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
Comparison of radiomic feature stability between human segmentations and automatic segmentation tools.
Session:
Sessão de Posters 46 - TC Cardíaca
Speaker:
Fábio Sousa Nunes
Congress:
CPC 2024
Topic:
B. Imaging
Theme:
03. Imaging
Subtheme:
03.6 Cross-Modality and Multi-Modality Imaging Topics
Session Type:
Cartazes
FP Number:
---
Authors:
Fábio Sousa Nunes; Carolina Santos; João Pedrosa; Miguel Coimbra; Jennifer Mancio; Ricardo Fontes Carvalho
Abstract
<p><span style="font-size:11pt"><span style="font-family:Calibri,sans-serif">Introduction: Radiomic feature analysis is only clinically relevant if feature reproducibility is fair, despite different segmentation techniques. A critical step in proving the external reproducibility of any radiomic study is, thus, to verify that the radiomic features assessed are robust and do not vary significantly despite segmentation techniques.</span></span></p> <p><span style="font-size:11pt"><span style="font-family:Calibri,sans-serif">Methods: We segmented the cardiac area, as defined by the pericardial borders, in 312 non-contrast CT scans. These scans were all segmented by one human operator and one semi-automatic segmentation tool (Siemen’s Cardiac Risk Assessment tool) to assess inter-observer variability between manual and automatic segmentations (H1 v. S – human 1 vs. Siemens). 30 scans were then re-segmented by the same human operator (H1 vs. H1), to assess for intra-observer variability and 30 scans were segmented by another human operator (H1 vs. H2), to evaluate for inter-observer variability. Dice Similarity Coefficient (DICE) was used to assess the variability of segmentations between all comparisons. Intraclass coefficient correlation (ICC) was used to measure the variability between radiomic features extracted after segmentation by all the methods. </span></span></p> <p><span style="font-size:11pt"><span style="font-family:Calibri,sans-serif">Results: As assessed by DICE, segmentation reproducibility was excellent when performed by human operators (DICE=0.954 for H1 vs H1; DICE=0.925 for H1 vs. H2). Reproducibility was more minor when automatic tools were used, with a DICE=0.875 for H1 vs. S. Regarding the H1 vs. H1 comparison, a total of 94 in 107 radiomic features (87.85%) were considered reproducible (ICC = 0.92 ± 0.12 (mean±SD). Regarding the H1 vs. H2 comparison, 77 in 107 radiomic features (71.96%) were considered reproducible (ICC = 0.80 ± 0.25). Regarding the H1 vs. S comparison, 41 in 107 radiomic features (38.32%) were considered reproducible (ICC = 0.59 ± 0.31). Of all 107 cardiac features, only 40 were deemed reproducible across all three comparisons, with an ICC > 0.8 for all comparisons.</span></span></p> <p><span style="font-size:11pt"><span style="font-family:Calibri,sans-serif">Conclusions: We determined the most robust radiomic features among all comparisons. These 40 radiomic features have proven their internal validity and may be tested for external validity. </span></span></p>
Our mission: To reduce the burden of cardiovascular disease
Visit our site