Improved image quality in dynamic OCT imaging by reduced imaging time and machine learning based data evaluation

Dynamic Optical Coherence Tomography combines high resolution tomographic imagery with a cell specific contrast by Fourier analysis. However, the conversion from frequency space into RGB images by binning requires a priori knowledge and artifacts due to global movements provide another obstacle for in vivo application. We could show that an automated binning based on the Neural Gas algorithm can yield the highest spectral contrast without a priori knowledge and that motion artifacts can be reduced with shorter sequence lengths. Imaging murine airways, we observed that even just 6 frames are enough to generate dOCT images without losing important image information.