The Forward-Forward Algorithm as a feature extractor for skin lesion classification: A preliminary study
This is an incremental study addressing computational cost and hardware constraints in deep learning for medical image analysis, specifically for skin cancer detection.
The paper tackled skin lesion classification by exploring the Forward-Forward Algorithm (FFA) as a feature extractor, finding that combining FFA with backpropagation improved prediction accuracy compared to using FFA alone.
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.