Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder

Abstract

The COVID-19 pandemic has underscored the urgent need for rapid and accurate diagnosis facilitated by artificial intelligence (AI), particularly in computer-aided diagnosis using medical imaging. However, this context presents two notable challenges: high diagnostic accuracy demand and limited availability of medical data for training AI models. To address these issues, we proposed the implementation of a Masked AutoEncoder (MAE), an innovative self-supervised learning approach, for classifying 2D Chest X-ray images. Our approach involved performing imaging reconstruction using a Vision Transformer (ViT) model as the feature encoder, paired with a custom-defined decoder. Additionally, we fine-tuned the pretrained ViT encoder using a labeled medical dataset, serving as the backbone. To evaluate our approach, we conducted a comparative analysis of three distinct training methods: training from scratch, transfer learning, and MAE-based training, all employing COVID-19 chest X-ray images. The results demonstrate that MAE-based training produces superior performance, achieving an accuracy of 0.985 and an AUC of 0.9957. We explored the mask ratio influence on MAE and found ratio = 0.4 shows the best performance. Furthermore, we illustrate that MAE exhibits remarkable efficiency when applied to labeled data, delivering comparable performance to utilizing only 30% of the original training dataset. Overall, our findings highlight the significant performance enhancement achieved by using MAE, particularly when working with limited datasets. This approach holds profound implications for future disease diagnosis, especially in scenarios where imaging information is scarce.

Applying Self-Supervised Learning to Image Quality Assessment in Chest CT Imaging

“…The current state of SSL research has already achieved promising results in different domains of medicine such as digital pathology or computer-aided diagnosis [15][16][17]26]. In particular, the SSL paradigm can take advantage of the large volumes of unlabeled datasets available in medical imaging [6,15].…”

“…This learning paradigm reduces the reliance on labeled data by training a model to extract meaningful representations of the input data with no manual labeling required [16]. Recent studies have leveraged the potential of SSL for various tasks such as image segmentation and classification [15][16][17]. The success of this approach strongly depends on how the pretext tasks are chosen [15].…”

Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET

“…Using SSL in a pre-training step, the model trained to perform the downstream task can be less biased to the limited labeled data, thus having better generalizability. SSL has resulted in remarkable improvements in various domain applications, including but not limited to natural images [13], histopathology images [14], autonomous driving [15], and medical images [16,17]. Recent studies have especially focused on medical images.…”