Human visual system (HVS) disorders, such as color vision deficiencies and impairments caused by traumatic brain injury (TBI), significantly alter perception. This paper presents a computational framework that leverages PerceptNet, a model of the HVS, combined with the optimization capabilities of deep learning frameworks such as JAX/Flax, to simulate how these disorders affect perceived images. The framework optimizes input images to match the feature maps of a modified PerceptNet model that incorporates disease-specific changes. We demonstrate its versatility by simulating visual perception in cases of color blindness and exploring the potential to model perceptual changes driven by neuroplasticity in the primary visual cortex (V1) following TBI. This framework offers a flexible and robust tool for studying altered visual perception and has potential applications in accessibility design, education, and research.Clinical relevance— This provides a framework to simulate how a disease in the human visual system changes the perception, providing both a system to adapt visual systems, and provides a computational framework to help study the behavior of some diseases.

The diagnosis of liver diseases such as fibrosis and steatosis has traditionally relied on invasive techniques like liver biopsy. This study investigates hepatic biomarkers derived from magnetic resonance imaging (MRI) to non-invasively detect and stratify liver fibrosis and steatosis. Parameters such as liver stiffness, fat fraction, T2 relaxation time, and diffusion coefficients (apparent diffusion coefficient -ADC- and intravoxel incoherent motion -IVIM-) were analyzed in a cohort of 27 patients suspected of metabolic dysfunction-associated steatotic liver disease (MASLD), using a 3T MR scanner. Results show ADC as a promising fibrosis biomarker with a significant negative correlation to liver stiffness (r = -0.6801, p-value = 0.0000953), while T2 relaxation time correlated positively with fat fraction (r = 0.6087, p-value = 0.0007536). No significant correlation was found between PDFF and fibrosis, and IVIM parameters showed limited predictive value. These findings highlight the potential of MRI biomarkers for non-invasive liver disease assessment.Clinical Relevance— The findings of this study highlight the potential of non-invasive MRI-derived biomarkers for the diagnosis and stratification of liver fibrosis and steatosis. By reducing reliance on invasive procedures such as liver biopsy, these biomarkers could improve clinical outcomes, enable earlier detection, and minimize the risks and economical costs associated with traditional diagnostic methods

The treatment and prognosis of a patient with breast cancer depend fundamentally on the TNM (classification of malignant tumors) staging, which requires a complex and delicate diagnostic process. This involves a combination of different techniques, including some invasive such as biopsies to assess lymph node involvement, and some non-invasive like imaging studies, including mammography, ultrasound, MRI, or CT scans, to determine tumor size and potential metastases. These procedures can be tedious for the patient and require significant clinical resources.This study explores the potential of hybrid PET/MRI imaging as a tool for simultaneous metabolic and morphological analysis, enabling precise breast cancer staging through a single test. PET/MRI images from 30 breast cancer patients were segmented in 3D to define regions of interest (ROI) in the breast. From these, 174 radiomic and textural features were extracted, capturing both morphological and metabolic tumor characteristics. These features were used to train multiple predictive models, including Fine Tree, Naive Bayes, SVM, KNN, and Bagged Tree, to evaluate their ability to determine the presence or absence of metastasis (M stage).The best-performing model employed 20 selected features and achieved an Area Under the Curve (AUC) of 93%, indicating high predictive accuracy. Evaluation metrics, such as the confusion matrix and AUC, highlighted the significant relevance of radiomic features derived from PET/MRI images for metastasis detection. This study underscores the potential of PET/MRI imaging in breast cancer diagnosis, offering a more streamlined and less invasive approach to TNM staging, which could improve patient outcomes and reduce diagnostic burden.

Aim To quantify regional LV deformation parameters in subjects with chronic myocardial infarction (MI) by the combination of CMR feature tracking (CMR-FT) and LGE images to assess segmental myocardial function in remote myocardium and to evaluate their relationships with infarct size and post-infarction LV global function. Materials and Methods CMR-images (SSFP cine and LGE) were acquired from 34 chronic MI patients and 32 healthy volunteers included in this retrospective study. LV ejection fraction (LVEF), infarct size (IS), CMR-FT regional circumferential, radial and longitudinal strain (CS, RS, LS), time-to-peak strain (TTP-CS, TTP-RS, TTP-LS) and rotation were measured. Results CS, RS and LS were greater for remote, adjacent and border zones than for infarct areas (p<0.01); TTP-CS, TTP-RS and TTP-LS values were shorter for remote and border zones than for infarct areas (p<0.05). Maximum apical rotation was found at the border zone (p<0.05). Remote CS, RS and LS in MI were significantly lower than in healthy subjects (p<0.01). Remote CS and LS correlated with IS (CS: r=0.75, LS: r=0.82, p<0.0001) and LVEF (CS: r=-0.87, LS: r=-0.83, p<0.001). In ROC analysis for the detection of contractile dysfunction in RM, IS and LVEF performed best with AUCs of 0.98 and 0.94, showing cut-off values of 17 % and 54 %, respectively. Conclusions Quantitative assessment of LV strain and rotation provides deformation characteristics of infarct, border and remote areas in patients with chronic MI, relating contractile dysfunction in remote areas to the extent of the infarcted region, which could offer useful clinical insights into the LV remodeling process.

Osteoarthritis (OA) is the most prevalent rheumatic disease, affecting an increasing number of people. This work proposes an innovative methodology based on texture analysis on femorotibial cartilage and T2 mapping on femoropatellar cartilage in T2-weighted magnetic resonance imaging (MRI) to identify early cartilage degeneration biomarkers, imperceptible to the human eye. Two distinct analyses were conducted: (1) On the one hand, in the femorotibial cartilage, 3D manual segmentation was performed and a radiomic approach was applied extracting 43 textural features; (2) On the other hand, in the femoropatellar cartilage through the elaboration of cartigrams, 27 features derived from T2 relaxation times were extracted to evaluate the deep, intermediate and superficial layers of the cartilage. The database included 100 subjects, distributed between controls and patients with different stages of OA according to the Kellgren & Lawrence scale (I-IV). In both analyses the KNN model is positioned as the most effective model followed by the SVM, demonstrating its potential in the early diagnosis of OA using advanced medical imaging techniques and machine learning methods.Clinical Relevance— The diagnosis of osteoarthritis is usually made in advanced stages, at which time treatment options are reduced. MRI makes it possible to detect joint alterations even before there are indications in other radiological tests or clinical symptoms suggesting joint deterioration. This study explores the correlation of MRI findings with clinical features, promoting the integration of advanced technologies into clinical practice to improve the accuracy and speed of OA diagnosis, thus contributing to more effective and personalized interventions.

Despite the improvement in prognosis in patients with acute myocardial infarction (AMI), a significant proportion of survivors still experience heart failure (HF)-related adverse outcomes. Adverse left ventricular remodeling (LVR), which refers to a progressive dilation of left ventricular (LV) end-diastolic and end-systolic volumes, usually accompanied by a deterioration in LV systolic function, occurs frequently and underlies most cases of HF development after AMI. In this review, we discuss the current definitions of post-AMI LVR, the most appropriate imaging modalities for its detection, and the pathophysiological mechanisms by which Cardiac Rehabilitation (CR) can improve LVR-including exercise interventions, cardiovascular risk factors control, and pharmacological therapy optimization. Finally, we provide up-to-date recommendations for the follow-up and management of LVR in post-AMI patients enrolled in CR and outline future prospects on this topic.

Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, traditionally assessed via manual scoring on ECG-gated CT scans. However, manual methods are time-consuming and subject to interobserver variability, especially in non-dedicated CT scans. This study presents a preliminary investigation into automated CAC segmentation using a dual-input W-Net architecture, which processes both raw CT volumes and thresholded binary masks (threshold: 130 Hounsfield units). The model was trained and evaluated on 93 patients, with CAC severity categorized by Agatston score. We tested both a 2-class (left/right arteries) and a 4-class (LAD, RCA, LCX, LMCA) segmentation approach. Morphological post-processing was used to refine predictions. The model’s performance was evaluated using the absolute error in Agatston score. In the 2-class model, post-processing reduced the error for the left artery from 302.7 to 51.4 and for the right artery from 1001.7 to 717.3 in the severe CAC group (>500 AS). In the 4-class model, post-processing reduced error for LAD from 99.1 to 25.7 and for RCA from 643.9 to 161.4 in the same group. Across models, mild CAC cases (<100 AS) had near-zero errors, while most false positives arose from mitral and aortic valve calcifications. These results show the potential of our approach for opportunistic CAC screening using routine CT scans. The proposed method significantly reduces absolute Agatston score error and manual burden, supporting its applicability in clinical workflows. Future work will focus on dataset expansion, model robustness, and artery-specific refinement.

Introduction and objectives: In patients with established chronic coronary syndrome (CCS), the significance of persistent angina is controversial. We aimed to evaluate the prognostic role of persistent angina in symptomatic CCS patients with abnormal stress cardiovascular magnetic resonance (CMR) and altered angiographic findings undergoing percutaneous revascularization. Methods: We analyzed 334 CCS patients with Canadian Cardiovascular Society angina class > 2, perfusion deficits on stress CMR and severe lesions in angiography who underwent medical therapy optimization plus CMR-guided percutaneous revascularization. We investigated the association of persistent angina at 6 months postintervention with subsequent cardiac death, myocardial infarction, and hospital admission. Results: All patients had angina class > 2 (mean: 2.8 f 0.7), abnormal stress CMR (mean ischemic burden: 5.8 f 2.7 segments), and severe angiographic lesions. The angina resolution rates were 81% at 6 months, and 81%, 81%, and 77% at 1, 2, and 5 years, respectively. During a median follow-up of 8.9 years, persistent angina was independently associated with higher rates of subsequent cardiac death (13% vs 4%; HR, 3.7; 95%CI, 1.59.2; P = .005), myocardial infarction (24% vs 6%; HR, 4.9; 95%CI, 2.4-9.9; P < .001), and hospital admission for heart failure (27% vs 13%; HR, 2.7; 95%CI, 1.5-5.2; P = .001). Conclusions: In CCS patients with robust diagnostic evidence from symptoms, stress CMR, and angiography, persistent angina after percutaneous revascularization is a strong predictor of subsequent cardiac death, myocardial infarction, and hospital admission for heart failure.

The treatment of bulky tumors with conventional radiotherapy is limited by the need for higher therapeutic doses, which can increase toxicity to healthy tissues and fail to exploit tumor heterogeneity. In this context, Lattice radiotherapy emerges as an innovative approach, focusing on heterogeneous partial irradiation that alternates areas of high dose, known as vertices, with lower dose zones. This method promotes immunogenic cell death in the vertices, releasing antigens and inflammatory cytokines that enhance immune system activation while reducing radiation exposure to at-risk organs and modulating the dose in areas of the tumor that are less radio-sensitive, such as hypoxic or necrotic zones. To facilitate the implementation of this technique, a Lattice-based algorithm has been developed to automate the generation and three-dimensional distribution of the vertices within the tumor volume, using DICOM RT files that contain CT images and anatomical segmentations. The developed algorithm allows for the adjustment of parameters such as the diameter and spacing of the vertices, as well as the ability to remove or modify their locations, thus optimizing the protection of surrounding organs. All of this is presented in an intuitive and interoperable graphical user interface, enabling the integration of the generated spheres into radiotherapy planning systems.Clinical RelevanceThis Lattice-based algorithm offers radiation oncologists a clinically significant tool for optimizing treatment by tailoring high-dose sphere distributions within the target tumor volume. It determines sphere diameters, defines boundaries between spheres and the target contour, and allows for adjustments such as redistributing, resizing, or removing spheres. Notably, the algorithm facilitates these adjustments not only in two-dimensional planes, where such modifications are relatively straightforward, but also in three-dimensional space, addressing the complexities that arise when working across multiple axes. This enhanced precision enables more effective tumor coverage while sparing healthy tissue, leading to improved therapeutic outcomes and enhanced patient quality of life

Artificial neural networks (ANN) in medicine are presented as a decision-making support method that allows obtaining more optimal solutions in terms of time and resource management. In this article, an ANN-aided decision support method has been developed to classify and quantify low back disease, specifically vertebrae and disc characterization, and spinal stenosis from MRI. A set of 1960 slices from 200 patients extracted from T2-weighted lumbar spine MRI has been used to train and evaluate neural networks. The segmentations of the discs and vertebrae have been accomplished using U-nets. Experiments on T2-weighted MR images of 200 subjects show that U-nets achieve performances with mean Dice similarity coefficients of 0.79 and 0.76 for the segmentations of 10 vertebrae and 9 intervertebral discs, respectively.Clinical Relevance—A computer-aided diagnosis (CAD) methodology using U-Net for segmentation of vertebrae and intervertebral discs on lumbar spine MRI with minimal user input is proposed. The suggested approach holds great potential as a clinical support system for radiologists.

This study investigated the feasibility of feature tracking cardiac computed tomography (CCT)-derived LV global and regional strain and its agreement with feature tracking cardiac magnetic resonance (CMR)-derived measurements. CMR images and CCT images were acquired from 15 adult patients (50

Cardiovascular diseases are the leading cause of death worldwide. Cardiac magnetic Resonance (CMR) imaging is presented as a remarkably valuable tool for non-invasively diagnosing heart diseases.In this paper we develop a classification method for the diagnosis of amyloidosis, and hypertensive and hypertrophic cardiomyopathy. These pathologies have a similar clinical presentation, characterized by a thickening of the ventricular walls, thus making their diagnosis and differentiation difficult. In this work we have developed a CMR image-based automatic diagnostic assistance system for these pathologies by means of convolutional neuronal networks (CNN). In addition, Data Augmentation techniques are applied in the training process to generate more data, which is important in the case of images of patients with amyloidosis since a small number of this data is available and this could lead to inaccurate predictions.It can be concluded from the obtained results that it is possible to obtain a model capable of distinguishing the four classes (control, amyloidosis, hypertensive cardiomyopathy, and hypertrophic cardiomyopathy) with an AUC ROC of 0.9.

Alzheimer’s Disease (AD), the leading cause of dementia, is characterized by a progressive cognitive decline and structural brain degeneration. This study is aimed to identify MRI-based biomarkers for early diagnosis of AD, by analyzing data from three clinical groups: controls, mild cognitive impairment (MCI) and AD patients. A total of 589 parameters were extracted: 536 from volumetry, 35 from diffusion, and 12 from perfusion measurements. Statistical analysis focused on two classification tasks: a binary classification to differentiate between controls and unhealthy patients, and a multiclass classification to distinguish between controls, MCI and AD patients. Key volumetric parameters included gray and white matter, hippocampus, limbic system, ventricles and the subventricular zone (SVZ). All the regions analyzed for diffusion and perfusion provided at least one significant parameter. Thirty key biomarkers were selected for each classification task and used to train machine learning models. These were KNN, SVM and Ensemble methods, trained with 5, 10, 15, 20, 25 and 30 parameters as well as a PCA 95%. Ensemble models achieved the highest accuracy, with 85% for binary classification and 75% for multiclass classification. These findings demonstrate the promise of MRI biomarkers combined with machine learning techniques for enhancing early diagnosis of AD.Clinical Relevance— This project provides innovative MRI-based biomarkers for Alzheimer’s diagnosis. Early identification of neurodegeneration is crucial for improving patient outcomes. These findings could also influence on diagnostic protocols to enable a more accurate differentiation between healthy individuals, those with mild cognitive impairment and Alzheimer’s Disease patients.

Analyzing functional networks (FNs) of brain activity of mammals can be challenging because of their fast dynamics and non-stationary properties. Here, we present a computational protocol for extracting FNs using scaled cross-correlation (SCA) and analyzing them independently for each epoch. We outline procedures for calculating edge weight and node distance distributions, with statistical comparisons using the Cliff's delta metric. We also detail procedures for visualizing results by plotting distributions. This protocol has potential in identifying disease biomarkers. For complete details on the use and execution of this protocol, please refer to Varga et al.1.

BACKGROUND:Left ventricular thrombus (LVTh) is a severe complication after ST-segment elevation myocardial infarction (STEMI). OBJECTIVES:We aim to predict LVTh occurrence by cardiac magnetic resonance (CMR) using clinical, echocardiographic, and electrocardiographic (ECG) variables readily available at admission. METHODS:We included 590 reperfused STEMI patients who underwent early (1-week) and/or late (6-month) CMR in our institution. Baseline clinical, echocardiographic (left ventricular ejection fraction -LVEF-) and ECG data (summatory of ST-segment elevation -sum-STE- and Q-wave and residual ST-elevation >1 mm -Q-STE-) during admission were registered. Multivariate binary logistic regression models and receiver operating characteristic curves were computed for LVTh prediction. RESULTS:LVTh was detected by CMR in 43 (7.3 %) patients and was predicted by previous chronic coronary syndrome (CCS, HR 4.74 [1.82-12.35], p = 0.001), anterior STEMI (HR 10.93 [2.47-48.31], p = 0.002), LVEF (HR 0.96 [0.93-0.99] per %, p = 0.008), maximum sum-STE (HR 1.04 [1.01-1.07] per mm, p = 0.04), and Q-STE (HR 1.31 [1.08-1.6] per lead, p = 0.008). High-risk patients with both major (anterior STEMI and Q-STE in ≥1 leads) and 1-3 minor (CCS, maximum sum-STE >10 mm, LVEF <50%) factors showed the highest LVTh risk (19.6 % within 6 months). The model showed excellent discrimination ability (area under the curve=0.85 [0.81-0.9], p < 0.001). Simplified 4-variable (excluding sum-STE) and 3-variable (also excluding CCS) risk scores showed similar discrimination ability and were externally validated. CONCLUSIONS:LVTh within 6 months post-STEMI can be predicted using pre-discharge clinical (anterior infarction and CCS), echocardiographic (LVEF), and ECG (sum-STE and Q-STE) data. Our results can help select patients who should undergo CMR after STEMI for LVTh detection.

Abstract Background In patients with established chronic coronary syndrome (CCS), the significance of myocardial ischemia is a controversial issue. Persistent angina within the first year after treatment intervention has ranged widely in previous studies and its association with subsequent hard clinical events is unclear. We aim to evaluate the long-term dynamics of angina class and the prognostic role of persistent angina in symptomatic chronic coronary syndrome (CCS) patients with abnormal stress cardiovascular magnetic resonance (CMR) and altered angiography. Methods We analyzed 486 CCS patients with Canadian Cardiovascular Society angina class ≥2, perfusion deficit in stress CMR and severe lesions in angiography submitted to treatment intervention (medical therapy plus, if feasible, CMR-guided revascularization). The dynamics and association of persistent angina at 6 months post-intervention with subsequent cardiac death, myocardial infarction, and admission for heart failure were investigated. Results All patients displayed angina class ≥2 (mean: 2.7±0.7), abnormal stress CMR (mean ischemic burden: 6.2±3 segments) and severe angiographic lesions. Most underwent CMR-guided revascularization (n=392, 81%). The angina resolution rate was 78% at 6 months, and 79%, 77%, and 75% at 1, 2, and 5 years respectively. Compared with medical treatment alone, CMR-guided revascularization was associated with less persistent angina (19% vs. 35%; HR 0.42 [0.2–0.7]; p=0.003). During an 8.3-year median follow-up, persistent angina was independently associated with higher subsequent cardiac death rates (18% vs. 4%; HR 10.9 [4.1–29.2]; p<0.001), myocardial infarction (24% vs. 6%; HR 5.8 [3.2–10.4]; p<0.001), and admission for heart failure (31% vs. 14%; HR 2.7 [1.7–4.2]; p<0.001). Conclusions In CCS patients with robust diagnostic evidence by symptoms, stress CMR and angiography, sustained improvement of anginal symptoms can be achieved in most patients after treatment intervention. Angina resolution is more frequent in patients treated with CMR-guided revascularization and is associated with fewer cardiac events.Central Figure.Persistent angina and MACE risk

Functional magnetic resonance imaging (fMRI) provides insights into cognitive processes with significant clinical potential. However, delays in brain region communication and dynamic variations are often overlooked in functional network studies. We demonstrate that networks extracted from fMRI cross-correlation matrices, considering time lags between signals, show remarkable reliability when focusing on statistical distributions of network properties. This reveals a robust brain functional connectivity pattern, featuring a sparse backbone of strong 0-lag correlations and weaker links capturing coordination at various time delays. This dynamic yet stable network architecture is consistent across rats, marmosets, and humans, as well as in electroencephalogram (EEG) data, indicating potential universality in brain dynamics. Second-order properties of the dynamic functional network reveal a remarkably stable hierarchy of functional correlations in both group-level comparisons and test-retest analyses. Validation using alcohol use disorder fMRI data uncovers broader shifts in network properties than previously reported, demonstrating the potential of this method for identifying disease biomarkers.

Traditionally, liver disease diagnosis relied heavily on invasive liver biopsies, considered the gold standard for direct liver assessment. However, the emergence of less invasive alternatives, such as magnetic resonance elastography (MRE) and magnetic resonance imaging (MRI), has transformed the field. In this study, a wide array of novel biomarkers, including stiffness, corrected longitudinal relaxation time (cT1), longitudinal relaxation time (T1), and apparent diffusion coefficient (ADC), were employed to assess liver fibrosis. Proton density fat fraction (PDFF) was determined using the Dixon technique for steatosis evaluation, and transversal relaxation time (T2*) was utilized to gauge iron overload. A comprehensive imaging protocol, including calibration with an albumin phantom, encompassed five sequences performed on 27 patients suspected of non-alcoholic steatohepatitis (NASH). The MRI data were acquired using a 3 Tesla GE Medical Systems SIGNA Architect MRI scanner. This study calibrated T1 maps with an albumin phantom and assessed the reliability of elastography by magnetic resonance (MRE) for fibrosis analysis. Significant correlations were observed between biomarkers and liver health indicators: cT1 correlated with stiffness (r=0.4272, p=0.0331) and PDFF (r=0.6699, p=0.0002), ADC correlated with stiffness (r=0.6278, p=0.0008), and PDFF demonstrated a strong association with the IDEAL technique (r=0.9792, p=0.0001), confirming its reliability for steatosis assessment.Clinical Relevance— The current study presents a novel and innovative approach to the non-invasive diagnosis of liver diseases, including conditions like iron overload, steatosis, and fibrosis. This groundbreaking approach involves a multiparametric and multimodal analysis of biomarkers, enabling a higher degree of non-invasive diagnostic accuracy.

Abstract Background Coronary artery calcium (CAC) score improves cardiovascular risk stratification in asymptomatic individuals. However, whether CAC can be quantified in ungated thoracic computed tomography (uTCT) performed for other indications, and if this CAC score associates with cardiovascular outcomes, hasn’t been confirmed yet. Purpose We aim to analyse the extension of CAC and its prognostic value in terms of major adverse cardiovascular events (MACE) in patients who underwent uTCT for other indications. Methods We analysed a preliminary sample of 115 uTCT performed in 2015 in our hospital. We studied the presence and extension of CAC and quantified the global CAC score by Agatston method using validated software. Patients were categorized according to Coronary Artery Calcium Data and Reporting System (CAC-DRS) categories. Cardiovascular risk factors, lipidic control and pharmacological therapy of the cohort were registered. We analysed the time to first 3P-MACE, defined as cardiovascular death, non-fatal myocardial infarction and non-fatal stroke, whichever occurred first. A p-value <0.05 was considered statistically significant. Results Mean age of the cohort was 60.8±16.1 years (53% male, 53% smokers). Mean LDL-cholesterol was 121.67±34.91 mg/dL, and 35.1% received lipid-lowering therapy. In more than half (n=59, 51.3%) of the population CAC was detected. Mean CAC score was 312.99±774.48 Agatston units, and patients were categorized in CAC-DRS category 1 (n=19, 16.5%), category 2 (n=15, 13%) and category 3 (n=25, 21.7%). Patients with CAC were older (71±10.1 vs. 50.1±14.2 years, p<0.001), had higher burden of cardiovascular risk factors and prevalence of chronic kidney disease (CKD; n=8, 13.6% vs. n=1, 1.8%, p=0.03) and higher levels of triglycerides (143.2±80.5 vs. 106.8±36.2 mg/dL, p=0.004), but not LDL-cholesterol. Eleven (9.6%) patients presented 3P-MACE during a mean follow-up of 6.55±2.82 years. CAC score independently predicted 3P-MACE (HR 1.06 [1.01-1.11] per 100 Agatston units, p=0.02) along with CKD (HR 6.94 [1.58-30.46], p=0.01) and basal glucose levels (HR 1.03 [1.02-1.04] per mg/dL, p<0.001). Conclusions CAC can be incidentally detected in more than half of our unselected cohort of patients undergoing uTCT for other indications. CAC score quantification by Agatston method is feasible in uTCT and associates with a higher risk of MACE during follow-up.Incidental CAC detection in uTCT

The number of studies in the medical field that uses machine learning and deep learning techniques has been increasing in the last years. To harness the full potential of deep learning for medical imaging, large datasets are required for training. These datasets are difficult to obtain due to privacy concerns, underrepresentation of rare diseases, poor standardization, and lack of diagnostic label quality and availability of experts for annotation. To solve this problem, we aim to explore the models offered by MONAI Generative Models, focusing on the Diffusion Models, to generate realistic synthetic cardiac magnetic resonance (MR) images. The model used has been able to generate very realistic cardiac MR images in a fast and easy-to-implement way. Given that the obtained synthetic images closely resemble the real one to the extent of being difficult to distinguish them, the study has shown its potential utility in augmenting datasets for medical imaging purposes.Clinical Relevance— The current work presents a framework to generate large amounts of synthetic cardiac MR images. Furthermore, the synthetic images obtained by the trained model are extremely realistic, maintaining the same details and characteristics of real cardiac MR images.