MULTICLASS CLASSIFICATION OF HISTOLOGY ON COLORECTAL CANCER USING DEEP LEARNING

Abstract

Colorectal cancer (CRC) is a type of cancer that occurs in the colon or rectum, caused by cells dividing uncontrollably. Deep learning has proven to perform image recognition accurately that rivals human capabilities. This method became popular and can handle various complex image data. This paper presents a multiclass classification of histology on colorectal cancer using a Convolutional Neural Network (CNN). We propose the usage of EfficientNet with transfer learning to create high-performance learners and combine the model with the attention Squeeze and Excitation layer (SE layer). In several studies, the SE layer can improve the model by extracting essential features of the images. We compare EfficientNet with other architectures such as ResNet-101, AlexNet, and VGG16. Our experiment result achieves 97% testing accuracy, whereas NN-Ensemble-CNNs as the baseline model achieves 96.16%. The combined EfficientNet model and SE layer performed better than regular EfficientNet and other models.