Super Resolution — Deep Generative Denoising Diffusion on Video Sequence Data
Authors / Developers: Joe Xing
Introduction
Showcasing Sections
In recent years, deep learning (DL) has made breakthroughs in many fields. However, the success of DL requires constant re-training with large amounts of data, which is often costly, causing data paucity problems in the medical space. Active learning (AL), on the other hand, aims to reduce the amount of training data while still retaining similar performance through the exploration of the added value of data. In this study, we designed an AL system for training Artificial Intelligence (AI) models to explore faster learning curves while minimizing the need for new data. The model was designed for vessel object detection, using a Deep Neural Network (DNN), for scanning laser ophthalmoscopy (SLO) retinal images. Image embedding vectors were used to proactively select the most informative data. We established a baseline of k-fold cross validation frameworks to measure model performance, where 809 annotated images were randomly selected from our database and divided into multiple regions of interest with minimal selection bias.
Scanning Laser Ophthalmoscopy (SLO) Video Sequence Data
Heuristic-based Data Quality Metrics
Radially averaged power spectrum (RAPS) is used to provide a rough estimate on the signal strength, image quality.
Healthcare 3D illustrations
Colliding Cubes
References
-
Youssef Mansour, Reinhard Heckel, Zero-Shot Noise2Noise: Efficient Image Denoising without any Data, CoRR abs/2303.11253 (2023)
-
Olaf Ronneberger and Philipp Fischer and Thomas Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv 1505.04597, 2015
-
Xiao, H., Wang, X., Wang, J. et al. Single image super-resolution with denoising diffusion GANS. Sci Rep 14, 4272 (2024). https://doi.org/10.1038/s41598-024-52370-3
-
Tiange Xiang and Mahmut Yurt and Ali B Syed and Kawin Setsompop and Akshay Chaudhari, DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models, arXiv 2302.03018, 2023
-
Mangal Prakash, Alexander Krull, Florian Jug, Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders, 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021
-
Evan Ruzanski, Radially averaged power spectrum of 2D real-valued matrix, 2009
-
Matteo Maggioni; Giacomo M. Maggioni, G. Boracchi, A. Foi and K. Egiazarian, “Video Denoising, Deblocking, and Enhancement Through Separable 4-D Nonlocal Spatiotemporal Transforms,” in IEEE Transactions on Image Processing, vol. 21, no. 9, pp. 3952-3966, Sept. 2012, doi: 10.1109/TIP.2012.2199324. Spatiotemporal Transforms
