Diffusion models applied to skin and oral cancer classification

TL;DR

This paper explores the use of diffusion models for classifying skin and oral cancer images, showing competitive accuracy and robustness, and comparing favorably with traditional deep learning methods.

Contribution

It introduces diffusion models as a new approach for medical image classification, demonstrating their effectiveness on skin and oral cancer datasets.

Findings

Diffusion models achieved balanced accuracy of 0.6457 (multi-class) and 0.8357 (binary) on skin cancer datasets.

The model attained 0.9050 balanced accuracy on oral cancer dataset.

Robustness tested on clinical images showed promising results.

Abstract

This study investigates the application of diffusion models in medical image classification (DiffMIC), focusing on skin and oral lesions. Utilizing the datasets PAD-UFES-20 for skin cancer and P-NDB-UFES for oral cancer, the diffusion model demonstrated competitive performance compared to state-of-the-art deep learning models like Convolutional Neural Networks (CNNs) and Transformers. Specifically, for the PAD-UFES-20 dataset, the model achieved a balanced accuracy of 0.6457 for six-class classification and 0.8357 for binary classification (cancer vs. non-cancer). For the P-NDB-UFES dataset, it attained a balanced accuracy of 0.9050. These results suggest that diffusion models are viable models for classifying medical images of skin and oral lesions. In addition, we investigate the robustness of the model trained on PAD-UFES-20 for skin cancer but tested on the clinical images of the HIBA dataset.