Abstract
Multi-modal intracoronary imaging (visualize the inner structure of coronary arteries) has been proved to have great ability to help the coronary disease diagnosis in recent studies. However, no reported success on detecting all clinically-valuable vessel borders in multi-modal image analysis, because of the varied environment where the vessels are located in, i.e. inconsistent image appearance and tissue morphologies. This challenges the multi-modal vessel border detection, which is difficultly addressed by the hand-engineering feature extraction in existing single-mode methods. We propose a context-aware inductive bias learning approach to enable the detection of three vessel borders in multi-modal intracoronary imaging, i.e. the lumen and media-adventitia borders in intravascular ultrasound (IVUS), and the lumen border in optical coherence tomography (OCT). Our approach exploits the detection process of one vessel border as a model constraint to another vessel border based on the vessel contextual information. It is specified by an elaborately-designed semantic-fusion multi-task neural network, which exploits the similarly semantic information and different environment information to lead the mutual regularization among different vessel border detection tasks. The extensive experiments show the effectiveness of our approach by the highly overlapping degree with the ground truth and the superiority to six state-of-the-art single-mode vessel border detection methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cao, Y., et al.: Automatic side branch ostium detection and main vascular segmentation in intravascular optical coherence tomography images. IEEE J. Biomed. Health Inf. 22(5), 1531–1539 (2018)
Su, S., et al.: An artificial neural network method for lumen and media-adventitia border detection in IVUS. Comput. Med. Imaging Graph. 57(4), 29–39 (2017)
Xu, C., et al.: Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture. Med. Image Anal. 50, 82–94 (2018)
Zhao, S., et al.: Robust segmentation of intima-media borders with different morphologies and dynamics during the cardiac cycle. IEEE J. Biomed. Health Inf. 22(5), 1571–1582 (2018)
Zhao, R., et al.: Weakly-supervised simultaneous evidence identification and segmentation for automated glaucoma diagnosis. In: AAAI, pp. 1571–1582 (2019)
Paulo, M., et al.: Combined use of OCT and IVUS in spontaneous coronary artery dissection. JACC: Cardiovasc. Imaging 6(7), 830–832 (2013)
Fujii, K., et al.: Accuracy of OCT, grayscale IVUS, and their combination for the diagnosis of coronary TCFA: an ex vivo validation study. JACC: Cardiovasc. Imaging 8(4), 451–460 (2015)
Waggoner, J., et al.: How do OCT and IVUS differ? A comparison and assessment of these modern imaging modalities. Card. Interv. Today 3, 46–52 (2011)
Pociask, E., et al.: Fully automated lumen segmentation method for intracoronary optical coherence tomography. J. Healthc. Eng. 2018, 1–13 (2018)
Baxter, J.: A model of inductive bias learning. J. Artif. Intell. Res. 12, 149–198 (2000)
Ruder, S.: An overview of multi-task learning in deep neural networks. Computing Research Repository arXiv:abs/1706.05098 (2017)
Zhang, Z., et al.: ExFuse: enhancing feature fusion for semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 273–288. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_17
Kermani, A., et al.: A new nonparametric statistical approach to detect lumen and Media-Adventitia borders in intravascular ultrasound frames. Comput. Biol. Med. 104(1), 10–28 (2019)
Lee, J.H., et al.: Segmentation of the lumen and media-adventitial borders in intravascular ultrasound images using a geometric deformable model. IET Image Proc. 12(10), 1881–1891 (2018)
Amrute, J.M., et al.: Polymeric endovascular strut and lumen detection algorithm for intracoronary optical coherence tomography images. J. Biomed. Opt. 23(3), 1–14 (2018)
Acknowledgement
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, Z., Li, S. (2019). Context-Aware Inductive Bias Learning for Vessel Border Detection in Multi-modal Intracoronary Imaging. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11765. Springer, Cham. https://doi.org/10.1007/978-3-030-32245-8_86
Download citation
DOI: https://doi.org/10.1007/978-3-030-32245-8_86
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32244-1
Online ISBN: 978-3-030-32245-8
eBook Packages: Computer ScienceComputer Science (R0)