Fully automated plaque characterization in intravascular OCT images using hybrid convolutional and lumen morphology features

For intravascular OCT (IVOCT) images, we developed an automated atherosclerotic plaque characterization method that used a hybrid learning approach, which combined deep-learning convolutional and hand-crafted, lumen morphological features. Processing was done on innate A-line units with labels fibro...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2020-02, Vol.10 (1), p.2596-2596, Article 2596
Main Authors: Lee, Juhwan, Prabhu, David, Kolluru, Chaitanya, Gharaibeh, Yazan, Zimin, Vladislav N., Dallan, Luis A. P., Bezerra, Hiram G., Wilson, David L.
Format: Article
Language:English
Subjects:
639/166/985
639/705/794
692/4019/2776
Arteriosclerosis
Automation
Calcification
Classification
Deep Learning
Diagnosis, Computer-Assisted - methods
Humanities and Social Sciences
Humans
Image Processing, Computer-Assisted - methods
Morphology
multidisciplinary
Plaque, Atherosclerotic - classification
Plaque, Atherosclerotic - diagnostic imaging
Plaques
Science
Science (multidisciplinary)
Statistical analysis
Tomography, Optical Coherence - methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For intravascular OCT (IVOCT) images, we developed an automated atherosclerotic plaque characterization method that used a hybrid learning approach, which combined deep-learning convolutional and hand-crafted, lumen morphological features. Processing was done on innate A-line units with labels fibrolipidic (fibrous tissue followed by lipidous tissue), fibrocalcific (fibrous tissue followed by calcification), or other. We trained/tested on an expansive data set (6,556 images), and performed an active learning, relabeling step to improve noisy ground truth labels. Conditional random field was an important post-processing step to reduce classification errors. Sensitivities/specificities were 84.8%/97.8% and 91.4%/95.7% for fibrolipidic and fibrocalcific plaques, respectively. Over lesions, en face classification maps showed automated results that agreed favorably to manually labeled counterparts. Adding lumen morphological features gave statistically significant improvement (p 
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-59315-6