Automatic Intelligent Model for Lung Tumor Detection using Medical Images

The rising mortality toll from tumor is indicative of a growing global health crisis. To put it simply, a tumor is an unnatural proliferation of abnormal cells that invades healthy cells. Lung tumor (LT) cause cellular imbalances that negatively impact lung function. In this era, LT has been and will continue to be the leading cause of mortality owing to tumor. Early LT prediction is crucial, especially in densely populated and low-income nations. Standard clinical techniques, such as blood tests and other medicines, are used by specialists. Using recent advances in Deep Learning (DL), it is possible to build an environmentally friendly prototype system for the prediction of LT. The goal of this study is to use DL to automate the process of detecting LT. Starting with data collecting and ending with model validation, this study's pipeline depicts the steps taken in the research process. Pre-processing steps like reshaping and resizing the data, building a DL model like a Convolutional Neural Network (CNN) and a Combined Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM), training and validating the model comes in between the data collection and model validation stages. The experimental findings indicates that the CNN-LSTM is effective for LT prediction, with accuracy and loss of 98.12% and 1.87%, respectively.