Deep learning for analysis of optical coherence tomography images
Title: |
Deep learning for analysis of optical coherence tomography images |
DNr: |
Berzelius-2022-37 |
Project Type: |
LiU Berzelius |
Principal Investigator: |
Neda Haj Hosseini <neda.haj.hosseini@liu.se> |
Affiliation: |
Linköpings universitet |
Duration: |
2022-02-28 – 2022-09-01 |
Classification: |
20603 |
Keywords: |
|
Abstract
The project aims at implementing deep learning on Optical Coherence Tomography (OCT) images for automatic analysis and classification of diseased thyroid tissue versus healthy tissue. The OCT images are challenging to analyze and quantify due to the imposed speckle noise in the scans and the depth dependent signal strength. Deep learning methods can improve the image analysis and tissue classification.
The 3D OCT images are very large (several GBs) due to the high resolution of the images, therefore access to Berzelius is needed.