Classification of colorectal cancer using ResNet and EfficientNet models

Introduction: Cancer is one of the most prevalent diseases from children to elderly adults. This will be deadly if not detected at an earlier stage of the cancerous cell formation, thereby increasing the mortality rate. One such cancer is colorectal cancer, caused due to abnormal growth in the rectum or colon. Early screening of colorectal cancer helps to identify these abnormal growth and can exterminate them before they turn into cancerous cells. Aim: Therefore, this study aims to develop a robust and efficient classification system for colorectal cancer through Convolutional Neural Networks (CNNs) on histological images. Methods: Despite challenges in optimizing model architectures, the improved CNN models like ResNet34 and EfficientNet34 could enhance Colorectal Cancer classification accuracy and efficiency, aiding doctors in early detection and diagnosis, ultimately leading to better patient outcomes. Results: ResNet34 outperforms the EfficientNet34. Conclusion: The results are compared with other models in the literature, and ResNet34 outperforms all the other models.

Text 116346.pdf - Published Version Available under License Creative Commons Attribution. Download (7MB) Official URL or Download Paper: https://openbiomedicalengineeringjournal.com/VOLUM...

Actions (login required)

View Item