Diagnose Colon and Lung Cancer Histopathological Images Using Pre-Trained Machine Learning Model
Ullagadi Maheshwari, Bellam Kiranmayee, Chalumuru Suresh
Abstract
Lung cancers and colon cancers are two of the leading causes of morbidity and mortality in human being. One of the essential elements to determining the type of cancer is the histopathological diagnosis. One of the most hazardous and severe diseases that people experience worldwide is colon and lung cancer, which has spread to become a common medical issue. It is very important to make a reliable and early discovery in order to reduce the danger of death. The difficulty of the task ultimately depends on the histopathologists’ experience. Recent times have seen a rise in the popularity of deep learning, which is now appreciated in the interpretation of medical imaging. As a result, artificial intelligence will soon become a useful technology. In order to identify lung cancers and colon cancer using histopathological pictures and more effective augmentation strategies, this research aims to utilize and modify the current pre-trained Convolutional Neural Network (CNN) based model. From the LC25000 dataset, the results were obtained. Precision, recall, f1score, and accuracy are all used to estimate the model performances. The findings show that the pre-trained and improved pre-trained models produced impressive outcomes ranging from 93% to 97% accuracy.