A Novel Method for Human MRI Based Pancreatic Cancer Prediction Using Integration of Harris Hawks Varients & VGG16: A Deep Learning Approach

Abstract

An extremely malignant tumor of the digestive system is the hallmark of Pancreatic Cancer (PC). Early diagnosis, as well as successful treatment, is difficult to achieve. As the death rate is increasing at a rapid rate (47,050 out of 57650 cases), it is of utmost importance for medical experts to diagnose PC at earlier stages. The application of Deep Learning (DL) techniques in the medical field has revolutionized so much in this era of technological advancement. An analysis of clinical proteomic tumor data provided by the Clinical Proteome Tumor Analysis Consortium Pancreatic Ductal Adenocarcinoma (CPTAC-PDA) at the National Cancer Institute was used to demonstrate an innovative deep learning approach in this study. This includes: a) collection of data b) preprocessed using CLAHE and BADF techniques for noise removal and image enhancement, c) segmentation using UNet++ for segmenting regions of interest of cancer. Once these are segmented, d) feature extraction using HHO based CNN and e) feature selection using HHO based BOVW for extracting and selecting features from the images. Finally, these are subject to the f) classification stage for better analysis using the VGG16 network. Experimental results are carried out using various state-of-art models over various measures in which the proposed model outperforms with better accuracy: 0.96, sensitivity: 0.97, specificity: 0.98, detection rate: 0.95.