Exploring deep generative models for improved data generation in hypertrophic cardiomyopathy
Open Access
- 1 July 2025
- journal article
- Published by Salesian Polytechnic University of Ecuador in INGENIUS
- No. 34,p. 116-125
Abstract
Data generation strategies are essential for addressing the challenge of limited training data in deep learning-based medical image analysis, particularly for hypertrophic cardiomyopathy (HCM) using magnetic resonance imaging (MRI). Unlike traditional augmentation techniques, deep generative models can synthesize novel and diverse MRI images, enriching the training datasets. This study evaluates several generative models, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Deep Convolutional GANs (DCGANs), Auxiliary Classifier GANs (ACGANs), InfoGANs, and Diffusion Models, using the Structural Similarity Index Measure (SSIM) and Cross-Correlation Coefficient (CC) to assess image quality and structural fidelity. While VAEs demonstrated limitations such as noticeable noise and blurriness, GAN-based models, particularly DCGANs and ACGANs, generated higher-quality and anatomically accurate images. Diffusion models achieved the highest image fidelity among all the methods evaluated, but required longer generation times. These findings underscore the trade-off between image quality and computational efficiency and highlight the potential of deep generative models to augment MRI datasets, thereby improving deep learning applications for HCM diagnosis.Keywords
This publication has 22 references indexed in Scilit:
- PADS-Net: GAN-based radiomics using multi-task network of denoising and segmentation for ultrasonic diagnosis of Parkinson diseaseComputerized Medical Imaging and Graphics, 2025
- A systematic review of deep learning data augmentation in medical imaging: Recent advances and future research directionsHealthcare Analytics, 2024
- Data programming enabled weak supervised labeling for ECG time seriesBiomedical Signal Processing and Control, 2023
- Deep learning based active learning technique for data annotation and improve the overall performance of classification modelsExpert Systems with Applications, 2023
- Machine learning and deep learning approach for medical image analysis: diagnosis to detectionMultimedia Tools and Applications, 2022
- Pros and cons of GAN evaluation measures: New developmentsComputer Vision and Image Understanding, 2022
- Deep learning in ECG diagnosis: A reviewKnowledge-Based Systems, 2021
- Improving classification accuracy using data augmentation on small data setsExpert Systems with Applications, 2020
- GAN-Based Novel Approach for Data Augmentation with Improved Disease Classification2019
- A hybrid machine learning approach to cerebral stroke prediction based on imbalanced medical datasetArtificial Intelligence in Medicine, 2019