The Forward-Forward Algorithm as a feature extractor for skin lesion classification: A preliminary study

TL;DR

This study investigates using the Forward-Forward Algorithm as a low-power alternative for skin lesion classification, and explores combining it with backpropagation to improve accuracy in medical image analysis.

Contribution

It introduces the application of the Forward-Forward Algorithm for skin lesion classification and examines its potential when combined with backpropagation.

Findings

FFA can be used as a feature extractor for skin lesion classification

Combining FFA with backpropagation improves prediction accuracy

FFA offers a low-power alternative to traditional deep learning methods

Abstract

Skin cancer, a deadly form of cancer, exhibits a 23\% survival rate in the USA with late diagnosis. Early detection can significantly increase the survival rate, and facilitate timely treatment. Accurate biomedical image classification is vital in medical analysis, aiding clinicians in disease diagnosis and treatment. Deep learning (DL) techniques, such as convolutional neural networks and transformers, have revolutionized clinical decision-making automation. However, computational cost and hardware constraints limit the implementation of state-of-the-art DL architectures. In this work, we explore a new type of neural network that does not need backpropagation (BP), namely the Forward-Forward Algorithm (FFA), for skin lesion classification. While FFA is claimed to use very low-power analog hardware, BP still tends to be superior in terms of classification accuracy. In addition, our experimental results suggest that the combination of FFA and BP can be a better alternative to achieve a more accurate prediction.