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
Refining the diagnosis of hypertrophic cardiomyopathy with a machine learning-based radiomics model: a cardiovascular magnetic resonance study
Session:
Comunicações Orais - Sessão 13 - Miocardiopatias
Speaker:
Inês Miranda
Congress:
CPC 2024
Topic:
F. Valvular, Myocardial, Pericardial, Pulmonary, Congenital Heart Disease
Theme:
17. Myocardial Disease
Subtheme:
17.3 Myocardial Disease – Diagnostic Methods
Session Type:
Comunicações Orais
FP Number:
---
Authors:
Inês Pereira De Miranda; Miguel Marques Antunes; Vera Ferreira; Mara Sarmento; Filipa Gerardo; Mariana Passos; Carolina Pereira Mateus; Joana Lima Lopes; Sílvia Aguiar Rosa; João Bicho Augusto
Abstract
<p style="text-align:justify"><span style="font-size:14px"><span style="font-family:Arial,Helvetica,sans-serif"><span style="color:#000000"><strong>Background: </strong>Cardiovascular magnetic resonance (CMR) plays a crucial role in the diagnosis of hypertrophic cardiomyopathy (HCM), but acquisition time can be long and some patients have contraindication to paramagnetic contrast, limiting the use of late gadolinium enhancement imaging. Simple, fast non-contrast single-shot fast spin echo black-blood (SS-FSE-BB) sequences can provide insights into the ultrastructure of the myocardium in HCM.</span></span></span></p> <p style="text-align:justify"><span style="font-size:14px"><span style="font-family:Arial,Helvetica,sans-serif"><span style="color:#000000"><strong>Objective: </strong>We aimed to analyze radiomics features in SS-FSE-BB sequences to identify ultrastructural characteristics of the myocardium to distinguish HCM patients from healthy controls.</span></span></span></p> <p style="text-align:justify"><span style="font-size:14px"><span style="font-family:Arial,Helvetica,sans-serif"><span style="color:#000000"><strong>Methods</strong>: We conducted a single-center study on 52 HCM patients who underwent CMR. SS-FSE-BB is widely used across MRI scanner vendors and acquired as a transaxial stack at the beginning of the scan (without contrast) with a <60s acquisition time. We excluded patients with poor imaging quality or missing the designated CMR sequence. The left ventricle (LV) was segmented using a semi-automated tool with minimal input from the user. A total of 107 radiomics features were extracted using the PyRadiomics v3.1.0 library which included first-order, textural, shape and size features. The same was done for 17 CMR scans from healthy volunteers (HVs). We first conducted correlation analyses with visualization of matrix, to exclude redundant/correlated features. Then we implemented a Machine Learning Random Forest Classifier (ML-RFC) model to provide insights into which features are most relevant in HCM versus HVs. </span></span></span></p> <p style="text-align:justify"><span style="font-size:14px"><span style="font-family:Arial,Helvetica,sans-serif"><span style="color:#000000"><strong>Results: </strong>A total of 46 HCM (60±15 years, 43.5% female) and 17 HVs (53±18 years, 58.8% female) scans were suitable for analysis. 56.5% of patients had septal HCM, 15.2% had apical HCM and 8.7% had mixed disease. The ML-RFC model showed a very high accuracy of 89% (summarized in Figure 1). HCM patients showed abnormal myocardial texture compared to HVs, with lower values of LV Coarseness (a lower value indicates a less uniform texture, median 0.0009 [IQR 0.0007-0.0013] vs 0.0026 [IQR 0.0023-0.0033], p<0.000001) and higher values of Dependence Non-uniformity (687 [578-810] vs 293 [257-343], p<0.000001). HCM patients presented LV shape features suggesting higher myocardial volume: higher voxel volume (225052 [162458-274457] vs 78131 [67597-89987], p<0.000001) and mesh volume (223912 [161483-273571] vs 76738 [65254-87213], p<0.000001), and lower surface area-volume ratio (0.183 [0.164-0.208] vs 0.355 [0.336-0.364], p<0.000001).</span></span></span></p> <p style="text-align:justify"><span style="font-size:14px"><span style="font-family:Arial,Helvetica,sans-serif"><span style="color:#000000"><strong>Conclusion: </strong>The complex structure of the LV wall through CMR radiomics conveys information far beyond conventional “human eye” imaging. Distinct features of myocardial heterogeneity can be found in HCM using routine sequences, acquired in the first minutes of the scan, without any contrast. These findings could enhance diagnostic and prognostic models in HCM, but require larger datasets and advanced modeling for validation.</span></span></span></p>
Slides
Our mission: To reduce the burden of cardiovascular disease
Visit our site