Show abstract - PDF - Reviews

Medical image classification is one of the most important tasks for computer-aided diagnosis. Deep learning models, particularly convolutional neural networks have been successfully used for disease classification from medical images, facilitated with automated feature learning. However, the diverse imaging modalities and clinical pathologies makes it challenging to generalized and robust classification. Towards improving the model performance, we propose a novel pretraining approach, namely \textbf{Forward Forward Contrastive Learning (FFCL)} which leverages the Forward-Forward Algorithm in a contrastive learning framework--both locally and globally. Our experimental results on chest X-ray dataset indicate that the proposed FFCL achieves superior performance (\textbf{3.69\%} accuracy over ImageNet pretrained ResNet-18) over existing pretraining models in pneumonia classification task. Moreover, an extensive ablation experiments support the particular local and global contrastive pretraining design in FFCL.
Hide abstract