Login
Search
Search
0 Dates
2024
2023
2022
2021
2020
2019
2018
0 Events
CPC 2018
CPC 2019
Curso de Atualização em Medicina Cardiovascular 2019
Reunião Anual Conjunta dos Grupos de Estudo de Cirurgia Cardíaca, Doenças Valvulares e Ecocardiografia da SPC
CPC 2020
CPC 2021
CPC 2022
CPC 2023
CPC 2024
0 Topics
A. Basics
B. Imaging
C. Arrhythmias and Device Therapy
D. Heart Failure
E. Coronary Artery Disease, Acute Coronary Syndromes, Acute Cardiac Care
F. Valvular, Myocardial, Pericardial, Pulmonary, Congenital Heart Disease
G. Aortic Disease, Peripheral Vascular Disease, Stroke
H. Interventional Cardiology and Cardiovascular Surgery
I. Hypertension
J. Preventive Cardiology
K. Cardiovascular Disease In Special Populations
L. Cardiovascular Pharmacology
M. Cardiovascular Nursing
N. E-Cardiology / Digital Health, Public Health, Health Economics, Research Methodology
O. Basic Science
P. Other
0 Themes
01. History of Cardiology
02. Clinical Skills
03. Imaging
04. Arrhythmias, General
05. Atrial Fibrillation
06. Supraventricular Tachycardia (non-AF)
07. Syncope and Bradycardia
08. Ventricular Arrhythmias and Sudden Cardiac Death (SCD)
09. Device Therapy
10. Chronic Heart Failure
11. Acute Heart Failure
12. Coronary Artery Disease (Chronic)
13. Acute Coronary Syndromes
14. Acute Cardiac Care
15. Valvular Heart Disease
16. Infective Endocarditis
17. Myocardial Disease
18. Pericardial Disease
19. Tumors of the Heart
20. Congenital Heart Disease and Pediatric Cardiology
21. Pulmonary Circulation, Pulmonary Embolism, Right Heart Failure
22. Aortic Disease
23. Peripheral Vascular and Cerebrovascular Disease
24. Stroke
25. Interventional Cardiology
26. Cardiovascular Surgery
27. Hypertension
28. Risk Factors and Prevention
29. Rehabilitation and Sports Cardiology
30. Cardiovascular Disease in Special Populations
31. Pharmacology and Pharmacotherapy
32. Cardiovascular Nursing
33. e-Cardiology / Digital Health
34. Public Health and Health Economics
35. Research Methodology
36. Basic Science
37. Miscellanea
0 Resources
Abstract
Slides
Vídeo
Report
CLEAR FILTERS
Enhancing the eyes of interventional cardiologists: impact of artifical intelligence in operator assessment of coronary lesions
Session:
Comunicações Orais - Sessão 19 - Saúde Digital e Economia da Saúde
Speaker:
Beatriz Valente Silva
Congress:
CPC 2023
Topic:
N. E-Cardiology / Digital Health, Public Health, Health Economics, Research Methodology
Theme:
33. e-Cardiology / Digital Health
Subtheme:
33.4 Digital Health
Session Type:
Comunicações Orais
FP Number:
---
Authors:
Beatriz Valente Silva; Miguel Nobre Menezes; João Lourenço Silva; Tiago Rodrigues; João Silva Marques; Cláudio Guerreiro; João Pedro Guedes; Manuel Oliveira Santos; Arlindo L Oliveira; Fausto J Pinto
Abstract
<p style="text-align:justify"><strong>Introduction</strong>: The assessment of the severity of coronary stenosis is essential for revascularization decisions. Percentage stenosis can be assessed by visual assessment (%DSVE) or quantitative coronary angiography (QCA). However, multiple studies have shown that visual inspection tend to overestimate the percent diameter stenosis compared to QCA. We have previously developed an artificial intelligence (AI) model capable of accurate coronary angiography segmentation. In this study we aimed to assess the impact of segmentation in the operators’ perception of lesion severity, by comparing the %DSVE evaluated by angiography vs AI-segmented images.</p> <p style="text-align:justify"><strong>Methods</strong>: Multicentric retrospective study of pts undergoing PCI or invasive physiology in four Portuguese centres. QCA was assessed with a validated software in the angiography images. A dedicated python script was written for measuring the diameters in the AI-segmented images, thus excluding differences between the two image groups. Operators then blindly assessed %DSVE in both the angiography and segmented images, in random order, with two separate sessions (at least a week apart) for each image group. Angiography QCA was used as reference.</p> <p style="text-align:justify"><strong>Results</strong>: We included 123 lesions from a total of 90 patients. There were no significant differences between the angiography and AI-segmented images: the median difference in lesion diameter was 0,1 mm and the mean QCA was 56 +/- 13% vs 55 +/- 13% (p = 0,071) in the angiography vs AI-segmented images, respectively. Thus, operators were able to proceed with %DSVE estimation because differences could only be attributed to visual perception rather than actual differences between the two groups.</p> <p style="text-align:justify">When considering QCA as reference, operators tended to overestimate lesion severity in angiography images (77% ± 20% vs 56% ± 13%, p< 0.001) to a much greater degree than with segmentation (59% ± 20% vs 56% ± 13%, p< 0.001).</p> <p style="text-align:justify">For lesions with a QCA between 50 and 70%, an even higher discrepancy was found (angiography: 83% ±13% vs 60% ± 5%, p<0.001; segmentation: 63% ±15% vs 60% ± 5%, p< 0.001). Similar findings were observed for QCA < 50% lesions. For lesions with a %DSQCA >70%, visual estimation was usually in agreement with QCA in both groups.</p> <p>Agreement between visual estimation and QCA across QCA strata (<50%, 50-70%, >70%) was approximately double in the segmentation group (60% vs 30%; p<0,001). Operator heterogeneity was also reduced with segmentation.</p> <p style="text-align:justify"><strong>Conclusion</strong>: Our study suggests that visualization of segmented images seems to render visual estimation of stenosis severity more objective, significantly reducing the tendency to overestimate, while reducing operator heterogeneity. The visual assessment of coronary lesions with segmented images may therefore lead to a lower likelihood of unwarranted revascularization, while potentially increasing the use of functional assessment, as recommended by current guidelines.</p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site