Machine learning in the detection of coronary stenosis problem solving

Abstract.

Background. Considering the growing interest of researchers and clinical specialists in algorithms for processing medical data, the prospects for the applied application of such approaches have significantly increased, primarily, involving the use of deep neural networks in the tasks of detecting pathological areas. However, the use of such approaches is associated with a low level of localization accuracy, insufficient to translate the developments into the field of assistive systems for making medical decisions.

Aim. This work is aimed at assessing the speed and accuracy of the modern architecture of the convolutional neural network RFCN ResNet-101 V2 for the prospects for automated processing of clinical data from coronary angiography.

Materials and methods. The basis for the chosen neural network architecture training was the clinical graphic data of 50 patients subjected to routine coronary angiography, which is characterized by the presence of single-focal lesions (stenoses) in more than 75% of all cases. The study evaluated the metrics of classification and localization accuracy in determining the position of a single-focal coronary artery lesion.

Results. The utilized architecture of the neural network was capable of detecting single-focal lesions with an accuracy of 94%. However, to a large extent, it didn’t the performance requirements (processing speed).

Conclusion. The results obtained determine the further direction of development of the presented approach, which should be reducing the time of analysis of each frame of coronary angiography due to image preprocessing methods.

1. Bokeriya LA, Milievskaya EB, Kudzoeva ZF, Pryanishnikov VV, Skopin AI, Yurlov IA, editors. Cardiovascular Surgery 2018. Diseases and congenital abnormalities of circulatory system. Moscow: NMITsSSKh im. A.N. Bakuleva. 2019. (In Russ).

2. Khan MA, Hashim MJ, Mustafa H, et al. Global Epidemiology of Ischemic Heart Disease: Results from the Global Burden of Disease Study. Cureus. 2020; 12(7): e9349. doi:10.7759/cureus.9349.

3. Gu D, Qu J, Zhang H, et al. Revascularization for Coronary Artery Disease: Principle and Challenges. 2020: 75-100. doi:10.1007/978-981-15-2517-9_3.

4. Tarasov RS, Ganyukov VI. Prognostic role of initial and residual severity of coronary atherosclerosis in myocardial in farction patients undergoing primary percutaneous coronary intervention. Complex Issues of Cardiovascular Diseases. 2016; 5(4): 6-14. (In Russ). doi: 10.17802/2306-1278-2016-4-6-14.

5. Sutton RT, Pincock D, Baumgart DC, et al. An overview of clinical decision support systems: benefits, risks, and strategies for success. npj Digit Med. 2020; 3(1): 17. doi:10.1038/s41746-020-0221-y.

6. Shahzad R, Kirişli H, Metz C, et al. Automatic segmentation, detection and quantification of coronary artery stenoses on CTA. Int J Cardiovasc Imaging. 2013; 29(8): 1847-1859. doi:10.1007/s10554-0130271-1.

7. Wang C, Moreno R, Smedby Ö. Vessel Segmentation Using Implicit Model-Guided Level Sets. In: MICCAI 2012.

8. Broersen A, Kitslaar PH, Frenay M, et al. FrenchCoast: Fast, Robust Extraction for the Nice CHallenge on COronary Artery Segmentation of the Tree. 2012.

9. Wu W, Zhang J, Xie H, et al. Automatic detection of coronary artery stenosis by convolutional neural network with temporal constraint. Comput Biol Med. 2020; 118: 103657. doi:10.1016/j.compbiomed.2020.103657.

10. Leonova VO, Kochergina AM, Barbarash OL. Clinical Portrait of The Patient before the Planned Percutral Coronary Intervention in Conditions of Real Practice. Kardiologiia. 2020; 60(4): 31-35. (In Russ). doi: 10.18087/cardio.2020.4.n937.

11. Lobanov MG, Sholomov DL. On the acceleration of the convolutional neural network architecture based on resnet in the task of road scene objects recognition. 2019; 3: 57-65. (In Russ). doi:10.14357/20718632190305.

12. Rice L, Wong E, Kolter JZ. Overfitting in adversarially robust deep learning [Internet. 2020 [cited 2022 June 27 Available at: https://arxiv.org/abs/2002.11569.

13. Zaidi SSA, Ansari M.S, Aslam A, Kanwal N, Asghar M, Lee B. A Survey of Modern Deep Learning based Object Detection Models. [Internet. 2021 [cited 2022 June 27 Available at: https://arxiv.org/abs/2104.11892.

14. Brnabic A, Hess LM. Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making. BMC Med Inform Decis Mak. 2021; 21(1): 54. doi:10.1186/s12911-021-01403-2.

15. Jankovic I, Chen JH. Clinical Decision Support and Implications for the Clinician Burnout Crisis. Yearb Med Inform. 2020; 29(1): 145-154. doi:10.1055/s-0040-1701986.

16. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation [Internet. 2015 [cited 2022 Apr 29 Available at: https://arxiv.org/abs/1505.04597.