Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Patients with atherosclerosis have a rather high risk of showing complications, if not diagnosed quickly and efficiently.

Objective

In this paper we aim to test and compare different pre-trained deep learning models, to find the best model for atherosclerosis detection in coronary CT angiography.

Methods

We experimented with different pre-trained deep learning models and fine-tuned each model to achieve the best classification accuracy. We then used the Haar wavelet decomposition to improve the model’s sensitivity.

Results

We found that the Resnet101 architecture had the best performance with an accuracy of 95.2%, 60.8% sensitivity, and 90.48% PPV. Compared to the state of the art which uses a 3D CNN and achieved 90.9% accuracy, 68.9% Sensitivity and 58.8% PPV, sensitivity was quite low. To improve the sensitivity, we chose to use the Haar wavelet decomposition and trained the CNN model with the module of the three details: Low_High, High_Low, and High_High. The best sensitivity reached 80% with the CNN_KNN classifier.

Conclusion

It is possible to perform atherosclerosis detection straight from CCTA images using a pretrained Resnet101, which has good accuracy and PPV. The low sensitivity can be improved using Haar wavelet decomposition and CNN-KNN classifier.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/1573405619666221221092933
2024-01-01
2025-06-26

  • From This Site

    /content/journals/cmir/10.2174/1573405619666221221092933
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. LittH.I. GatsonisC. SnyderB. CT angiography for safe discharge of patients with possible acute coronary syndromes.N. Engl. J. Med.2012366151393140310.1056/NEJMoa1201163
     [Google Scholar]
  2. ParikhR. PatelA. LuB. SenapatiA. MahmarianJ. ChangS.M. Cardiac computed tomography for comprehensive coronary assessment: beyond diagnosis of anatomic stenosis.Methodist DeBakey Cardiovasc. J.2020162778510.14797/mdcj‑16‑2‑77
     [Google Scholar]
  3. GhanemA.M. HamimiA.H. MattaJ.R. Automatic coronary wall and atherosclerotic plaque segmentation from 3D coronary CT angiography.Sci. Rep.2019914710.1038/s41598‑018‑37168‑4
     [Google Scholar]
  4. GaoZ. LiuX. QiS. WuW. HauW.K. ZhangH. Automatic segmentation of coronary tree in CT angiography images.Int. J. Adapt. Control Signal Process.20193381239124710.1002/acs.2762
     [Google Scholar]
  5. TianF. GaoY. FangZ. GuJ. Automatic coronary artery segmentation algorithm based on deep learning and digital image processing.Appl. Intell.202151128881889510.1007/s10489‑021‑02197‑6
     [Google Scholar]
  6. SuiC. FuZ. FuZ. WangY. ZhuangY. XieR. A novel method for vessel segmentation and automatic diagnosis of vascular stenosis.2019IEEE International Conference on Robotics and Biomimetics (ROBIO)91823
     [Google Scholar]
  7. ZreikM. van HamersveltR.W. WolterinkJ.M. LeinerT. ViergeverM.A. IsgumI. A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography.IEEE Trans. Med. Imaging20193871588159810.1109/TMI.2018.2883807
     [Google Scholar]
  8. MerkowJ. MarsdenA. KriegmanD. TuZ. Dense Volume-to-Volume Vascular Boundary Detection.Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016.BerlinSpringer2016371379
     [Google Scholar]
  9. PimM. JelmerM.W. BasH.M.V. Deep learning for multi-task medical image segmentation in multiple modalities.Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016.BerlinSpringer2016478486
     [Google Scholar]
  10. ShenY FangZ GaoY XiongN ZhongC TangX. Coronary Arteries Segmentation Based on 3D FCN With Attention Gate and Level Set Function.IEEE Access201974282635
     [Google Scholar]
  11. HuangW. HuangL. LinZ. Artery Segmentation by Deep Learning Neural Networks on Computed Tomographic Coronary Angiographic Images.2018
     [Google Scholar]
  12. GreenlandP. BlahaM.J. BudoffM.J. ErbelR. WatsonK. Coronary calcium score and cardiovascular risk.J. Am. Coll. Cardiol.2018434-710.1016/j.jacc.2018.05.027
     [Google Scholar]
  13. LiuJ. JinC. FengJ. DuY. LuJ. ZhouJ.A. A Vessel-Focused 3D Convolutional Network for Automatic Segmentation and Classifica-tion of Coronary Artery Plaques in Cardiac CTA.In: International Workshop on Statistical At-lases and Computational Models of the Heart201913114110.1007/978‑3‑030‑12029‑0_15
     [Google Scholar]
  14. SAnchez CI Contextual computer-aided detection: Improving bright lesion detection in retinal images and coronary calcification identification in CT scans.Med. Image Anal.2012161506210.1016/j.media.2011.05.004
     [Google Scholar]
  15. ShahzadR. van WalsumT. SchaapM. Vessel specific coronary artery calcium scoring: an automatic system.Acad. Radiol.20132011910.1016/j.acra.2012.07.018
     [Google Scholar]
  16. WolterinkJ.M. LeinerT. TakxR.A.P. ViergeverM.A. IsgumI. Automatic coronary calcium scoring in non-contrast-enhanced ECG-triggered cardiac CT with ambiguity detection.IEEE Trans. Med. Imaging20153491867187810.1109/TMI.2015.2412651
     [Google Scholar]
  17. IsgumI. ProkopM. NiemeijerM. ViergeverM.A. van GinnekenB. Automatic coronary calcium scoring in low-dose chest computed tomography.IEEE Trans. Med. Imaging201231122322233410.1109/TMI.2012.2216889
     [Google Scholar]
  18. YangG. ChenY. NingX. SunQ. ShuH. CoatrieuxJ.L. Automatic coronary calcium scoring using noncontrast and contrast CT images.Med. Phys.20164352174218610.1118/1.4945045
     [Google Scholar]
  19. WolterinkJ.M. LeinerT. de VosB.D. van HamersveltR.W. ViergeverM.A. IgumI. Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks.Med. Image Anal.20163412313610.1016/j.media.2016.04.004
     [Google Scholar]
  20. LessmannN. van GinnekenB. ZreikM. Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions.IEEE Trans. Med. Imaging201837261562510.1109/TMI.2017.2769839
     [Google Scholar]
  21. Cano-EspinosaC. GonzAlezG. WashkoG.R. CazorlaM. EstA(c)par RSJ. Automated Agatston Score Computation in non-ECG Gated CT Scans Using Deep Learning.In: SPIE Int Opti Eng201810574105742k
     [Google Scholar]
  22. de VosB.D. WolterinkJ.M. LeinerT. de JongP.A. LessmannN. IsgumI. Direct automatic coronary calcium scoring in cardiac and chest CT.IEEE Trans. Med. Imaging20193892127213810.1109/TMI.2019.2899534
     [Google Scholar]
  23. ZhaoF. WuB. ChenF. An automatic multi-class coronary atherosclerosis plaque detection and classification framework.Med. Biol. Eng. Comput.201957124525710.1007/s11517‑018‑1880‑6
     [Google Scholar]
  24. JawaidM.M. RiazA. RajaniR. Reyes-AldasoroC.C. SlabaughG. Framework for detection and localization of coronary non-calcified plaques in cardiac CTA using mean radial profiles.Comput. Biol. Med.201789849510.1016/j.compbiomed.2017.07.021
     [Google Scholar]
  25. WeiJ. ZhouC. ChanH.P. Computerized detection of noncalcified plaques in coronary CT angiography: Evaluation of topological soft gradient prescreening method and luminal analysis.Med. Phys.2014418Part108190110.1118/1.4885958
     [Google Scholar]
  26. HampeN. WolterinkJ.M. van VelzenS.G.M. LeinerT. IgumI. Machine learning for assessment of coronary artery disease in cardiac CT: A survey.Front. Cardiovasc. Med.2019617210.3389/fcvm.2019.00172
     [Google Scholar]
  27. YoungtaekH. FredericC. SebastienC. Deep learning-based stenosis quantification from coronary CT Angiography. Medical Imaging 2019: Image Processing.International Society for Optics and Photonics2019
     [Google Scholar]
  28. CandemirS. WhiteR.D. DemirerM. Automated coronary artery atherosclerosis detection and weakly supervised localization on coronary CT angiography with a deep 3-dimensional convolutional neural network.Comput. Med. Imaging Graph.20208310172110.1016/j.compmedimag.2020.101721
     [Google Scholar]
  29. GuptaV. BigelowM. ErdalB. PrevedelloL. WhiteR. Image dataset for a CNN algorithm development to detect coronary atherosclerosis in coronary CT angiography.Mendeley Data2019
     [Google Scholar]
  30. AlomM.Z. TahaT.M. YakopcicC. A state-of-the-art survey on deep learning theory and architectures.Electronics (Basel)20198329210.3390/electronics8030292
     [Google Scholar]
  31. KrizhevskyA. SutskeverI. HintonG.E. ImageNet Classification with Deep Convolutional Neural Networks.2012
     [Google Scholar]
  32. RussakovskyO. DengJ. SuH. Imagenet large scale visual recognition challenge.Int. J. Comput. Vis.2015115321125210.1007/s11263‑015‑0816‑y
     [Google Scholar]
  33. SimonyanK ZissermanA Very deep convolutional networks for large-scale image recognition.2017
     [Google Scholar]
  34. SzegedyC. LiuW. JiaY. Going Deeper with Convolutions.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2019Boston, MA7-12 June 201519
     [Google Scholar]
  35. HeK. ZhangX. RenS. Sun J. Deep Residual Learning for Image Recognition.IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2016770778
     [Google Scholar]
  36. SzegedyC. IoffeS. VanhouckeV. AlemiA. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning.2016
  37. SzegedyC. VanhouckeV. IoffeS. ShlensJ. WojnaZ. Rethinking the Inception Architecture for Computer Vision.IEEE Conference on Computer Vision and Pattern Recognition (CVPR)201628182826
     [Google Scholar]
  38. SrivastavaN. HintonG. KrizhevskyA. SutskeverI. SalakhutdinovR. Dropout: A simple way to prevent neural networks from overfitting.J. Mach. Learn. Res.2014155619291958
     [Google Scholar]
  39. AltmanN. An Introduction to kernel and nearest-neighbor nonparametric regression.Am. Stat.199246175185
     [Google Scholar]
  40. CortesC. VapnikV. Support-vector networks.Mach. Learn.199520327329710.1007/BF00994018
     [Google Scholar]
  41. BottouL. LinC.J. Support vector machine solvers.2007
     [Google Scholar]
  42. FisherR.A. The use of multiple measurements in taxonomic problems.Ann. Eugen.19367217918810.1111/j.1469‑1809.1936.tb02137.x
     [Google Scholar]
  43. RaoC.R. The utilization of multiple measurements in problems of biological classification.J. R. Stat. Soc. B194810215919310.1111/j.2517‑6161.1948.tb00008.x
     [Google Scholar]
  44. FelixD. MichaelW. NishantR. Coronary artery plaque characterization from CCTA scans using deep learning and radiomics.International Conference on Medical Image Computing and Computer-Assisted Intervention2019
     [Google Scholar]
/content/journals/cmir/10.2174/1573405619666221221092933
Loading
Deep Learning Models for Coronary Atherosclerosis Detection in Coronary CT Angiography
Curr. Med. Imaging 20, e211222212072 (2024); https://doi.org/10.2174/1573405619666221221092933
/content/journals/cmir/10.2174/1573405619666221221092933
/content/journals/cmir/10.2174/1573405619666221221092933
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Angiography; Atherosclerosis; Coronary artery diseases; Deep learning; Resnet101; Wavelet decomposition

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test