Deep learning-based plaque characterization in hybrid IVUS-OCT images is superior to single-modality deep learning analysis and human experts: head-to-head comparison against histology

Key Points

• Plaque characterization with a hybrid IVUS-OCT deep learning classifier shows greater accuracy than single-modality approaches.
• The histology-trained classifier identifies plaque components and phenotypes more effectively than human experts.
• Assessment using a hybrid imaging technique reveals nuanced details that improve differentiation of plaque features.
• These findings highlight the potential for advanced deep learning methods to enhance cardiovascular diagnostics.

Abstract