Effective Deep Learning Approach to Denoise Optical Coherence Tomography Images Using BM3D-Based Preprocessing of the Training Data Including Both Healthy and Pathological Cases.
Piotr BogackiAndrzej DziechPublished in: IEEE Access (2023)
Keyphrases
- deep learning
- training data
- optical coherence tomography
- oct images
- image features
- three dimensional
- image data
- input image
- image analysis
- spectral domain
- supervised learning
- segmentation method
- ground truth
- object recognition
- segmentation algorithm
- machine learning
- test images
- fully automatic
- region of interest
- contrast enhancement
- image registration
- automated segmentation
- learning algorithm