Lyme disease diagnosis poses a significant challenge, with blood tests exhibiting an alarming inaccuracy rate of nearly 60% in detecting early-stage infections. As a result, there is an urgent need for improved diagnostic methods that can offer more accurate detection outcomes. To address this pressing issue, our study focuses on harnessing the potential of deep learning approaches, specifically by employing model pipelining through progressive resizing and multiple self-supervised learning models. In this paper, we present a comprehensive exploration of self-supervised learning models, including SimCLR, SwAV, MoCo, and BYOL, tailored to the context of Lyme disease detection using medical imaging. The effectiveness and performance of these models are evaluated using standard metrics such as F1 score, precision, recall, and accuracy. Furthermore, we emphasize the significance of progressive resizing and its implications when dealing with convolutional neural networks (CNNs) for medical image analysis. By leveraging deep learning approaches, progressive resizing, and self-supervised learning models, the challenges associated with Lyme disease detection are effectively addressed in this study. The application of our novel methodology and the execution of a comprehensive evaluation framework contribute invaluable insights, fostering the development of more efficient and accurate diagnostic methods for Lyme disease. It is firmly believed that our research will serve as a catalyst, inspiring interdisciplinary collaborations that accelerate progress at the convergence of medicine, computing, and technology, ultimately benefiting public health.
- Contrast learning
- Convolutional neural networks
- Lyme disease
- Momentum contrast for unsupervised visual representation learning
- Progressive resizing
- Self-supervised learning