Speckle noise reduction and segmentation on polarization sensitive optical coherence tomography images

The retinal layers of a monkey were imaged using a polarization sensitive optical coherence tomography (PS-OCT) system in an effort to develop a clinically reliable automatic diagnostic system for glaucoma. Glaucoma is characterized by the progressive loss of ganglion cells and axons in the retinal nerve fiber layer (RNFL). Automatic segmentation of the RNFL from the PS-OCT images is a fundamental step to diagnose the progress of the disease. Due to the use of a coherent light, speckle noise is inherent in the images. Wavelet denoising techniques with a combination of image processing techniques were applied to remove the speckle noise in the PS-OCT images, and a fuzzy logic classifier was used to segment the RNFL. A significant signal to noise ratio improvement was observed qualitatively and quantitatively after the denoising. The upper boundary for the RNFL was reliably detected, but the lower boundary detection still remains as a problem.