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
AI Automated Echocardiographic measurements – is this the future?
Session:
Sessão de Posters 05 - Ecocardiografia
Speaker:
Miguel Azaredo Raposo
Congress:
CPC 2024
Topic:
B. Imaging
Theme:
03. Imaging
Subtheme:
03.1 Echocardiography
Session Type:
Cartazes
FP Number:
---
Authors:
Miguel Azaredo Raposo; Ana Margarida Martins; Ana Beatriz Garcia; Catarina Simões Oliveira; Ana Abrantes; Catarina Gregório; Susana Gonçalves; Matthew Frost; Pierre Michel; Ana Almeida; Catarina Sousa; Fausto J. Pinto
Abstract
<h1 style="text-align:justify"><span style="font-size:16pt"><span style="font-family:"Calibri Light",sans-serif"><span style="color:#2f5496"><strong><span style="font-size:11pt"><span style="font-family:"Trebuchet MS",sans-serif"><span style="color:black">Introduction</span></span></span></strong></span></span></span></h1> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif">Echocardiography is a fundamental diagnostic modality for assessing cardiac function and structure. Demand for this exam is rising sharply, increasing the pressure on the health system. </span></span></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif">Acquiring adequate images takes experienced operators. Manually measuring standard dimensions, volumes and more complex parameters is a time-consuming task, subject to human error and interobserver variability.</span></span></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif">Deep learning algorithms have been developed, and validated, to automatically classify, segment, and annotate two-dimensional (2D) videos and Doppler modalities in standardized views. </span></span></span></span></span></p> <p style="text-align:start"> </p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><strong><span style="font-size:11pt"><span style="font-family:"Trebuchet MS",sans-serif">Aim</span></span></strong></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif">To compare acquired measurements, using a proprietary deep learning software (Us2.AI) with measurements obtained by experienced operators, when analyzing the same set of standardized views. </span></span></span></span></span></p> <p style="text-align:start"> </p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><strong><span style="font-size:11pt"><span style="font-family:"Trebuchet MS",sans-serif">Methods</span></span></strong></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif"> We compared results from 102 echocardiograms performed in a one-week time span. Standardized views were acquired by experienced operators, in the normal workflow of an echocardiography lab.</span></span></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif"> DICOM files were uploaded to the Us2.AI platform and subjected to automated assessment. We compared measurements of 24 parameters (table 1), regarding left ventricular (LV) volumetric assessment, wall thickness, mitral (MV) annular tissue Doppler and inflow pulsed Doppler, tricuspid regurgitation (TR) maximum velocity and aortic valve (AV) velocity and area assessment.</span></span></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif"> Mean absolute differences between automated and operator measurements were calculated. Pearson’s correlation test was applied. </span></span></span></span></span></p> <p style="text-align:start"> </p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><strong><span style="font-size:11pt"><span style="font-family:"Trebuchet MS",sans-serif">Results </span></span></strong></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif"> Very strong correlations (r. >0.9) were found between measurements of MV E, A and E’ waves, AV velocities and VTI, and TR pressure gradient. LVOT VTI, AV area and LV biplane volumes also showed strong correlations. Moderate correlations were found between LV 4 chamber volume measurements and ejection fraction (EF). E wave deceleration time showed the poorest correlation (r. 0.226). Mean absolute difference (MAD) in LV EF was 5,2%, a satisfactory result for an essential parameter, described to have an inter-observer variability of up to 14%. </span></span></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif">MAB in LV wall thickness was <2mm. Regarding AV assessment, MAD in AV vmax was <0,1m/s.</span></span></span></span></span></p> <p style="text-align:start"> </p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><strong><span style="font-size:11pt"><span style="font-family:"Trebuchet MS",sans-serif">Conclusion</span></span></strong></span></span></span></p> <p style="text-align:start"><span style="font-size:medium"><span style="font-family:Calibri,sans-serif"><span style="color:#000000"><span style="font-size:9pt"><span style="font-family:"Lucida Sans Unicode",sans-serif"> Automated measurements showed relatively small mean differences compared to conventional expert measurements. Strong and very strong correlations were observed for most parameters. This study strengthens and supports the use of automated measurements when applied in a real-world environment. The adoption of such validated tools may significantly reduce time per exam, and improve access to echocardiography, particularly in busy settings. </span></span></span></span></span></p> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div> <div> </div>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site