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
Automatic Quality Assessment of Focused Cardiac Ultrasound Exams
Session:
Posters (Sessão 4 - Écran 3) - Imagem multimodal 1
Speaker:
Catarina Rodrigues
Congress:
CPC 2023
Topic:
B. Imaging
Theme:
03. Imaging
Subtheme:
03.6 Cross-Modality and Multi-Modality Imaging Topics
Session Type:
Pósters Electrónicos
FP Number:
---
Authors:
Catarina Rodrigues; Bárbara Malainho; Ana Cláudia Tonelli; Cátia Costa Oliveira; André Santanchè; Marco A. Carvalho-Filho; Jaime C. Fonseca; Vítor Hugo Pereira; Sandro Queirós
Abstract
<p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif"><strong>Introduction:</strong> Focused cardiac ultrasound (FoCUS) is being increasingly used at the bedside to enable faster and more accurate decision making. This brings to the frontline the need to provide appropriate training in this technique. However, the lack of people with expertise hampers the massive training of physicians in FoCUS. </span></span></p> <p style="text-align:justify"><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif"><strong>Objectives:</strong> To overcome this limitation, this work aimed at developing an AI-based automatic tool to assess the quality of a FoCUS acquisition. </span></span></p> <p style="text-align:justify"><strong><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif">Methods and Results: </span></span></strong><span style="font-size:12pt"><span style="font-family:Calibri,sans-serif">We used a database which consists of saved clips from examinations performed by residents in FoCUS training. The first stage of the development was the classification of each recorded loop into one of seven FoCUS views, where a total of 4029 videos from 713 exams were used. To do so, a 3D neural network architecture based on the ResNet-18 was proposed, along with a training strategy that leverages of domain knowledge into the augmentation scheme and a multi-clip inference routine. This pipeline and the blocks it entails were evaluated in an extensive set of experiments, showing its accuracy and robustness. In a held-out test set (615 videos from 119 exams), the proposal achieved a Matthew's correlation coefficient (MCC) of 0.9569 and an accuracy of 95.01% (macro-averaged F1-score). Upon being separated by views, each video is then passed through view-specific models that assess a variety of quality attributes and provide an overall acquisition quality score. The quality feedback focuses on features such as image gain, acquisition depth, and the presence of the necessary anatomical references in each cardiac window. At this stage, the current quality assessment work focused in the subxiphoid, apical four-chamber and inferior vena cava views. For this, 819, 1168 and 1073 videos of each view, respectively, were used and annotated regarding a total of 24 attributes across the three views. Despite affected by class imbalance and noisy labels, the proposed models achieved an average MCC of 0.6024 and an average F1-score of 0.7243 on the held-out test set. </span></span></p> <p><span style="font-size:12.0pt"><span style="font-family:"Calibri",sans-serif"><strong>Conclusion:</strong> This automatic pipeline proved its feasibility. In the future, one believes it may be used to support medical professionals performing FoCUS in clinical practice, accelerating their training even in workplaces where this expertise is not available.</span></span></p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site