Improving Automated Tissue Characterization in Optical Coherence Tomography by Melding Attenuation Compensation with Deep Learning

The added benefit of intravascular imaging, such as optical coherence tomography (OCT), is that lumenography is augmented by lesion micro-morphology. For intravascular image analysis, deep learning methods have achieved satisfactory performance in automatic characterization of micro-morphology and tissue distribution, but have still been restricted by inherent OCT signal attenuation. Leveraging domain knowledge, we demonstrate the benefits of melding deep learning with existing attenuation compensation approaches to achieve more accurate full atherosclerotic tissue classification in OCT images. By combining acquired OCT images with attenuation-compensated and contrast-enhanced equivalents, overall classification accuracy was improved, with notable gains in calcium and lipid sensitivity. Results suggest that machine learning methods for tissue classification in modalities suffering from significant attenuation effects, such as OCT, may reap distinctive gains from integrating pre-processing steps that compensate for signal attenuation to augment the differentiable information contained therein.