esophageal cancer stage classification
What is it about?
The research paper develops a deep learning model for classifying the various stages of EC and the premalignant stage, Barrett's Esophagus, from endoscopic images. The proposed model uses a multi-CNN model with Xception, Mobilenetv2, GoogLeNet, and Darknet53 for feature extraction. The extracted features are blended and are then applied to the wrapper-based Artificial Bee Colony (ABC) optimization technique to grade the most accurate and relevant attributes. A multi-class support vector machine classifies the selected feature set into various stages.
Why is it important?
Esophageal cancer (EC) is an aggressive cancer with a high fatality rate, ranked sixth worldwide. There is a rapid rise in the incidence of EC globally, and early diagnosis is challenging for clinicians. The Convolution Neural Network (CNN) has a significant role in diagnosing EC. Almost all the pre-trained networks can be efficiently used in Computer-Aided Diagnosis (CAD) and classification of esophageal cancer.