Related Experiment Video
Updated: Sep 16, 2025
Retrospective Cardiac Gating with A Prototype Small-Animal X-ray Computed Tomograph
Published on: February 21, 2025
Exploring advanced deep learning approaches in cardiac image analysis: A comprehensive review
Assia Boukhamla1, Nabiha Azizi1, Samir Brahim Belhaouari2
1LabGED Laboratory, Department of Computer Science, Faculty of Technology, Badji Mokhtar - Annaba University 12, P.O.Box, 23000, Annaba, Algeria.
Insights
Deep learning (DL) advances cardiac image analysis for early cardiovascular disease (CVD) diagnosis. This review covers DL applications, including transformers and compression techniques, for improved heart condition detection.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Cardiac image analysis is crucial for diagnosing cardiovascular diseases (CVDs).
- Automated disease identification aids early diagnosis and management.
- Deep learning (DL) and advanced imaging offer new opportunities in cardiology.
Purpose of the Study:
- To review recent deep learning applications in cardiac image analysis.
- To survey common imaging modalities and DL architectures used.
- To analyze deep model compression techniques in cardiac image processing.
Main Methods:
- Systematic review following PRISMA methodology.
- Analysis of recent research on DL architectures in cardiac imaging.
- Examination of cardiac imaging datasets and model compression contributions.
Main Results:
- Significant progress in DL for cardiac image analysis.
- Introduction of new techniques like transformers and foundation models.
- Advancements in deep model compression for cardiac image processing.
Conclusions:
- Deep learning is transforming cardiac image interpretation.
- Open challenges and future research directions are discussed.
- The field shows promise for enhanced cardiovascular diagnostics.
Background:
Cardiac image analysis plays an important role in detecting and categorizing cardiovascular diseases (CVDs), such as coronary artery disease (CAD), heart failure, congenital heart defects, arrhythmias (irregular heartbeat), and valvular heart disease. The automated identification of these diseases represents a significant advancement in achieving early diagnosis and mitigating disease exacerbations. While extant methodologies offer advanced means for the automatic segmentation and identification of cardiac structures and pathologies, recent strides in deep learning (DL) and modern imaging modalities within cardiology have introduced new opportunities for researchers. This has underscored the importance of deep model compression and optimization techniques. This review comprehensively surveys recent deep learning applications in interpreting cardiac images, encompassing common imaging modalities.
Method:
Following the PRISMA methodology, we reviewed recent research on advanced and frequently used DL architectures in cardiac image analysis, along with the most employed cardiac imaging datasets. Additionally, we analyse recent contributions focused on deep model compression in cardiac image processing tasks.
Results:
The application of DL techniques in cardiac image analysis has seen significant progress through the introduction of new techniques such as transformers, foundation models and compression techniques.
Conclusions:
The paper concludes with a critical discussion addressing open challenges and proposing future research directions in this domain.
