Speckle reduction using an artificial neural network algorithm

Abstract

This paper presents an algorithm for reducing speckle noise from optical coherence tomography (OCT) images using an artificial neural network (ANN) algorithm. The noise is modeled using Rayleigh distribution with a noise parameter, sigma, estimated by the ANN. The input to the ANN is a set of intensity and wavelet features computed from the image to be processed, and the output is an estimated sigma value. This is then used along with a numerical method to solve the inverse Rayleigh function to reduce the noise in the image. The algorithm is tested successfully on OCT images of Drosophila larvae. It is demonstrated that the signal-to-noise ratio and the contrast-to-noise ratio of the processed images are increased by the application of the ANN algorithm in comparison with the respective values of the original images.

A new algorithm for speckle reduction of optical coherence tomography images

“…Putting together the noise model segments, we can generate a noise model image. The noise model image was deducted from the original image with a scale factor which obtained experimentally [20]. r f e f f s images.…”

“…Besides the hardware modifications, a number of image processing algorithms have been reported such as adaptive digital filters [15][16], filters based on interval type II fuzzy algorithm [17], artificial neural network [3,[18][19][20][21][22][23], wavelet transformation with various configurations [24], or the use of median [2], averaging [25], Kuwahara filter and their combinations [2].…”

Two applications of solid phantoms in performance assessment of optical coherence tomography systems

“…The images were then averaged at each depth to reduce the amount of speckle noise. We used the same method introduced in [32] for the speckle-noise reduction. The signal-to-noise ratio (SNR) of the original images was increased by an average of 7 dB after despeckling compared to the original images.…”

Speckle reduction and deblurring of ultrasound images using artificial neural network

“…Linear diffusion methods also dislocate edges when moving from finer to coarser scales, [6], [7], [8], rely on the diffusion flux to iteratively eliminate small variations due to noise or texture, and preserve large variations due to edges. Some other methods have been reported, such as adaptive digital filters [9], fuzzy algorithm-based filters [10], artificial neural networks (ANNs) [11], [12], [13], wavelet transformation with various configurations [14], the use of median [15], and Kuwahara filters and their combinations [15]. An ANN based method for speckle reduction is proposed in [14].…”

“…Some other methods have been reported, such as adaptive digital filters [9], fuzzy algorithm-based filters [10], artificial neural networks (ANNs) [11], [12], [13], wavelet transformation with various configurations [14], the use of median [15], and Kuwahara filters and their combinations [15]. An ANN based method for speckle reduction is proposed in [14]. They applied their algorithm on optical tomographic im ages for speckle reduction using the noise variance estimated by a an ANN.…”