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
Development of deep learning segmentation models for coronary X-Ray angiography: performance assessment by new clinical criteria score and comparison with human performance
Session:
Comunicações Orais (Sessão 19) - Prémio Jovem Investigador - Investigação Clínica
Speaker:
Beatriz Valente Silva
Congress:
CPC 2022
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 Silva; Miguel Nobre Menezes; João Lourenço; Tiago Rodrigues; Ana Rita Francisco; Pedro Carrilho Ferreira; Arlindo Oliveira; Fausto j. Pinto
Abstract
<p style="margin-left:-47px; margin-right:-37px"><span style="font-size:12pt"><span style="font-family:"Times New Roman",serif"><strong><span style="font-size:10.0pt"><span style="font-family:"Arial",sans-serif">Int</span></span></strong></span></span></p> <p><strong>Introduction</strong>: Artificial intelligence applied to invasive coronary angiography is underexplored. Few publications explored automatic invasive coronary angiography segmentation, arguably the first step for future clinical application. None have provided an appreciation of the results using clinical experts’ criteria.</p> <p>The purpose of this study was to develop artificial intelligence models for invasive coronary angiography segmentation and assess the results with a set of criteria clinically defined by a panel of Interventional Cardiologists.</p> <p><strong>Methods</strong>: Patients undergoing invasive coronary angiography and physiology assessment were randomly selected. Per incidence, an ideal frame was segmented by trained physicians, forming a baseline human dataset. A baseline artificial intelligence model was then trained. An enhanced human segmentation was created combining the best of baseline human model, baseline artificial intelligence model and additional human segmentation as needed. An enhanced artificial intelligence model was trained with the enhanced human model dataset - Figure 1A and 1B.</p> <p>Results were assessed by three Interventional Cardiologists with eleven criteria, combined into a Global Segmentation Score (GSS: 0 – 100 points), where each criteria’s relevance was weighted - Figure 1C.</p> <p><strong>Results</strong>: We included 416 images from 69 patients. Global Segmentation Score for baseline human dataset, enhanced human segmentation, baseline artificial intelligence model and enhanced artificial intelligence model were 96,9 ± 5,7; 98,9 ± 3,1; 86,1 ± 10,1 and 90 ± 7,6, respectively (p< 0,001 for both paired and global differences) – Figure 1D.</p> <p>The enhanced artificial intelligence model outperformed the baseline artificial intelligence model in coronary segmentation, catheter to coronary transition and catheter thickness, but performed less well in other catheter tasks. </p> <p><strong>Conclusions</strong>: The use of Global Segmentation Score and its criteria was feasible. Artificial intelligence models performed very well. Human models were superior to artificial intelligence models, but only enhanced human segmentation achieved a near perfect Global Segmentation Score.</p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site