AI-Based Aortic Stenosis Classification in MRI Scans

Aortic stenosis (AS) is a critical cardiovascular condition that necessitates precise diagnosis for effective patient care. Despite a limited dataset comprising only 202 images, our study employs transfer learning to investigate the efficacy of five convolutional neural network (CNN) models, coupled...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) 2023-12, Vol.12 (23), p.4835
Main Authors: Elvas, Luís B, Águas, Pedro, Ferreira, Joao C, Oliveira, João Pedro, Dias, Miguel Sales, Rosário, Luís Brás
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Aorta
Aortic stenosis
Aortic valve stenosis
Artificial intelligence
Artificial neural networks
Automation
Calcification
Cardiovascular disease
Classification
Collaboration
Computer vision
Coronary vessels
Data augmentation
Datasets
Deep learning
Diagnosis
Health care
Heart failure
Image processing
Learning
Literature reviews
Machine learning
Machine vision
Magnetic resonance imaging
Medical imaging
Methods
Neural networks
Older people
Pandemics
Patients
Vein & artery diseases
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aortic stenosis (AS) is a critical cardiovascular condition that necessitates precise diagnosis for effective patient care. Despite a limited dataset comprising only 202 images, our study employs transfer learning to investigate the efficacy of five convolutional neural network (CNN) models, coupled with advanced computer vision techniques, in accurately classifying AS. The VGG16 model stands out among the tested models, achieving 95% recall and F1-score. To fortify the model’s robustness and generalization, we implement various data augmentation techniques, including translation, rotation, flip, and brightness adjustment. These techniques aim to capture real-world image variations encountered in clinical settings. Validation, conducted using authentic data from Hospital Santa Maria, not only affirms the clinical applicability of our model but also highlights the potential to develop robust models with a limited number of images. The models undergo training after the images undergo a series of computer vision and data augmentation techniques, as detailed in this paper. These techniques augment the size of our dataset, contributing to improved model performance. In conclusion, our study illuminates the potential of AI-driven AS detection in MRI scans. The integration of transfer learning, CNN models, and data augmentation yields high accuracy rates, even with a small dataset, as validated in real clinical cases.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics12234835