Ensemble Deep Learning Approaches for Liver Tumor Detection and Prediction

Cancer is a fatal illness with several underlying causes in metabolism and genetics. Liver cancer ranks as the third leading cause of cancer-related mortality globally and the sixth most prevalent illness in terms of total incidence. The liver plays a pivotal part in the physiological functioning of the human body. The liver controls cholesterol homeostasis and stores fat-soluble vitamins. Liver cancer may be treated more effectively if detected and classified early on. Brain, breast, liver, and other tumors may be examined using CT and MRI, two types of imaging technology. Convolutional neural networks (CNNs) have improved medical imaging for identifying and classifying cancer compared to earlier methods. To help radiologists notice anomalies more quickly, this research presents a classification model for recognizing liver tumors utilizing a convolutional neural network (CNN), an enhanced optimization technique, and transfer learning. The MPA (algorithm for detecting marine predators) was the basis for our optimization strategy. Using an improved version of the marine predator's algorithm (IMPA), developed as part of this project, I was able to identify the ideal values for the CNN's meta parameters. The proposed method combines a version of the ResNet50 CNN model that has already been trained with the IMPA algorithm to create the IMPA-ResNet50 architecture. This IMPA offers superior precision than competing optimization techniques accuracy is 99.20%. IMPA modifies the primary discovery and exploitation procedures to zero down on the most relevant features for reliable categorization.