Related Experiment Video
Updated: Jul 18, 2026
Myocardial Infarction and Functional Outcome Assessment in Pigs
Published on: April 25, 2014
Segmentation of the Left Ventricle and Its Pathologies for Acute Myocardial Infarction After Reperfusion in LGE-CMR
Insights
This study introduces the LGE-LVP dataset and LVPSegNet model for segmenting left ventricle pathologies from cardiac MRI. The model achieves state-of-the-art performance, matching clinician accuracy.
Area of Science:
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
- Medical Image Analysis
Background:
- Accurate segmentation of left ventricle (LV) pathologies like myocardial infarction and microvascular obstruction from late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) images is critical for managing cardiac dysfunction.
- Challenges in LGE-CMR segmentation include limited datasets, diverse pathological shapes/locations, extreme class imbalance, and overlapping intensity distributions.
Purpose of the Study:
- To address the segmentation challenges by releasing a benchmark dataset and proposing a novel deep learning model.
- To facilitate automated segmentation of the left ventricle and its associated pathologies in LGE-CMR images.
Main Methods:
- Development of the LGE-LVP dataset, a benchmark containing 140 patients with LV myocardial infarction and microvascular obstruction.
- Proposal of LVPSegNet, a progressive deep learning model incorporating adaptive region of interest extraction, sample augmentation, curriculum learning, and multiple receptive field fusion.
- Rigorous comparison against state-of-the-art models on internal and external datasets.
Main Results:
- The proposed LVPSegNet model demonstrated superior performance compared to existing methods on both geometric and clinical metrics.
- LVPSegNet's segmentation results closely approximated the performance of expert clinicians.
- The LGE-LVP dataset provides crucial data support for research in cardiac pathology segmentation.
Conclusions:
- The LGE-LVP dataset and LVPSegNet offer a practical and effective solution for automated segmentation of left ventricle pathologies in LGE-CMR imaging.
- This work facilitates improved clinical decision-making and patient management through accurate cardiac MRI analysis.
- The dataset and source code are publicly available to promote further research and development.
Abstract:
Due to the association with higher incidence of left ventricular dysfunction and complications, segmentation of left ventricle and related pathological tissues: microvascular obstruction and myocardial infarction from late gadolinium enhancement cardiac magnetic resonance images is crucially important. However, lack of datasets, diverse shapes and locations, extreme imbalanced class, severe intensity distribution overlapping are the main challenges. We first release a late gadolinium enhancement cardiac magnetic resonance benchmark dataset LGE-LVP containing 140 patients with left ventricle myocardial infarction and concomitant microvascular obstruction. Then, a progressive deep learning model LVPSegNet is proposed to segment the left ventricle and its pathologies via adaptive region of interest extraction, sample augmentation, curriculum learning, and multiple receptive field fusion in dealing with the challenges. Comprehensive comparisons with state-of-the-art models on the internal and external datasets demonstrate that the proposed model performs the best on both geometric and clinical metrics and it most closely matched the clinician's performance. Overall, the released LGE-LVP dataset alongside the LVPSegNet we proposed offer a practical solution for automated left ventricular and its pathologies segmentation by providing data support and facilitating effective segmentation. The dataset and source codes will be released via https://github.com/DFLAG-NEU/LVPSegNet.
Related Concept Videos
01:21Imaging Studies for Cardiovascular System IV: CMRI
01:23Mitral Stenosis II: Clinical features and Diagnostic Tests
01:22Aortic Regurgitation II: Clinical Features and Diagnostic Tests
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:25Cardiomyopathy I: Introduction and Classification