Automatic Assessment of Calcified Plaque and Nodule by Optical Coherence Tomography Adopting Deep Learning Mode

Abstract

Purpose: Optical coherence tomography (OCT) has become the best imaging tool in assessment of calcified plaque and nodule. However, every OCT pullback has large number of images and artificial analysis need too much time and energy, so it is not suitable for clinical application. This study aimed to develop and validate an automatic assessment of calcified plaque and nodule by OCT using deep learning model.Methods: The OCT images of calcified plaque and nodule were labeled by two expert readers based on the consensus. A deep learning model with a Multi-Scale and Multi-Task u-net network (MS-MT u-net) was developed. Then with the ground truth labeled by expert readers as reference, the diagnostic accuracy and agreement of the model would be validated.Results: For the pixel-wise evaluation of calcified plaque, the model had a high performance with precision (93.95%), recall (88.95%) and F1 score (91.38%). For the lesion-level evaluation of calcified plaque, the quantitative metrics by the model correlated excellent with the ground truth (calcium score, r=0.90, p< 0.01; calcified volume, r=0.99, p＜0.01). For calcified nodules, the model showed an excellent diagnostic performance of model including sensitivity (91.7%), specificity (89.3%) and accuracy (91.0%).Conclusions: We developed a novel deep learning model for identifying attributes of calcified plaque and nodule. This model provides an excellent diagnostic accuracy and agreement with the ground truth, which reduces subjectivity of manual measurements and saves lots of time. These findings would help practitioners efficiently adopting appropriate therapeutic strategy in the treatment of calcified lesions.