Segmentation of Anatomical Layers and Artifacts in Intravascular Polarization Sensitive Optical Coherence Tomography Using Attending Physician and Boundary Cardinality Lost Terms

Intravascular ultrasound and optical coherence tomography are widely available for characterizing coronary stenoses and provide critical vessel parameters to optimize percutaneous intervention. Intravascular polarization-sensitive optical coherence tomography (PS-OCT) simultaneously provides high-resolution crosssectional images of vascular structures while also revealing preponderant tissue components such as collagen and smooth muscle and thereby enhances plaque characterization. Automated interpretation of these features promises to facilitate the objective clinical investigation of the natural history and significance of coronary atheromas. Here, we propose a convolutional neural network model, optimized using a new multi-term loss function, to classify the lumen, intima, and media layers in addition to the guidewire and plaque shadows. We demonstrate that our multi-class classification model outperforms state-of-theart methods in detecting the coronary anatomical layers. Furthermore, the proposed model segments two classes of common imaging artifacts and detects the anatomical layers within the thickened vessel wall regions that were excluded from analysis by other studies. The source code This work was supported by the National Institutes of Health NIBIB under Grants P41EB-015902 and P41EB-015903. Also, Mohammad Haft-Javaherian was supported by Bullock Postdoctoral Fellowship. This work was done partially using MIT-IBM Satori hardware resource (Corresponding author: Mohammad Haft-Javaherian). * Polina Golland and Brett E. Bouma have equal contributions. Mohammad Haft-Javaherian is with the Wellman Center for Photomedicine, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114 USA, and the Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02142 USA (e-mail: haft@csail.mit.edu). Martin Villiger and Kenichiro Otsuka are with the Wellman Center for Photomedicine, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114 USA (e-mail: mvilliger@mgh.harvard.edu; kotsuka@mgh.harvard.edu). Joost Daemenis is with the Department of Interventional Cardiology, Thoraxcenter, Erasmus Medical Center, Rotterdam, The Netherlands (email: j.daemen@erasmusmc.nl). Peter Libby is with the Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115 (e-mail: plibby@bwh.harvard.edu). Polina Golland is with the Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology, Cambridge, MA 02142 USA (e-mail: polina@csail.mit.edu). Brett E. Bouma is with the Wellman Center for Photomedicine, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114 USA, and the Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA 02142 USA (email: bouma@mgh.harvard.edu). and the trained model are publicly available at https:// github.com/mhaft/OCTseg.