Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral data
| Autor: | Yijie Zhang, Manmohan Singh, Tairan Liu, Ege Cetintas, Yair Rivenson, Kirill V. Larin, Yilin Luo, Aydogan Ozcan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition FOS: Physical sciences 02 engineering and technology Iterative reconstruction 01 natural sciences Article Machine Learning (cs.LG) 010309 optics Optical coherence tomography Sampling (signal processing) Aliasing 0103 physical sciences Medical imaging medicine FOS: Electrical engineering electronic engineering information engineering Applied optics. Photonics Computer vision Image resolution Microscopy medicine.diagnostic_test business.industry Deep learning Image and Video Processing (eess.IV) Imaging and sensing QC350-467 Optics. Light Electrical Engineering and Systems Science - Image and Video Processing 021001 nanoscience & nanotechnology Atomic and Molecular Physics and Optics TA1501-1820 Electronic Optical and Magnetic Materials Undersampling Artificial intelligence 0210 nano-technology business Physics - Optics Optics (physics.optics) |
| Zdroj: | Light: Science & Applications, Vol 10, Iss 1, Pp 1-14 (2021) Light, Science & Applications |
| DOI: | 10.48550/arxiv.2103.03877 |
| Popis: | Optical Coherence Tomography (OCT) is a widely used non-invasive biomedical imaging modality that can rapidly provide volumetric images of samples. Here, we present a deep learning-based image reconstruction framework that can generate swept-source OCT (SS-OCT) images using undersampled spectral data, without any spatial aliasing artifacts. This neural network-based image reconstruction does not require any hardware changes to the optical set-up and can be easily integrated with existing swept-source or spectral domain OCT systems to reduce the amount of raw spectral data to be acquired. To show the efficacy of this framework, we trained and blindly tested a deep neural network using mouse embryo samples imaged by an SS-OCT system. Using 2-fold undersampled spectral data (i.e., 640 spectral points per A-line), the trained neural network can blindly reconstruct 512 A-lines in ~6.73 ms using a desktop computer, removing spatial aliasing artifacts due to spectral undersampling, also presenting a very good match to the images of the same samples, reconstructed using the full spectral OCT data (i.e., 1280 spectral points per A-line). We also successfully demonstrate that this framework can be further extended to process 3x undersampled spectral data per A-line, with some performance degradation in the reconstructed image quality compared to 2x spectral undersampling. This deep learning-enabled image reconstruction approach can be broadly used in various forms of spectral domain OCT systems, helping to increase their imaging speed without sacrificing image resolution and signal-to-noise ratio. Comment: 20 Pages, 7 Figures, 1 Table |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|