An Exploratory Analysis of Deep Learning Models for Detection of Lung Cancer in Medical Images

Lung cancer remains a significant global health concern, and advancements in early detection methodologies are required. This paper conducts a detailed investigation and comparative analysis of four models in deep learning (Extreme Learning Machine (ELM), VGG16, ResNet50, and VGG19) applied to the important task of detecting lung cancer from medical images. The goal of the project is to gain nuanced insights into the trade-offs between model complexity, computing resources, and performance of these models in detection of lung cancer. These findings are intended to guide clinicians and medical researchers in choosing the top deep learning model for a specific clinical application. Our study focuses on key performance metrics such as training and inference time, number of parameters, and model accuracy and uses a diverse dataset of medical images, including lung scans.