Deep learning segmentation of fibrous cap in intravascular optical coherence tomography images

作者：Juhwan Lee, Justin N. Kim, Luís Augusto Palma Dallan, Vladislav N. Zimin, Ammar Hoori, Neda Shafiabadi Hassani, Mohamed H. E. Makhlouf, Giulio Guagliumi, Hiram G. Bezerra, David L. Wilson · 发表于：Scientific Reports · 年份：2024 · DOI：10.1038/s41598-024-55120-7 · 被引用次数：17 · 研究领域：Coronary Interventions and Diagnostics、Cerebrovascular and Carotid Artery Diseases、Optical Coherence Tomography Applications

Thin-cap fibroatheroma (TCFA) is a prominent risk factor for plaque rupture. Intravascular optical coherence tomography (IVOCT) enables identification of fibrous cap (FC), measurement of FC thicknesses, and assessment of plaque vulnerability. We developed a fully-automated deep learning method for FC segmentation. This study included 32,531 images across 227 pullbacks from two registries (TRANSFORM-OCT and UHCMC). Images were semi-automatically labeled using our OCTOPUS with expert editing using established guidelines. We employed preprocessing including guidewire shadow detection, lumen segmentation, pixel-shifting, and Gaussian filtering on raw IVOCT (r,θ) images. Data were augmented in a natural way by changing θ in spiral acquisitions and by changing intensity and noise values. We used a modified SegResNet and comparison networks to segment FCs. We employed transfer learning from our existing much larger, fully-labeled calcification IVOCT dataset to reduce deep-learning training. Postprocessing with a morphological operation enhanced segmentation performance. Overall, our method consistently delivered better FC segmentation results (Dice: 0.837 ± 0.012) than other deep-learning methods. Transfer learning reduced training time by 84% and reduced the need for more training samples. Our method showed a high level of generalizability, evidenced by highly-consistent segmentations across five-fold cross-validation (sensitivity: 85.0 ± 0.3%, Dice: 0.846 ± 0.011) and the held-out...