MedMAE: A Self-Supervised Backbone for Medical Imaging Tasks
This addresses the lack of labeled data and domain mismatch for researchers and practitioners in medical imaging, though it is incremental as it adapts an existing self-supervised method to a new domain.
The authors tackled the problem of domain shift in medical imaging by proposing MedMAE, a self-supervised backbone pre-trained on a large-scale unlabeled medical image dataset, which outperformed existing pre-trained models on four medical imaging tasks.
Medical imaging tasks are very challenging due to the lack of publicly available labeled datasets. Hence, it is difficult to achieve high performance with existing deep-learning models as they require a massive labeled dataset to be trained effectively. An alternative solution is to use pre-trained models and fine-tune them using the medical imaging dataset. However, all existing models are pre-trained using natural images, which is a completely different domain from that of medical imaging, which leads to poor performance due to domain shift. To overcome these problems, we propose a large-scale unlabeled dataset of medical images and a backbone pre-trained using the proposed dataset with a self-supervised learning technique called Masked autoencoder. This backbone can be used as a pre-trained model for any medical imaging task, as it is trained to learn a visual representation of different types of medical images. To evaluate the performance of the proposed backbone, we used four different medical imaging tasks. The results are compared with existing pre-trained models. These experiments show the superiority of our proposed backbone in medical imaging tasks.