RESUMEN
BACKGROUND: The clinico-oncological outcomes of precursor epithelial subtypes of adenocarcinoma arising from intraductal papillary mucinous neoplasms (A-IPMN) are limited to small cohort studies. Differences in recurrence patterns and response to adjuvant chemotherapy between A-IPMN subtypes are unknown. METHODS: Clincopathological features, recurrence patterns and long-term outcomes of patients undergoing pancreatic resection (2010-2020) for A-IPMN were reported from 18 academic pancreatic centres worldwide. Precursor epithelial subtype groups were compared using uni- and multivariate analysis. RESULTS: In total, 297 patients were included (median age, 70 years; male, 78.9%), including 54 (18.2%) gastric, 111 (37.3%) pancreatobiliary, 80 (26.9%) intestinal and 52 (17.5%) mixed subtypes. Gastric, pancreaticobiliary and mixed subtypes had comparable clinicopathological features, yet the outcomes were significantly less favourable than the intestinal subtype. The median time to recurrence in gastric, pancreatobiliary, intestinal and mixed subtypes were 32, 30, 61 and 33 months. Gastric and pancreatobiliary subtypes had worse overall recurrence (p = 0.048 and p = 0.049, respectively) compared with the intestinal subtype but gastric and pancreatobiliary subtypes had comparable outcomes. Adjuvant chemotherapy was associated with improved survival in the pancreatobiliary subtype (p = 0.049) but not gastric (p = 0.992), intestinal (p = 0.852) or mixed subtypes (p = 0.723). In multivariate survival analysis, adjuvant chemotherapy was associated with a lower likelihood of death in pancreatobiliary subtype, albeit with borderline significance [hazard ratio (HR) 0.56; 95% confidence interval (CI) 0.31-1.01; p = 0.058]. CONCLUSIONS: Gastric, pancreatobiliary and mixed subtypes have comparable recurrence and survival outcomes, which are inferior to the more indolent intestinal subtype. Pancreatobiliary subtype may respond to adjuvant chemotherapy and further research is warranted to determine the most appropriate adjuvant chemotherapy regimens for each subtype.
RESUMEN
BACKGROUND: Cardiovascular magnetic resonance (CMR) is increasingly utilized to evaluate expanding cardiovascular conditions. The Society for Cardiovascular Magnetic Resonance (SCMR) Registry is a central repository for real-world clinical data to support cardiovascular research, including those relating to outcomes, quality improvement, and machine learning. The SCMR Registry is built on a regulatory-compliant, cloud-based infrastructure that houses searchable content and Digital Imaging and Communications in Medicine images. The goal of this study is to summarize the status of the SCMR Registry at 150,000 exams. METHODS: The processes for data security, data submission, and research access are outlined. We interrogated the Registry and presented a summary of its contents. RESULTS: Data were compiled from 154,458 CMR scans across 20 United States sites, containing 299,622,066 total images (â¼100 terabytes of storage). Across reported values, the human subjects had an average age of 58 years (range 1 month to >90 years old), were 44% (63,070/145,275) female, 72% (69,766/98,008) Caucasian, and had a mortality rate of 8% (9,962/132,979). The most common indication was cardiomyopathy (35,369/131,581, 27%), and most frequently used current procedural terminology code was 75561 (57,195/162,901, 35%). Macrocyclic gadolinium-based contrast agents represented 89% (83,089/93,884) of contrast utilization after 2015. Short-axis cines were performed in 99% (76,859/77,871) of tagged scans, short-axis late gadolinium enhancement (LGE) in 66% (51,591/77,871), and stress perfusion sequences in 30% (23,241/77,871). Mortality data demonstrated increased mortality in patients with left ventricular ejection fraction <35%, the presence of wall motion abnormalities, stress perfusion defects, and infarct LGE, compared to those without these markers. There were 456,678 patient-years of all-cause mortality follow-up, with a median follow-up time of 3.6 years. CONCLUSION: The vision of the SCMR Registry is to promote evidence-based utilization of CMR through a collaborative effort by providing a web mechanism for centers to securely upload de-identified data and images for research, education, and quality control. The Registry quantifies changing practice over time and supports large-scale real-world multicenter observational studies of prognostic utility.
RESUMEN
4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive measurement technique capable of quantifying blood flow across the cardiovascular system. While practical use is limited by spatial resolution and image noise, incorporation of trained super-resolution (SR) networks has potential to enhance image quality post-scan. However, these efforts have predominantly been restricted to narrowly defined cardiovascular domains, with limited exploration of how SR performance extends across the cardiovascular system; a task aggravated by contrasting hemodynamic conditions apparent across the cardiovasculature. The aim of our study was therefore to explore the generalizability of SR 4D Flow MRI using a combination of existing super-resolution base models, novel heterogeneous training sets, and dedicated ensemble learning techniques; the latter-most being effectively used for improved domain adaption in other domains or modalities, however, with no previous exploration in the setting of 4D Flow MRI. With synthetic training data generated across three disparate domains (cardiac, aortic, cerebrovascular), varying convolutional base and ensemble learners were evaluated as a function of domain and architecture, quantifying performance on both in-silico and acquired in-vivo data from the same three domains. Results show that both bagging and stacking ensembling enhance SR performance across domains, accurately predicting high-resolution velocities from low-resolution input data in-silico. Likewise, optimized networks successfully recover native resolution velocities from downsampled in-vivo data, as well as show qualitative potential in generating denoised SR-images from clinicallevel input data. In conclusion, our work presents a viable approach for generalized SR 4D Flow MRI, with the novel use of ensemble learning in the setting of advanced fullfield flow imaging extending utility across various clinical areas of interest.
RESUMEN
BACKGROUND: Intraductal oncocytic papillary neoplasms (IOPNs) of the pancreas are now considered a separate entity to intraductal papillary mucinous neoplasms (IPMN). Invasive IOPNs are extremely rare, and their recurrence patterns, response to adjuvant chemotherapy and long-term survival outcomes are unknown. METHODS: Consecutive patients undergoing pancreatic resection (2010-2020) for invasive IOPNs or adenocarcinoma arising from IPMN (A-IPMN) from 18 academic pancreatic centers worldwide were included. Outcomes of invasive IOPNs were compared with A-IPMN invasive subtypes (ductal and colloid A-IPMN). RESULTS: 415 patients were included: 20 invasive IOPN, 331 ductal A-IPMN and 64 colloid A-IPMN. After a median follow-up of 6-years, 45% and 60% of invasive IOPNs had developed recurrence and died, respectively. There was no significant difference in recurrence or overall survival between invasive IOPN and ductal A-IPMN. Overall survival of invasive IOPNs was inferior to colloid A-IPMNs (median time of survival 24.4 months vs. 86.7, months, p = 0.013), but the difference in recurrence only showed borderline significance (median time to recurrence, 22.5 months vs. 78.5 months, p = 0.132). Adjuvant chemotherapy, after accounting for high-risk features, did not reduce rates of recurrence in invasive IOPN (p = 0.443), ductal carcinoma (p = 0.192) or colloid carcinoma (p = 0.574). CONCLUSIONS: Invasive IOPNs should be considered an aggressive cancer with a recurrence rate and prognosis consistent with ductal type A-IPMN.
RESUMEN
BACKGROUND: Echocardiography is widely used to evaluate left ventricular (LV) diastolic function in patients suspected of heart failure. For patients in sinus rhythm, a combination of several echocardiographic parameters can differentiate between normal and elevated LV filling pressure with good accuracy. However, there is no established echocardiographic approach for the evaluation of LV filling pressure in patients with atrial fibrillation. The objective of the present study was to determine if a combination of several echocardiographic and clinical parameters may be used to evaluate LV filling pressure in patients with atrial fibrillation. RESULTS: In a multicentre study of 148 atrial fibrillation patients, several echocardiographic parameters were tested against invasively measured LV filling pressure as the reference method. No single parameter had sufficiently strong association with LV filling pressure to be recommended for clinical use. Based on univariate regression analysis in the present study, and evidence from existing literature, we developed a two-step algorithm for differentiation between normal and elevated LV filling pressure, defining values ≥ 15 mmHg as elevated. The parameters in the first step included the ratio between mitral early flow velocity and septal mitral annular velocity (septal E/e'), mitral E velocity, deceleration time of E, and peak tricuspid regurgitation velocity. Patients who could not be classified in the first step were tested in a second step by applying supplementary parameters, which included left atrial reservoir strain, pulmonary venous systolic/diastolic velocity ratio, and body mass index. This two-step algorithm classified patients as having either normal or elevated LV filling pressure with 75% accuracy and with 85% feasibility. Accuracy in EF ≥ 50% and EF < 50% was similar (75% and 76%). CONCLUSIONS: In patients with atrial fibrillation, no single echocardiographic parameter was sufficiently reliable to be used clinically to identify elevated LV filling pressure. An algorithm that combined several echocardiographic parameters and body mass index, however, was able to classify patients as having normal or elevated LV filling pressure with moderate accuracy and high feasibility.
RESUMEN
BACKGROUND: Predictors of long-term survival after resection of adenocarcinoma arising from intraductal papillary mucinous neoplasms are unknown. This study determines predictors of long-term (>5 years) disease-free survival and recurrence in adenocarcinoma arising from intraductal papillary mucinous neoplasms and derives a prognostic model for disease-free survival. METHODS: Consecutive patients who underwent pancreatic resection for adenocarcinoma arising from intraductal papillary mucinous neoplasms in 18 academic pancreatic centers in Europe and Asia between 2010 to 2017 with at least 5-year follow-up were identified. Factors associated with disease-free survival were determined using Cox proportional hazards model. Internal validation was performed, and discrimination and calibration indices were assessed. RESULTS: In the study, 288 patients (median age, 70 years; 52% male) were identified; 140 (48%) patients developed recurrence after a median follow-up of 98 months (interquartile range, 78.4-123), 57 patients (19.8%) developed locoregional recurrence, and 109 patients (37.8%) systemic recurrence. At 5 years after resection, the overall and disease-free survival was 46.5% (134/288) and 35.0% (101/288), respectively. On Cox proportional hazards model analysis, multivisceral resection (hazard ratio, 2.20; 95% confidence interval, 1.06-4.60), pancreatic tail location (hazard ratio, 2.34; 95% confidence interval, 1.22-4.50), poor tumor differentiation (hazard ratio, 2.48; 95% confidence interval, 1.10-5.30), lymphovascular invasion (hazard ratio, 1.74; 95% confidence interval, 1.06-2.88), and perineural invasion (hazard ratio, 1.83; 95% confidence interval, 1.09-3.10) were negatively associated with long-term disease-free survival. The final predictive model incorporated 8 predictors and demonstrated good predictive ability for disease-free survival (C-index, 0.74; calibration, slope 1.00). CONCLUSION: A third of patients achieve long-term disease-free survival (>5 years) after pancreatic resection for adenocarcinoma arising from intraductal papillary mucinous neoplasms. The predictive model developed in the current study can be used to estimate the probability of long-term disease-free survival.
Asunto(s)
Recurrencia Local de Neoplasia , Pancreatectomía , Neoplasias Pancreáticas , Humanos , Masculino , Femenino , Anciano , Neoplasias Pancreáticas/cirugía , Neoplasias Pancreáticas/mortalidad , Neoplasias Pancreáticas/patología , Persona de Mediana Edad , Pronóstico , Pancreatectomía/mortalidad , Supervivencia sin Enfermedad , Recurrencia Local de Neoplasia/epidemiología , Estudios Retrospectivos , Carcinoma Ductal Pancreático/cirugía , Carcinoma Ductal Pancreático/mortalidad , Carcinoma Ductal Pancreático/patología , Adenocarcinoma Mucinoso/cirugía , Adenocarcinoma Mucinoso/patología , Adenocarcinoma Mucinoso/mortalidad , Modelos de Riesgos Proporcionales , Neoplasias Intraductales Pancreáticas/cirugía , Neoplasias Intraductales Pancreáticas/patología , Neoplasias Intraductales Pancreáticas/mortalidad , Estudios de Seguimiento , Europa (Continente)/epidemiología , Adenocarcinoma/cirugía , Adenocarcinoma/mortalidad , Adenocarcinoma/patología , Tasa de Supervivencia , Anciano de 80 o más AñosRESUMEN
AIMS: Standard methods of heart chamber volume estimation in cardiovascular magnetic resonance (CMR) typically utilize simple geometric formulae based on a limited number of slices. We aimed to evaluate whether an automated deep learning neural network prediction of 3D anatomy of all four chambers would show stronger associations with cardiovascular risk factors and disease than standard volume estimation methods in the UK Biobank. METHODS: A deep learning network was adapted to predict 3D segmentations of left and right ventricles (LV, RV) and atria (LA, RA) at â¼1mm isotropic resolution from CMR short and long axis 2D segmentations obtained from a fully automated machine learning pipeline in 4723 individuals with cardiovascular disease (CVD) and 5733 without in the UK Biobank. Relationships between volumes at end-diastole (ED) and end-systole (ES) and risk/disease factors were quantified using univariate, multivariate and logistic regression analyses. Strength of association between deep learning volumes and standard volumes was compared using the area under the receiving operator characteristic curve (AUC). RESULTS: Univariate and multivariate associations between deep learning volumes and most risk and disease factors were stronger than for standard volumes (higher R2 and more significant P values), particularly for sex, age, and body mass index. AUC for all logistic regressions were higher for deep learning volumes than standard volumes (p<0.001 for all four chambers at ED and ES). CONCLUSIONS: Neural network reconstructions of whole heart volumes had significantly stronger associations with cardiovascular disease and risk factors than standard volume estimation methods in an automatic processing pipeline.
RESUMEN
BACKGROUND: The clinical impact of adjuvant chemotherapy after resection for adenocarcinoma arising from intraductal papillary mucinous neoplasia is unclear. The aim of this study was to identify factors related to receipt of adjuvant chemotherapy and its impact on recurrence and survival. METHODS: This was a multicentre retrospective study of patients undergoing pancreatic resection for adenocarcinoma arising from intraductal papillary mucinous neoplasia between January 2010 and December 2020 at 18 centres. Recurrence and survival outcomes for patients who did and did not receive adjuvant chemotherapy were compared using propensity score matching. RESULTS: Of 459 patients who underwent pancreatic resection, 275 (59.9%) received adjuvant chemotherapy (gemcitabine 51.3%, gemcitabine-capecitabine 21.8%, FOLFIRINOX 8.0%, other 18.9%). Median follow-up was 78 months. The overall recurrence rate was 45.5% and the median time to recurrence was 33 months. In univariable analysis in the matched cohort, adjuvant chemotherapy was not associated with reduced overall (P = 0.713), locoregional (P = 0.283) or systemic (P = 0.592) recurrence, disease-free survival (P = 0.284) or overall survival (P = 0.455). Adjuvant chemotherapy was not associated with reduced site-specific recurrence. In multivariable analysis, there was no association between adjuvant chemotherapy and overall recurrence (HR 0.89, 95% c.i. 0.57 to 1.40), disease-free survival (HR 0.86, 0.59 to 1.30) or overall survival (HR 0.77, 0.50 to 1.20). Adjuvant chemotherapy was not associated with reduced recurrence in any high-risk subgroup (for example, lymph node-positive, higher AJCC stage, poor differentiation). No particular chemotherapy regimen resulted in superior outcomes. CONCLUSION: Chemotherapy following resection of adenocarcinoma arising from intraductal papillary mucinous neoplasia does not appear to influence recurrence rates, recurrence patterns or survival.
Asunto(s)
Recurrencia Local de Neoplasia , Pancreatectomía , Neoplasias Pancreáticas , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adenocarcinoma/patología , Adenocarcinoma/tratamiento farmacológico , Adenocarcinoma/mortalidad , Adenocarcinoma/terapia , Adenocarcinoma Mucinoso/patología , Adenocarcinoma Mucinoso/tratamiento farmacológico , Adenocarcinoma Mucinoso/terapia , Adenocarcinoma Mucinoso/mortalidad , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapéutico , Capecitabina/administración & dosificación , Capecitabina/uso terapéutico , Carcinoma Ductal Pancreático/patología , Carcinoma Ductal Pancreático/mortalidad , Carcinoma Ductal Pancreático/tratamiento farmacológico , Carcinoma Ductal Pancreático/terapia , Carcinoma Ductal Pancreático/cirugía , Quimioterapia Adyuvante , Gemcitabina , Recurrencia Local de Neoplasia/epidemiología , Neoplasias Intraductales Pancreáticas/patología , Neoplasias Intraductales Pancreáticas/terapia , Neoplasias Intraductales Pancreáticas/mortalidad , Neoplasias Intraductales Pancreáticas/cirugía , Neoplasias Pancreáticas/patología , Neoplasias Pancreáticas/tratamiento farmacológico , Neoplasias Pancreáticas/mortalidad , Neoplasias Pancreáticas/terapia , Neoplasias Pancreáticas/cirugía , Puntaje de Propensión , Estudios RetrospectivosRESUMEN
Background: Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods: A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results: Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions: Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.
RESUMEN
Background: A reduced left atrial (LA) strain correlates with the presence of atrial fibrillation (AF). Conventional atrial strain analysis uses two-dimensional (2D) imaging, which is, however, limited by atrial foreshortening and an underestimation of through-plane motion. Retrospective gated computed tomography (RGCT) produces high-fidelity three-dimensional (3D) images of the cardiac anatomy throughout the cardiac cycle that can be used for estimating 3D mechanics. Its feasibility for LA strain measurement, however, is understudied. Aim: The aim of this study is to develop and apply a novel workflow to estimate 3D LA motion and calculate the strain from RGCT imaging. The utility of global and regional strains to separate heart failure in patients with reduced ejection fraction (HFrEF) with and without AF is investigated. Methods: A cohort of 30 HFrEF patients with (n = 9) and without (n = 21) AF underwent RGCT prior to cardiac resynchronisation therapy. The temporal sparse free form deformation image registration method was optimised for LA feature tracking in RGCT images and used to estimate 3D LA endocardial motion. The area and fibre reservoir strains were calculated over the LA body. Universal atrial coordinates and a human atrial fibre atlas enabled the regional strain calculation and the fibre strain calculation along the local myofibre orientation, respectively. Results: It was found that global reservoir strains were significantly reduced in the HFrEF + AF group patients compared with the HFrEF-only group patients (area strain: 11.2 ± 4.8% vs. 25.3 ± 12.6%, P = 0.001; fibre strain: 4.5 ± 2.0% vs. 15.2 ± 8.8%, P = 0.001), with HFrEF + AF patients having a greater regional reservoir strain dyssynchrony. All regional reservoir strains were reduced in the HFrEF + AF patient group, in whom the inferior wall strains exhibited the most significant differences. The global reservoir fibre strain and LA volume + posterior wall reservoir fibre strain exceeded LA volume alone and 2D global longitudinal strain (GLS) for AF classification (area-under-the-curve: global reservoir fibre strain: 0.94 ± 0.02, LA volume + posterior wall reservoir fibre strain: 0.95 ± 0.02, LA volume: 0.89 ± 0.03, 2D GLS: 0.90 ± 0.03). Conclusion: RGCT enables 3D LA motion estimation and strain calculation that outperforms 2D strain metrics and LA enlargement for AF classification. Differences in regional LA strain could reflect regional myocardial properties such as atrial fibrosis burden.
RESUMEN
OBJECTIVE: The aim of the present study was to compare long-term post-resection oncological outcomes between A-IPMN and PDAC. SUMMARY BACKGROUND DATA: Knowledge of long term oncological outcomes (e.g recurrence and survival data) comparing between adenocarcinoma arising from intraductal papillary mucinous neoplasms (A-IPMN) and pancreatic ductal adenocarcinoma (PDAC) is scarce. METHODS: Patients undergoing pancreatic resection (2010-2020) for A-IPMN were identified retrospectively from 18 academic pancreatic centres and compared with PDAC patients from the same time-period. Propensity-score matching (PSM) was performed and survival and recurrence were compared between A-IPMN and PDAC. RESULTS: 459 A-IPMN patients (median age,70; M:F,250:209) were compared with 476 PDAC patients (median age,69; M:F,262:214). A-IPMN patients had lower T-stage, lymphovascular invasion (51.4%vs. 75.6%), perineural invasion (55.8%vs. 71.2%), lymph node positivity (47.3vs. 72.3%) and R1 resection (38.6%vs. 56.3%) compared to PDAC(P<0.001). The median survival and time-to-recurrence for A-IPMN versus PDAC were 39.0 versus19.5months (P<0.001) and 33.1 versus 14.8months (P<0.001), respectively (median follow-up,78 vs.73 months). Ten-year overall survival for A-IPMN was 34.6%(27/78) and PDAC was 9%(6/67). A-IPMN had higher rates of peritoneal (23.0 vs. 9.1%, P<0.001) and lung recurrence (27.8% vs. 15.6%, P<0.001) but lower rates of locoregional recurrence (39.7% vs. 57.8%; P<0.001). Matched analysis demonstrated inferior overall survival (P=0.005), inferior disease-free survival (P=0.003) and higher locoregional recurrence (P<0.001) in PDAC compared to A-IPMN but no significant difference in systemic recurrence rates (P=0.695). CONCLUSIONS: PDACs have inferior survival and higher recurrence rates compared to A-IPMN in matched cohorts. Locoregional recurrence is higher in PDAC but systemic recurrence rates are comparable and constituted by their own distinctive site-specific recurrence patterns.
RESUMEN
Universal coordinate systems have been proposed to facilitate anatomic registration between three-dimensional images, data and models of the ventricles of the heart. However, current universal ventricular coordinate systems do not account for the outflow tracts and valve annuli where the anatomy is complex. Here we propose an extension to the 'Cobiveco' biventricular coordinate system that also accounts for the intervalvular bridges of the base and provides a tool for anatomically consistent registration between widely varying biventricular shapes. CobivecoX uses a novel algorithm to separate intervalvular bridges and assign new coordinates, including an inflow-outflow coordinate, to describe local positions in these regions uniquely and consistently. Anatomic consistency of registration was validated using curated three-dimensional biventricular shape models derived from cardiac MRI measurements in normal hearts and hearts from patients with congenital heart diseases. This new method allows the advantages of universal cardiac coordinates to be used for three-dimensional ventricular imaging data and models that include the left and right ventricular outflow tracts and valve annuli.
Asunto(s)
Catéteres , Cardiopatías Congénitas , Humanos , Cardiopatías Congénitas/diagnóstico por imagen , Corazón , Ventrículos Cardíacos/diagnóstico por imagen , AlgoritmosRESUMEN
Large-cohort studies using cardiovascular imaging and diagnostic datasets have assessed cardiac anatomy, function, and outcomes, but typically do not reveal underlying biological mechanisms. Cardiac digital twins (CDTs) provide personalized physics- and physiology-constrained in-silico representations, enabling inference of multi-scale properties tied to these mechanisms. We constructed 3464 anatomically-accurate CDTs using cardiac magnetic resonance images from UK biobank and personalised their myocardial conduction velocities (CVs) from electrocardiograms (ECG), through an automated framework. We found well-known sex-specific differences in QRS duration were fully explained by myocardial anatomy, as CV remained consistent across sexes. Conversely, significant associations of CV with ageing and increased BMI suggest myocardial tissue remodelling. Novel associations were observed with left ventricular ejection fraction and mental-health phenotypes, through a phenome-wide association study, and CV was also linked with adverse clinical outcomes. Our study highlights the utility of population-based CDTs in assessing intersubject variability and uncovering strong links with mental health.
RESUMEN
BACKGROUND: Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. METHODS: Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. RESULTS: The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. CONCLUSIONS: Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
Asunto(s)
Enfermedades Cardiovasculares , Sistema Cardiovascular , Humanos , Angiografía por Resonancia Magnética , Valor Predictivo de las Pruebas , Corazón , Procesamiento de Imagen Asistido por ComputadorRESUMEN
Abstract Background: Cardiac Magnetic Resonance is in need of a simple and robust method for diastolic function assessment that can be done with routine protocol sequences. Objective: To develop and validate a three-dimensional (3D) model-based volumetric assessment of diastolic function using cardiac magnetic resonance (CMR) imaging and compare the results obtained with the model with those obtained by echocardiography. Methods: The study participants provided written informed consent and were included if having undergone both echocardiography and cine steady-state free precession (SSFP) CMR on the same day. Guide points at the septal and lateral mitral annulus were used to define the early longitudinal relaxation rate (E'), while a time-volume curve from the 3D model was used to assess diastolic filling parameters. We determined the correlation between 3D CMR and echocardiography and the accuracy of CMR in classifying the diastolic function grade. Results: The study included 102 subjects. The E/A ratio by CMR was positively associated with the E/A ratio by echocardiography (r = 0.71, p < 0.0001). The early diastolic relaxation velocity by tissue Doppler and longitudinal relaxation rate for the lateral mitral annulus displacement were positively associated (p = 0.007), as were the ratio between Doppler E/e' and CMR E/E' (p = 0.01). CMR-determined normalized peak E (NE) and deceleration time (DT) were able to predict diastolic dysfunction (areas under the curve [AUCs] = 0.70 and 0.72, respectively). In addition, the lateral E/E' ratio showed good utility in identifying diastolic dysfunction (AUC = 0.80). Overall, echocardiography and CMR interobserver and intraobserver agreements were excellent (intraclass correlation coefficient range 0.72 - 0.97). Conclusion: 3D modeling of standard cine CMR images was able to identify study subjects with reduced diastolic function and showed good reproducibility, suggesting a potential for a routine diastolic function assessment by CMR.
Resumo Fundamento: A ressonância magnética cardíaca necessita de um método simples e robusto para a avaliação da função diastólica que pode ser feito com sequências protocolares de rotina. Objetivo: Desenvolver e validar a avaliação volumétrica da função diastólica através de um modelo tridimensional (3D) com utilização de imagens de ressonância magnética cardíaca (RMC) e comparar os resultados obtidos com este modelo com os obtidos por ecocardiografia. Métodos: Os participantes do estudo assinaram um termo de consentimento e foram incluídos se tivessem sido submetidos no mesmo dia tanto à ecocardiografia quanto à cine RMC com precessão livre no estado estacionário (steady-state free precession, SSFP). Pontos-guia foram utilizados no anel mitral septal e lateral para definir a velocidade de estiramento no início da diástole (E'), enquanto curvas de volume-tempo do modelo 3D foram utilizadas para avaliar os parâmetros de enchimento diastólico. Foram determinadas a correlação entre a RMC 3D e a ecocardiografia, além da acurácia da RMC em classificar o grau de função diastólica. Resultados: Ao todo, 102 sujeitos foram incluídos no estudo. A razão E/A pela RMC esteve positivamente associada com a razão E/A obtida pela ecocardiografia (r = 0,71, p < 0,0001). Estiveram positivamente associadas a velocidade de relaxamento diastólico inicial ao Doppler tecidual e a velocidade de relaxamento longitudinal de deslocamento do anel mitral lateral (p = 0,007), bem como a razão entre E/e' por Doppler e E/E' pela RMC (p = 0,01). A velocidade normalizada de pico de enchimento (EM) determinada pela RMC e o tempo de desaceleração (TD) foram capazes de predizer a disfunção diastólica (áreas sob a curva [AUCs] = 0,70 e 0,72, respectivamente). Além disso, a razão E/E' lateral mostrou boa utilidade para a identificação da disfunção diastólica (AUC = 0,80). No geral, a ecocardiografia e a RMC apresentaram excelente concordância interobservador e intraobservador (coeficiente de correlação intraclasse 0,72 - 0,97). Conclusão: Uma modelagem 3D de imagens padrões de cine RMC foi capaz de identificar os indivíduos do estudo com função diastólica reduzida e mostrou uma boa reprodutibilidade, sugerindo ter potencial na avaliação rotineira da função diastólica por RMC.