Iterative-in-Iterative Super-Resolution Biomedical Imaging Using One Real Image
This addresses the challenge of data scarcity in clinical practice for biomedical imaging, offering a potential solution for early detection and personalized medicine, though it appears incremental as it builds on existing super-resolution methods.
The paper tackled the problem of training deep learning-based super-resolution models for biomedical imaging with limited data by proposing an approach using only one real image, achieving improvements of 7.5% in structural similarity and 5.49% in peak-signal-to-noise ratio after five iterations.
Deep learning-based super-resolution models have the potential to revolutionize biomedical imaging and diagnoses by effectively tackling various challenges associated with early detection, personalized medicine, and clinical automation. However, the requirement of an extensive collection of high-resolution images presents limitations for widespread adoption in clinical practice. In our experiment, we proposed an approach to effectively train the deep learning-based super-resolution models using only one real image by leveraging self-generated high-resolution images. We employed a mixed metric of image screening to automatically select images with a distribution similar to ground truth, creating an incrementally curated training data set that encourages the model to generate improved images over time. After five training iterations, the proposed deep learning-based super-resolution model experienced a 7.5\% and 5.49\% improvement in structural similarity and peak-signal-to-noise ratio, respectively. Significantly, the model consistently produces visually enhanced results for training, improving its performance while preserving the characteristics of original biomedical images. These findings indicate a potential way to train a deep neural network in a self-revolution manner independent of real-world human data.