Objective: Spectral domain optical coherence tomography(SD-OCT)is a non-invasive diagnostic tool that can be used to visualize,treat,and monitor the structural changes of macular degeneration in patients with different retinopathy.However,the evaluation of SD-OCT images is hampered by a lack of image quality that ophthalmologists need to analyze and quantify the disease.This has hindered the potential role of hyperreflective foci(HRF)as a prognostic indicator of visual outcome in patients with retinal diseases.We present a new multi-vendor algorithm that is robust to noise while enhancing the HRF in SD-OCT images.Methods: The proposed algorithm processes the SD-OCT images in two parallel processes simultaneously.The two parallel processes are combined by histogram matching.The inverse of logarithmic and orthogonal transformations is applied to the rendering of data to generate enhanced images.Results: We evaluated our algorithm on a dataset consisting of 40 SD-OCT volumes.This proposed method obtained high values for the measure of enhancement,peak signal-to-noise ratio,structural similarity and correlation,a low value for mean square error of 36.72,38.87,0.87,0.98,and25.12 for Cirrus;40.77,41.84,0.89,0.98 and22.15 for Spectralis;and 30.81,32.10,0.81,0.96 and 28.55 for Topcon SD-OCT equipment respectively.Conclusion: The proposed enhancement algorithm improves the visualization and detection of HRF and can help clinicians determine patient treatment plans and disease monitoring.Assist ophthalmologist and medical image preprocessing. |