A Pathology-Based Machine Learning Method to Assist in Epithelial Dysplasia Diagnosis

TL;DR

This paper introduces a low-cost neural network-based method to assist in diagnosing epithelial dysplasia, reducing variability among pathologists and achieving high accuracy with minimal computational resources.

Contribution

The study presents a simple multilayer neural network approach that matches complex CNN performance in dysplasia detection while significantly lowering computational costs.

Findings

Achieved 87% accuracy in dysplasia classification.

Reduced variability compared to trained evaluators.

Comparable results to CNN with 100 times less computation.

Abstract

The Epithelial Dysplasia (ED) is a tissue alteration commonly present in lesions preceding oral cancer, being its presence one of the most important factors in the progression toward carcinoma. This study proposes a method to design a low computational cost classification system to support the detection of dysplastic epithelia, contributing to reduce the variability of pathologist assessments. We employ a multilayer artificial neural network (MLP-ANN) and defining the regions of the epithelium to be assessed based on the knowledge of the pathologist. The performance of the proposed solution was statistically evaluated. The implemented MLP-ANN presented an average accuracy of 87%, with a variability much inferior to that obtained from three trained evaluators. Moreover, the proposed solution led to results which are very close to those obtained using a convolutional neural network (CNN) implemented by transfer learning, with 100 times less computational complexity. In conclusion, our results show that a simple neural network structure can lead to a performance equivalent to that of much more complex structures, which are routinely used in the literature.