Deep Learning Method to Detect Plaques in IVOCT Images

Grigorios Aris Cheimariotis*, Maria Riga, Konstantinos Toutouzas, Dimitris Tousoulis, Aggelos Katsaggelos, Nikolaos Maglaveras

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Intravascular Optical Coherence Tomography (IVOCT) is a modality which gives in vivo insight of coronaries’ artery morphology. Thus, it helps diagnosis and prevention of atherosclerosis. About 100–300 cross-sectional OCT images are obtained for each artery. Therefore, it is important to facilitate and objectify the process of detecting regions of interest, which otherwise demand a lot of time and effort from medical experts. We propose a processing pipeline to automatically detect parts of the arterial wall which are not normal and possibly consist of plaque. The first step of the processing is transforming OCT images to polar coordinates and to detect the arterial wall. After binarization of the image and removal of the catheter, the arterial wall is detected in each axial line from the first white pixel to a depth of 80 pixels which is equal to 1.5 mm. Then, the arterial wall is split to orthogonal patches which undergo OCT-specific transformations and are labelled as plaque (4 distinct kinds: fibrous, calcified, lipid and mixed) or normal tissue. OCT-specific transformations include enhancing the more reflective parts of the image and rendering patches independent of the arterial wall curvature. The patches are input to AlexNet which is fine-tuned to learn to classify them. Fine-tuning is performed by retraining an already trained AlexNet with a learning rate which is 20 times larger for the last 3 fully-connected layers than for the initial 5 convolutional layers. 114 cross-sectional images were randomly selected to fine-tune AlexNet while 6 were selected to validate the results. Training accuracy was 100% while validation accuracy was 86%. Drop in validation accuracy rate is attributed mainly to false negatives which concern only calcified plaque. Thus, there is potential in this method especially in detecting the 3 other classes of plaque.

Original languageEnglish (US)
Title of host publicationFuture Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019
EditorsKang-Ping Lin, Ratko Magjarevic, Paulo de Carvalho
PublisherSpringer
Pages389-395
Number of pages7
ISBN (Print)9783030306359
DOIs
StatePublished - Jan 1 2020
Event4th International Conference on Biomedical and Health Informatics, ICBHI 2019 - Taipei, Taiwan, Province of China
Duration: Apr 17 2019Apr 20 2019

Publication series

NameIFMBE Proceedings
Volume74
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference4th International Conference on Biomedical and Health Informatics, ICBHI 2019
CountryTaiwan, Province of China
CityTaipei
Period4/17/194/20/19

Keywords

  • Convolutional Neural Networks
  • Deep learning
  • Intravascular OCT
  • Segmentation

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Deep Learning Method to Detect Plaques in IVOCT Images'. Together they form a unique fingerprint.

  • Cite this

    Cheimariotis, G. A., Riga, M., Toutouzas, K., Tousoulis, D., Katsaggelos, A., & Maglaveras, N. (2020). Deep Learning Method to Detect Plaques in IVOCT Images. In K-P. Lin, R. Magjarevic, & P. de Carvalho (Eds.), Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019 (pp. 389-395). (IFMBE Proceedings; Vol. 74). Springer. https://doi.org/10.1007/978-3-030-30636-6_53