ViT-DeiT: An Ensemble Model for Breast Cancer Histopathological Images Classification

TL;DR

This paper introduces an ensemble of Vision Transformer models for classifying breast cancer histopathological images, achieving high accuracy and precision to aid in early diagnosis.

Contribution

It presents a novel ensemble approach combining Vision Transformer and Data-Efficient Image Transformer for improved breast cancer image classification.

Findings

Achieved 98.17% accuracy on a public dataset.

Demonstrated high precision and recall around 98%.

Validated the effectiveness of the ensemble model.

Abstract

Breast cancer is the most common cancer in the world and the second most common type of cancer that causes death in women. The timely and accurate diagnosis of breast cancer using histopathological images is crucial for patient care and treatment. Pathologists can make more accurate diagnoses with the help of a novel approach based on image processing. This approach is an ensemble model of two types of pre-trained vision transformer models, namely, Vision Transformer and Data-Efficient Image Transformer. The proposed ensemble model classifies breast cancer histopathology images into eight classes, four of which are categorized as benign, whereas the others are categorized as malignant. A public dataset was used to evaluate the proposed model. The experimental results showed 98.17% accuracy, 98.18% precision, 98.08% recall, and a 98.12% F1 score.