Automated A-line coronary plaque classification of intravascular optical coherence tomography images using handcrafted features and large datasets

Abstract

We developed machine learning methods to identify fibrolipidic and fibrocalcific A-lines in intravascular optical coherence tomography (IVOCT) images using a comprehensive set of handcrafted features. We incorporated features developed in previous studies (e.g., optical attenuation and A-line peaks). In addition, we included vascular lumen morphology and three-dimensional (3-D) digital edge and texture features. Classification methods were developed using expansive datasets (∼7000 images), consisting of both clinical in-vivo images and an ex-vivo dataset, which was validated using 3-D cryo-imaging/histology. Conditional random field was used to perform 3-D classification noise cleaning of classification results. We tested various multiclass approaches, classifiers, and feature selection schemes and found that a three-class support vector machine with minimal-redundancy-maximal-relevance feature selection gave the best performance. We found that inclusion of our morphological and 3-D features improved overall classification accuracy. On a held-out test set consisting of >1700 images, we obtained an overall accuracy of 81.58%, with the following (sensitivity/ specificity) for each class: other (81.43/89.59), fibrolipidic (94.48/87.32), and fibrocalcific (74.82/95.28). The en-face views of classification results showed that automated classification easily captured the preponderance of a disease segment (e.g., a calcified segment had large regions of fibrocalcific classifications). Finally, we demonstrated proof-of-concept for streamlining A-line classification output with existing fibrolipidic and fibrocalcific boundary segmentation methods, to enable fully automated plaque quantification. The results suggest that our classification approach is a viable step toward fully automated IVOCT plaque classification and segmentation for live-time treatment planning and for offline assessment of drug and biologic therapeutics.

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

“…The proposed hybrid method was compared to our two previous A-line-based classification approaches which used deep learning 27 and hand crafted features 28 alone. We trained/tested the previous approaches on the exact same data sets (five folds for training and held-out for testing) used in this study.…”

“…In case of disagreement, readers revaluated the frames and reached a consensus decision. From a simple rule, we next created A-line labels, consisting of fibrolipidic, fibrocalcific, and other, as reported previously 27,28 . If an A-line included ≥3 pixels of either lipidous or calcified plaques, we determined which of these two classes was in the majority, and then labeled the A-line accordingly as fibrolipidic or fibrocalcific.…”

“…After training, we removed the last fully connected layer and obtained Lumen morphology features. We extracted lumen morphological features using methods described previously 28 , which are now only briefly described. We estimated the change in lumen area by analyzing the lumen area of current frame to each of its adjacent ± 3 frames.…”

“…In total, we extracted 371 morphological features in IVOCT images. The details of these features are referred in 28 .…”

Coronary calcification segmentation in intravascular OCT images using deep learning: application to calcification scoring

“…Zhou et al 20 developed a classification and segmentation method using texture features described by the Fourier transform and discrete wavelet transform to classify adventitia, calcification, lipid, and mixed tissue. Our group developed machine learning 21 and deep learning 22,23 methods to automatically classify plaque regions. Rico-Jimenez et al 24 used linear discriminant analysis to identify normal and fibrolipidic A-lines.…”