Automated Detection and Classification of Oral Squamous Cell Carcinoma Using Deep Neural Networks

Abstract

This work aims to classify normal and carcinogenic cells in the oral cavity using two different approaches with an eye towards achieving high accuracy. The first approach extracts local binary patterns and metrics derived from a histogram from the dataset and is fed to several machine-learning models. The second approach uses a combination of neural networks as a backbone feature extractor and a random forest for classification. The results show that information can be learnt effectively from limited training images using these approaches. Some approaches use deep learning algorithms to generate a bounding box that can locate the suspected lesion. Other approaches use handcrafted textural feature extraction techniques and feed the resultant feature vectors to a classification model. The proposed method will extract the features pertaining to the images using pre-trained convolution neural networks (CNN) and train a classification model using the resulting feature vectors. By using the extracted features from a pre-trained CNN model to train a random forest, the problem of requiring a large amount of data to train deep learning models is bypassed. The study selected a dataset consisting of 1224 images, which were divided into two sets with varying resolutions.The performance of the model is calculated based on accuracy, specificity, sensitivity, and the area under curve (AUC). The proposed work is able to produce a highest test accuracy of 96.94% and an AUC of 0.976 using 696 images of 400× magnification and a highest test accuracy of 99.65% and an AUC of 0.9983 using only 528 images of 100× magnification images.

Keywords: CNN; computer vision; feature extraction; medical image analysis; oral cancer.

Figure 1

A block diagram of the proposed methodology. The left path is approach used for CNN based feature extraction. The right path is approach used for textural feature extraction.

Figure 2

Top-left image shows the original image converted to grey scale; bottom-left image shows the histogram of the original image; top-right image shows the processed image after histogram equalization; bottom-right image shows the histogram of the processed image.

Figure 3

Left image shows the original processed by histogram equalization; right image shows the sharpened left image.

Figure 4

An example to demonstrate LBP mechanism.

Figure 5

ROC curve of different classification models on textural and histogram features extracted from 400× images.

Figure 6

ROC curve of different classification models on textural and histogram features extracted from 100× images.

Figure 7

ROC curve for different CNN models with random forest classifier for 400× images classification.

Figure 8

ROC curve for different CNN models with random forest classifier for 100× images classification.