of factors such as ethical concerns, a scarcity of expert explanatory notes and labelled data, and a general scarcity of disease images. In this paper, lung nodules classification using CNN with transfer learning is proposed to help in classifying benign and malignant lung nodules from CT scan images. The objectives of this study are to pre-process lung nodules data, develop a CNN with transfer learning algorithm, and analyse the effectiveness of CNN with transfer learning compared to standard of other methods. According to the findings of this study, CNN with transfer learning outperformed standard CNN without transfer learning.