Learning Cardiac Magnetic Resonance

Imazio, Massimo; Andriani, Monica; Bodoni, Luisa Lobetti; Gaïta, Fiorenzo

doi:10.1007/978-3-030-11608-8

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 The added complexity further increases processing time and requires specialized knowledge of CHD. 10 A recent study utilizing a deep learning-based approach has enabled fully automated and fast segmentation of the aorta in adult 4D flow MRI examinations with performance similar to human observers. 8 However, this initial study, which employed a U-net convolutional neural network (CNN), has been limited to a single site and single vendor platform, and was only capable of identifying a single label or vascular territory (i.e., the thoracic aorta).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of the Aorta and Pulmonary Arteries Based on 4D Flow MRI in the Pediatric Setting Using Fully Automated Multi‐Site, Multi‐Vendor, and Multi‐Label Dense U‐Net

Fujiwara

Berhane

Scott

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Automated segmentation using convolutional neural networks (CNNs) have been developed using four‐dimensional (4D) flow magnetic resonance imaging (MRI). To broaden usability for congenital heart disease (CHD), training with multi‐institution data is necessary. However, the performance impact of heterogeneous multi‐site and multi‐vendor data on CNNs is unclear. Purpose To investigate multi‐site CNN segmentation of 4D flow MRI for pediatric blood flow measurement. Study Type Retrospective. Population A total of 174 subjects across two sites (female: 46%; N = 38 healthy controls, N = 136 CHD patients). Participants from site 1 (N = 100), site 2 (N = 74), and both sites (N = 174) were divided into subgroups to conduct 10‐fold cross validation (10% for testing, 90% for training). Field Strength/Sequence 3 T/1.5 T; retrospectively gated gradient recalled echo‐based 4D flow MRI. Assessment Accuracy of the 3D CNN segmentations trained on data from single site (single‐site CNNs) and data across both sites (multi‐site CNN) were evaluated by geometrical similarity (Dice score, human segmentation as ground truth) and net flow quantification at the ascending aorta (Qs), main pulmonary artery (Qp), and their balance (Qp/Qs), between human observers, single‐site and multi‐site CNNs. Statistical Tests Kruskal–Wallis test, Wilcoxon rank‐sum test, and Bland–Altman analysis. A P‐value <0.05 was considered statistically significant. Results No difference existed between single‐site and multi‐site CNNs for geometrical similarity in the aorta by Dice score (site 1: 0.916 vs. 0.915, P = 0.55; site 2: 0.906 vs. 0.904, P = 0.69) and for the pulmonary arteries (site 1: 0.894 vs. 0.895, P = 0.64; site 2: 0.870 vs. 0.869, P = 0.96). Qs site‐1 medians were 51.0–51.3 mL/cycle (P = 0.81) and site‐2 medians were 66.7–69.4 mL/cycle (P = 0.84). Qp site‐1 medians were 46.8–48.0 mL/cycle (P = 0.97) and site‐2 medians were 76.0–77.4 mL/cycle (P = 0.98). Qp/Qs site‐1 medians were 0.87–0.88 (P = 0.97) and site‐2 medians were 1.01–1.03 (P = 0.43). Bland–Altman analysis for flow quantification found equivalent performance. Data Conclusion Multi‐site CNN‐based segmentation and blood flow measurement are feasible for pediatric 4D flow MRI and maintain performance of single‐site CNNs. Level of Evidence 3 Technical Efficacy Stage 2

show abstract

mentioning

confidence: 99%

“…This is further complicated in pediatric patients with CHD, who can present with highly complex cardiac and great vessel anatomy 9 . The added complexity further increases processing time and requires specialized knowledge of CHD 10 …”

mentioning

confidence: 99%

Segmentation of the Aorta and Pulmonary Arteries Based on 4D Flow MRI in the Pediatric Setting Using Fully Automated Multi‐Site, Multi‐Vendor, and Multi‐Label Dense U‐Net

Fujiwara

Berhane

Scott

et al. 2021

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…Despite being widely known entities by the healthcare community, the prevalence of cardiac masses is less than 0.3% 1 , with a cumulative incidence of 13.8 cases per million people per year in the case of primary tumors 2 . The differential diagnosis of these neoplasms includes other cardiac masses, e.g., vegetations, thrombi, or myocardial hypertrophy 3 , as well as other entities such as vascular neoplasms or intrapericardial cysts.…”

Section: Introductionmentioning

confidence: 99%

Series of patients operated for masses and cysts in the heart in a Spanish general hospital: A 20-year experience

Gil-Korilis,

Esquíroz-Patiño,

Llamas-Llamazares

et al. 2023

An Sist Sanit Navar

View full text Add to dashboard Cite

Resumen Fundamento Las masas y quistes cardíacos son entidades bien conocidas, cuya reducida prevalencia y sintomatología inespecífica dificultan su diagnóstico. El objetivo del estudio fue caracterizar el cuadro de los pacientes afectos en nuestro medio para orientar futuros diagnósticos. Metodología Estudio descriptivo de los pacientes intervenidos de tumores y quistes cardíacos entre 2002 y 2022 mediante la búsqueda en el registro del Servicio de Cardiología y Cirugía Cardíaca de la Clínica Universidad de Navarra (Pamplona, España). Se recogieron variables sociodemográficas, clínicas, histológicas y quirúrgicas. Resultados Se identificaron 13 pacientes, la mayoría (76,92%) mujeres, con media de edad 63,08 años (DE: 15,17). El 92,31% de los pacientes tenían al menos un factor de riesgo cardiovascular, siendo los más prevalentes un IMC ≥25 kg/m 2 y la hipertensión arterial (61,54% y 53,85%, respectivamente). El tipo de masa cardíaca más frecuente fue el mixoma (69,23%). El 46,15% de masas cardiacas fueron hallazgos incidentales; el síntoma más frecuente fue la disnea (53,85%) y el 30,77% de los pacientes se encontraban asintomáticos. . La prueba de imagen más empleada para en el diagnóstico fue la ecocardiografía transtorácica Doppler color (69,23%). La concordancia entre los diámetros medios precirugía y postcirugía resultó muy alta (CCI = 0,807, IC95%: 0,450-0,943). Conclusiones Se describieron los cuadros de los pacientes, aportando información poco descrita en la literatura, como los factores de riesgo cardiovascular más frecuentes en estas entidades. Se describieron un caso de leiomiosarcoma cardíaco y un caso de sarcoma intimal del tronco pulmonar, dos tipos de tumores extremadamente raros de los que existen pocos casos descritos.

show abstract

Learning Cardiac Magnetic Resonance

Cited by 2 publications

References 0 publications

Segmentation of the Aorta and Pulmonary Arteries Based on 4D Flow MRI in the Pediatric Setting Using Fully Automated Multi‐Site, Multi‐Vendor, and Multi‐Label Dense U‐Net

Segmentation of the Aorta and Pulmonary Arteries Based on 4D Flow MRI in the Pediatric Setting Using Fully Automated Multi‐Site, Multi‐Vendor, and Multi‐Label Dense U‐Net

Series of patients operated for masses and cysts in the heart in a Spanish general hospital: A 20-year experience

Contact Info

Product

Resources

About