Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans
- 48 Downloads
Analysing coronary artery plaque segments with respect to their functional significance and therefore their influence to patient management in a non-invasive setup is an important subject of current research. In this work we compare and improve three deep learning algorithms for this task: A 3D recurrent convolutional neural network (RCNN), a 2D multi-view ensemble approach based on texture analysis, and a newly proposed 2.5D approach. Current state of the art methods utilising fluid dynamics based fractional flow reserve (FFR) simulation reach an AUC of up to 0.93 for the task of predicting an abnormal invasive FFR value. For the comparable task of predicting revascularisation decision, we are able to improve the performance in terms of AUC of both existing approaches with the proposed modifications, specifically from 0.80 to 0.90 for the 3D-RCNN, and from 0.85 to 0.90 for the multi-view texture-based ensemble. The newly proposed 2.5D approach achieves comparable results with an AUC of 0.90.
Unable to display preview. Download preview PDF.
- 1.Mendis S, Davis S, Norrving B. Organizational update: the world health organization global status report on noncommunicable diseases 2014. Stroke. 2015;46(5):e121–e122.Google Scholar
- 2.Taylor CA, Fonte TA, Min JK. Computational fluid dynamics applied to cardiac computed tomography for noninvasive quantification of fractional flow reserve: scientific basis. JACC. 2013;61(22):2233–2241.Google Scholar
- 3.Wels M, Lades F, Hopfgartner C, et al. Intuitive and accurate patient-specific coronary tree modeling from cardiac computed-tomography angiography. In: The 3rd interactive MIC Workshop; 2016. p. 86–93.Google Scholar
- 4.Zreik M, et al. A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography. IEEE Transactions on Medical Imaging. 2018;38(7):1588–1598.Google Scholar
- 5.Tejero-de Pablos A, et al. Texture-Based classification of significant stenosis in CCTA multi-view images of coronary arteries. In: MICCAI. Springer; 2019. p. 732–740.Google Scholar
- 6.Zheng Y, Tek H, Funka-Lea G. Robust and accurate coronary artery centerline extraction in CTA by combining model-driven and data-driven approaches. In: MICCAI. Springer; 2013. p. 74–81.Google Scholar
- 7.Cimpoi M, Maji S, Vedaldi A. Deep filter banks for texture recognition and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 3828–3836.Google Scholar
- 8.He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770–778.Google Scholar
- 9.Denzinger F, et al. Coronary artery plaque characterization from CCTA scans using deep learning and radiomics. In: MICCAI. Springer; 2019. p. 593–601.Google Scholar