Improvement in left atrial strain following ferric carboxymaltose in heart failure: an analysis of the Myocardial-IRON trial.

AIMS: Iron deficiency (ID) is associated with an impaired cardiac function and remodelling in heart failure (HF). Treatment with ferric carboxymaltose (FCM) has been showed recently to improve biventricular systolic function and ventricular strain parameters in patients with HF with reduced ejection fraction and ID, but there is no evidence on the benefit of FCM on the left atrium (LA). In this study, we aimed to evaluate the effect of FCM on LA longitudinal strain (LA-LS). METHODS AND RESULTS: This is a post hoc subanalysis of a double-blind, placebo-controlled, randomized clinical trial that enrolled 53 ambulatory patients with HF, left ventricular ejection fraction (LVEF) < 50%, and ID [Myocardial-IRON trial (NCT03398681)], treated with FCM or placebo. Cardiac magnetic resonance-featured tracking (CMR-FT) strain changes were evaluated before and 7 and 30 days after randomization using linear mixed regression analysis. The median age of the sample was 68 years (interquartile range: 64-76), and 20 (69%) were men. Mean ± standard deviation of LVEF was 39 ± 11%, and most (97%) were in stable New York Heart Association class II. At baseline, mean LA-LS was -8.9 ± 3.5%. At 30 days, and compared with placebo, LA-LS significantly improved in those allocated to FCM treatment arm (LA-LS = -12.0 ± 0.5 and -8.5 ± 0.6, respectively; - ∆ 3.55%, P < 0.001). CONCLUSIONS: In patients with stable HF, LVEF < 50%, and ID, treatment with FCM was associated with short-term improvements in LA-LS assessed by CMR-FT. Future works should assess the potential benefit of iron repletion on LA function.

Breast Cancer Diagnosis Using Texture and Shape Features in MRI.

Contrast-enhanced magnetic resonance (MR) breast imaging represents a tool with great potential for the detection, evaluation and diagnosis of breast cancer (BC). Due to its high sensitivity and in combination with medical imaging biomarkers, it can overcome setbacks and limitations manifested in other diagnostic modalities such as mammography or ultrasound. In order to aid and assist clinicians in the diagnosis of BC, a methodology based on the extraction of 2D texture and 3D shape features in MR images is proposed. To categorize breast tumor malignancy, we considered its location in the coronal plane, divided into 4 quadrants (UOQ, UIQ, LOQ and LOQ), and the tumor type according to its genetic information (positive HER2 and Luminal B with negative HER2). In this regard, six different studies were conducted: one per feature type (texture and shape), as well as the combination of both features (texture + shape) for each of the two covariables (tumor type and location in the coronal plane). A dataset of 43 BC patients were considered. A radiomics approach was implemented extracting 43 texture and 17 shape features and using to train 5 different predictive models (Linear SVM, Gaussian SVM, Bagged Tree, KNN and Naïve Bayes). The highest precision result for the tumor type study (74.04% in terms of AUC) was obtained with 43 texture features. Whereas for the quadrant localization study, the highest precision result (67.99% AUC) was obtained as a combination of 3 textures and shape features. Both results were achieved with the SVM with Linear Kernel classification model.Clinical Relevance- This work emphasizes the use of quantitative biomarkers as texture and shape features in combination with machine learning techniques to aid in breast tumor malignancy diagnosis on MR imaging. Moreover, considering the location of the tumor in the coronal plane and its type according to its genetic information may improve the selection of appropriate treatments, survival rate, and quality of life for breast cancer patients.

Reference ventricular dimensions and function parameters by cardiovascular magnetic resonance in highly trained Caucasian athletes.

BACKGROUND: Data regarding cardiovascular magnetic resonance (CMR) reference values in athletes have not been well determined yet. Using CMR normal reference values derived from the general population may be misleading in athletes and may have clinical implications. AIMS: To determine reference ventricular dimensions and function parameters and ratios by CMR in high performance athletes. METHODS: Elite athletes and age- and gender-matched sedentary healthy controls were included. Anatomical and functional variables, including biventricular volumes, mass, systolic function, wall thickness, sphericity index and longitudinal function were determined by CMR. RESULTS: A total of 148 athletes (29.2 ± 9.1 years; 64.8% men) and 124 controls (32.1 ± 10.5 years; 67.7% men) were included. Left ventricular (LV) mass excluding papillary muscles was 67 ± 13 g/m2 in the control group and increased from 65 ± 14 g/m2 in the low intensity sport category to 83 ± 16 g/m2 in the high cardiovascular demand sport category; P < 0.001. Regarding right ventricular (RV) mass, the data were 20 ± 5, 31 ± 6, and 38 ± 8 g/m2, respectively; P < 0.001. LV and RV volumes, and wall thickness were higher in athletes than in the control group, and also increased with sport category. However, LV and RV ejection fractions were similar in both groups. LV and RV dimensions, wall thickness and LV/RV ratios reference parameters for athletes are provided. CONCLUSIONS: LV and RV masses, volumes, and wall thicknesses are higher in athletes than in sedentary subjects. Specific CMR reference ranges for athletes are provided and can be used as reference levels, rather than the standard upper limits used for the general population to exclude cardiomyopathy.

Synthetic Generation of Cardiac MR Images Combining Convolutional Variational Autoencoders and Style Transfer.

The number of studies in the medical field that uses machine learning and deep learning techniques has been increasing in the last years. However, these techniques require a huge amount of data that can be difficult and expensive to obtain. This specially happens with cardiac magnetic resonance (MR) images. One solution to the problem is raise the dataset size by generating synthetic data. Convolutional Variational Autoencoder (CVAe) is a deep learning technique which allows to generate synthetic images, but sometimes the synthetic images can be slightly blurred. We propose the combination of the CVAe technique combined with Style Transfer technique to generate synthetic realistic cardiac MR images. Clinical Relevance-The current work presents a tool to increase in a simple easy and fast way the cardiac magnetic resonance images dataset with which perform machine learning and deep learning studies.

Multiclass Classification of Prostate Tumors Following an MR Image Analysis-Based Radiomics Approach.

Prostate cancer is one of the most common cancers in men, with symptoms that may be confused with those caused by benign prostatic hyperplasia. One of the key aspects of treating prostate cancer is its early detection, increasing life expectancy and improving the quality of life of those patients. However, the tests performed are often invasive, resulting in a biopsy. A non-invasive alternative is the magnetic resonance imaging (MRI)-based PI-RADS v2 classification. The aim of this work was to find objective biomarkers that allow the PI-RADS classification of prostate lesions using a radiomics approach on Multiparametric MRI. A total of 90 subjects were analyzed. From each segmented lesion, 609 different texture features were extracted using five different statistical methods. Two feature selection methods and eight multiclass predictive models were evaluated. This was a multiclass study in which the best AUC result was 0.7442 ± 0.0880, achieved with the Naïve Bayes model using a subset of 120 features. Valuable results were also obtained using the Random Forests model, obtaining an AUC of 0.7394 ± 0.0965 with a lower number of features (52). Clinical Relevance- The current study establishes a methodology for classifying prostate cancer and supporting clinical decision-making in a fast and efficient manner and avoiding additional invasive procedures using MRI.

Texture Analysis in MRI of the Knee for an Early Diagnosis of Osteoarthritis.

Osteoarthritis is one of the most disabling diseases in developed countries. Its etiology is not firmly established, and the diagnosis is made by observing radiographs, assigning a degree of severity based on the information displayed. For this reason, the diagnosis is usually late and determined by the subjectivity of the doctor, which implies a restriction of the treatment. Magnetic resonance imaging (MRI) has allowed us to see in greater detail the alterations produced in soft joint structures. In this work, biomarkers for an early diagnosis of knee osteoarthritis have been developed by means of textures analysis on MRI. For this purpose, 50 subjects underwent T1-weighted MR image acquisitions: 25 controls and 25 diagnosed with knee osteoarthritis between grades I and III. Six regions were segmented on these images, corresponding to the femorotibial cartilage, femoral condyles, and tibial plateau. 43 textures were extracted for each region of interest (ROI) employing 5 statistical methods and 5 different predictive models were trained and compared. In addition, a study of the thickness of the cartilage was carried out to make a comparison with the texture analysis. The best result has been obtained using a K-nearest neighbor model with the combination of 33 textures (maximum value of AUC = 0.7684). Furthermore, in the analysis of the cartilage thickness, no statistically significant differences were found. Finally, it is concluded that the texture analysis has great potential for the diagnosis of knee osteoarthritis. Clinical Relevance - The current study establishes a methodology for an early diagnosis of knee osteoarthritis by means of MRI-based texture analysis, in a fast and objective manner.

End-systole and end-diastole detection in short axis cine MRI using a fully convolutional neural network with dilated convolutions.

The correct assessment and characterization of heart anatomy and functionality is usually done through inspection of magnetic resonance image cine sequences. In the clinical setting it is especially important to determine the state of the left ventricle. This requires the measurement of its volume in the end-diastolic and end-systolic frames within the sequence trough segmentation methods. However, the first step required for this analysis before any segmentation is the detection of the end-systolic and end-diastolic frames within the image acquisition. In this work we present a fully convolutional neural network that makes use of dilated convolutions to encode and process the temporal information of the sequences in contrast to the more widespread use of recurrent networks that are usually employed for problems involving temporal information. We trained the network in two different settings employing different loss functions to train the network: the classical weighted cross-entropy, and the weighted Dice loss. We had access to a database comprising a total of 397 cases. Out of this dataset we used 98 cases as test set to validate our network performance. The final classification on the test set yielded a mean frame distance of 0 for the end-diastolic frame (i.e.: the selected frame was the correct one in all images of the test set) and 1.242 (relative frame distance of 0.036) for the end-systolic frame employing the optimum setting, which involved training the neural network with the Dice loss. Our neural network is capable of classifying each frame and enables the detection of the end-systolic and end-diastolic frames in short axis cine MRI sequences with high accuracy.

Short-Term Changes in Left and Right Ventricular Cardiac Magnetic Resonance Feature Tracking Strain Following Ferric Carboxymaltose in Patients With Heart Failure: A Substudy of the Myocardial-IRON Trial.

Background The mechanisms explaining the clinical benefits of ferric carboximaltose (FCM) in patients with heart failure, reduced or intermediate left ventricular ejection fraction, and iron deficiency remain not fully clarified. The Myocardial-IRON trial showed short-term cardiac magnetic resonance (CMR) changes suggesting myocardial iron repletion following administration of FCM but failed to find a significant increase in left ventricular ejection fraction in the whole sample. Conversely, the strain assessment could evaluate more specifically subtle changes in contractility. In this subanalysis, we aimed to evaluate the effect of FCM on the short-term left and right ventricular CMR feature tracking derived strain. Methods and Results This is a post hoc subanalysis of the double-blind, placebo-controlled, randomized clinical trial that enrolled 53 ambulatory patients with heart failure and left ventricular ejection fraction <50%, and iron deficiency [Myocardial-IRON trial (NCT03398681)]. Three-dimensional left and 2-dimensional right ventricular CMR tracking strain (longitudinal, circumferential, and radial) changes were evaluated before, 7 and 30 days after randomization using linear mixed-effect analysis. The median (interquartile range) age of the sample was 73 years (65-78), and 40 (75.5%) were men. At baseline, there were no significant differences in CMR feature tracking strain parameters across both treatment arms. At 7 days, the only global 3-dimensional left ventricular circumferential strain was significantly higher in the FCM treatment-arm (difference: -1.6%, P=0.001). At 30 days, and compared with placebo, global 3-dimensional left ventricular strain parameters significantly improved in those allocated to FCM treatment-arm [longitudinal (difference: -2.3%, P<0.001), circumferential (difference: -2.5%, P<0.001), and radial (difference: 4.2%, P=0.002)]. Likewise, significant improvements in global right ventricular strain parameters were found in the active arm at 30 days (longitudinal [difference: -3.3%, P=0.010], circumferential [difference: -4.5%, P<0.001], and radial [difference: 4.5%, P=0.027]). Conclusions In patients with stable heart failure, left ventricular ejection fraction <50%, and iron deficiency, treatment with FCM was associated with short-term improvements in left and right ventricular function assessed by CMR feature tracking derived strain parameters. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT03398681.

The Future of Cardiac Magnetic Resonance Clinical Trials.

Over the past 2 decades, cardiac magnetic resonance (CMR) has become an essential component of cardiovascular clinical care and contributed to imaging-guided diagnosis and management of coronary artery disease, cardiomyopathy, congenital heart disease, cardio-oncology, valvular, and vascular disease, amongst others. The widespread availability, safety, and capability of CMR to provide corresponding anatomical, physiological, and functional data in 1 imaging session can improve the design and conduct of clinical trials through both a reduction of sample size and provision of important mechanistic data that may augment clinical trial findings. Moreover, prospective imaging-guided strategies using CMR can enhance safety, efficacy, and cost-effectiveness of cardiovascular pathways in clinical practice around the world. As the future of large-scale clinical trial design evolves to integrate personalized medicine, cost-effectiveness, and mechanistic insights of novel therapies, the integration of CMR will continue to play a critical role. In this document, the attributes, limitations, and challenges of CMR's integration into the future design and conduct of clinical trials will also be covered, and recommendations for trialists will be explored. Several prominent examples of clinical trials that test the efficacy of CMR-imaging guided pathways will also be discussed.

Automatic Multi-Atlas Liver Segmentation and Couinaud Classification from CT Volumes.

Primary Live Cancer (PLC) is the sixth most common cancer worldwide and its occurrence predominates in patients with chronic liver diseases and other risk factors like hepatitis B and C. Treatment of PLC and malignant liver tumors depend both in tumor characteristics and the functional status of the organ, thus must be individualized for each patient. Liver segmentation and classification according to Couinaud's classification is essential for computer-aided diagnosis and treatment planning, however, manual segmentation of the liver volume slice by slice can be a time-consuming and challenging task and it is highly dependent on the experience of the user. We propose an alternative automatic segmentation method that allows accuracy and time consumption amelioration. The procedure pursues a multi-atlas based classification for Couinaud segmentation. Our algorithm was implemented on 20 subjects from the IRCAD 3D data base in order to segment and classify the liver volume in its Couinaud segments, obtaining an average DICE coefficient of 0.94.Clinical Relevance- The final purpose of this work is to provide an automatic multi-atlas liver segmentation and Couinaud classification by means of CT image analysis.

Automatic left ventricle volume calculation with explainability through a deep learning weak-supervision methodology.

BACKGROUND AND OBJECTIVE: Magnetic resonance imaging is the most reliable imaging technique to assess the heart. More specifically there is great importance in the analysis of the left ventricle, as the main pathologies directly affect this region. In order to characterize the left ventricle, it is necessary to extract its volume. In this work we present a neural network architecture that is capable of directly estimating the left ventricle volume in short axis cine Magnetic Resonance Imaging in the end-diastolic frame and provide a segmentation of the region which is the basis of the volume calculation, thus offering explainability to the estimated value. METHODS: The network was designed to directly target the volumes to estimate, not requiring any labeled segmentation on the images. The network was based on a 3D U-net with extra layers defined in a scanning module that learned features like the circularity of the objects and the volumes to estimate in a weakly-supervised manner. The only targets defined were the left ventricle volumes and the circularity of the object detected through the estimation of the π value derived from its shape. We had access to 397 cases corresponding to 397 different subjects. We randomly selected 98 cases to use as test set. RESULTS: The results show a good match between the real and estimated volumes in the test set, with a mean relative error of 8% and a mean absolute error of 9.12 ml with a Pearson correlation coefficient of 0.95. The derived segmentations obtained by the network achieved Dice coefficients with a mean value of 0.79. CONCLUSIONS: The proposed method is capable of obtaining the left ventricle volume biomarker in the end-diastole and offer an explanation of how it obtains the result in the form of a segmentation mask without the need of segmentation labels to train the algorithm, making it a potentially more trustworthy method for clinicians and a way to train neural networks more easily when segmentation labels are not readily available.

Multimodality imaging of myocardial viability: an expert consensus document from the European Association of Cardiovascular Imaging (EACVI).

In clinical decision making, myocardial viability is defined as myocardium in acute or chronic coronary artery disease and other conditions with contractile dysfunction but maintained metabolic and electrical function, having the potential to improve dysfunction upon revascularization or other therapy. Several pathophysiological conditions may coexist to explain this phenomenon. Cardiac imaging may allow identification of myocardial viability through different principles, with the purpose of prediction of therapeutic response and selection for treatment. This expert consensus document reviews current insight into the underlying pathophysiology and available methods for assessing viability. In particular the document reviews contemporary viability imaging techniques, including stress echocardiography, single photon emission computed tomography, positron emission tomography, cardiovascular magnetic resonance, and computed tomography and provides clinical recommendations for how to standardize these methods in terms of acquisition and interpretation. Finally, it presents clinical scenarios where viability assessment is clinically useful.

Variants translating reduced expression of the beta estrogen receptor gene were associated with increased carotid intima media thickness: A cross-sectional study in late postmenopausal women.

ABSTRACT: There is debate on the role of estrogens in modulating the risk for atherosclerosis in women. Our purpose was to investigate whether the size of the estrogenic impact was independently associated with variation of carotid intima-media thickness (IMT) in healthy late postmenopausal women. The levels of circulating estrogens have been used in previous studies but the influence of SNPs of the estrogen receptors (ER) α and ß have not been investigated.We performed a crossed-sectional study of 91 women in a university hospital. We used a double approach in which, in addition to the measurement of estradiol levels by ultrasensitive methods, genetic variants (SNPs) associated with differing expression of the ER α and ß genes were assessed. Multivariable analysis was used to examine the association of candidate factors with the value of IMT and plaque detection at both the carotid wall and the sinus.A genotype combination translating reduced gene expression of the ERß was directly associated with IMT at both the carotid wall (P = .001) and the sinus (P = .002). Other predictors of IMT were the levels of glucose, positively associated with IMT at both the carotid wall (P < .001) and the sinus (P = .001), age positively associated with IMT at the sinus (P = .003), and levels of vitamin D, positively associated with IMT at the carotid wall (P = .04).Poorer estrogenic impact, as concordant with a SNP variant imposing reduced expression of the ERß, was directly associated with IMT at both the carotid wall and the sinus. Glucose level, vitamin D only for the carotid wall, and age only for the sinus, also emerged as independent factors in the IMT variance.

Short-term changes in left and right systolic function following ferric carboxymaltose: a substudy of the Myocardial-IRON trial.

AIMS: The mechanisms underlying the beneficial effect of ferric carboxymaltose (FCM) in patients with heart failure (HF) and iron deficiency (ID) have not been completely characterized. The Myocardial-IRON trial was a double-blind, randomized trial that evaluated myocardial iron repletion following FCM vs. placebo in 53 patients with HF and ID. In this post hoc analysis, we evaluated whether treatment with FCM was associated with cardiac magnetic resonance changes in left and right ventricular function (LVEF and RVEF, respectively) at different points of systolic dysfunction. METHODS AND RESULTS: We included patients from the Myocardial-IRON trial with left and right ventricular systolic dysfunction (LVSD and RVSD, respectively) at enrolment. Linear mixed regression models were used to evaluate changes at 7 and 30 days on LVEF and RVEF at cardiac magnetic resonance. At enrolment, 27 (50.9%) and 38 (71.7%) patients had LVEF < 40% (LVSD1 ) or <45% (LVSD2 ), respectively, and 10 (18.9%) and 17 (32.1%) patients had RVEF < 45% (RVSD1 ) or <51% in women and <52% in men (RVSD2) , respectively. Treatment with FCM was associated with a significant improvement in LVEF at 30 days (LVSD1 : Δ2.3%, P < 0.001; LVSD2 : Δ4.1, P = 0.014). FCM was also associated with a significant and early improvement in RVEF at 7 days (RVSD1 : Δ6.9%, P = 0.003; RVSD2 : Δ3.2%, P = 0.003) that persisted at 30 days (RVSD1 : Δ8.1%, P < 0.001; RVSD2 : Δ4.7%, P < 0.001). CONCLUSIONS: In patients with HF and systolic dysfunction with ID, FCM was associated with short-term improvement in LVEF and, especially, in RVEF.

Detection of subclinical myocardial dysfunction in cocaine addicts with feature tracking cardiovascular magnetic resonance.

BACKGROUND: Cocaine is an addictive, sympathomimetic drug with potentially lethal effects. We have previously shown with cardiovascular magnetic resonance (CMR) the presence of cardiovascular involvement in a significant percentage of consecutive asymptomatic cocaine addicts. CMR with feature-tracking analysis (CMR-FT) allows for the quantification of myocardial deformation which may detect preclinical involvement. Therefore, we aimed to assess the effects of cocaine on the left ventricular myocardium in a group of asymptomatic cocaine users with CMR-FT. METHODS: In a cohort of asymptomatic cocaine addicts (CA) who had been submitted to CMR at 3 T, we used CMR-FT to measure strain, strain rate and dyssynchrony index in CA with mildly decreased left ventricular ejection fraction (CA-LVEFd) and in CA with preserved ejection fraction (CA-LVEFp). We also measured these parameters in 30 age-matched healthy subjects. RESULTS: There were no differences according to age. Significant differences were seen in global longitudinal, radial and circumferential strain, in global longitudinal and radial strain rate and in radial and circumferential dyssynchrony index among the groups, with the lowest values in CA-LVEFd and intermediate values in CA-LVEFp. Longitudinal, radial and circumferential strain values were significantly lower in CA-LVEFp with respect to controls. CONCLUSIONS: CA-LVEFp show decreased systolic strain and strain rate values, with intermediate values between healthy controls and CA-LVEFd. Signs suggestive of dyssynchrony were also detected. In CA, CMR-FT based strain analysis can detect early subclinical myocardial involvement.

Mejora del tratamiento de la dislipemia para pacientes con muy alto riesgo cardiovascular en la práctica clínica. Proyecto COLIPAR / Improvement in the management of dyslipidemia in a clinical practice population at very high cardiovascular risk. The COLIPAR project

No disponible

Feasibility and reproducibility of feature-tracking-based strain and strain rate measures of the left ventricle in different diseases and genders.

BACKGROUND: The measurement of myocardial deformation by strain analysis is an evolving tool to quantify regional and global myocardial function. PURPOSE: To assess the feasibility and reproducibility of myocardial strain/strain rate measurements with magnetic resonance feature tracking (MR-FT) in healthy subjects and in patient groups. STUDY TYPE: Prospective study. POPULATION: Sixty patients (20 hypertensives with left ventricular (LV) hypertrophy (H); 20 nonischemic dilated cardiomyopathy (D); 20 ischemic heart disease (I); as well as 20 controls (C) were included, 10 men and 10 women in each group. FIELD STRENGTH/SEQUENCE: A 1.5T MR protocol including steady-state free precession (SSFP) cine sequences in the standard views and late enhancement sequences. ASSESSMENT: LV volumes, mass, global and regional radial, circumferential, and longitudinal strain/strain rate were measured using CVI42 software. The analysis time was recorded. STATISTICAL TESTS: Intraobserver and interobserver agreement and intraclass correlation coefficients (ICC) were obtained for reproducibility assessment as well as differences according to gender and group of pertinence. RESULTS: Strain/strain rate analysis could be achieved in all subjects. The average analysis time was 14 ± 3 minutes. The average intraobserver ICC was excellent (ICC >0.90) for strain and good (ICC >0.75) for strain rate. Reproducibility of strain measurements was good to excellent (ICC >0.75) for all groups of subjects and both genders. Reproducibility of strain measurements was good for basal segments (ICC >0.75) and excellent for middle and apical segments (ICC >0.90). Reproducibility of strain rate measurements was moderate for basal segments (ICC >0.50) and good for middle and apical segments. DATA CONCLUSION: MR-FT for strain/strain rate analysis is a feasible and highly reproducible technique. CVI42 FT analysis was equally feasible and reproducible in various pathologies and between genders. Better reproducibility was seen globally for middle and apical segments, which needs further clarification. LEVEL OF EVIDENCE: 3 Technical Efficacy Stage 2 J. Magn. Reson. Imaging 2018;47:1415-1425.

CRM en hipertensión arterial, más allá del corazón / CMR in hypertension. looking beyond the heart

No disponible