Related Experiment Video
Updated: Jun 8, 2025
Identifying Coronary Artery Calcification on Non-gated Computed Tomography Scans
Published on: August 28, 2018
Classification of coronary artery disease severity based on SPECT MPI polarmap images and deep learning: A study on
Jui-Jen Chen1, Ting-Yi Su2, Chien-Che Huang3
1Department of Nuclear Medicine, Chang Gung Memorial Hospital, Kaohsiung Medical Center, Chang Gung University College of Medicine, Kaohsiung.
Insights
Deep learning accurately predicts multivessel disease (MVD) using SPECT MPI scans, improving coronary artery disease assessment. This approach offers efficient diagnosis and potential cost savings.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Coronary artery disease (CAD) is a major global health issue.
- Single photon emission computed tomography myocardial perfusion imaging (SPECT MPI) is used to assess CAD severity.
- Manual interpretation of SPECT MPI can lead to errors; deep learning offers automated analysis.
Purpose of the Study:
- To apply deep learning for assessing CAD severity and identifying multivessel disease (MVD).
- To evaluate the efficacy of the EfficientNet-V2 model combined with DeepSMOTE for MVD prediction using SPECT MPI images.
Main Methods:
- Utilized the EfficientNet-V2 deep learning model.
- Employed DeepSMOTE for data augmentation and model training.
- Analyzed a dataset of 254 patients with SPECT MPI images.
Main Results:
- Achieved an accuracy of 84.31% in predicting MVD.
- Obtained an area under the receiver operating characteristic curve (AUC) of 0.8714 for MVD prediction.
- Successfully distinguished between MVD and single-vessel disease (SVD).
Conclusions:
- Deep learning techniques are feasible for predicting MVD from SPECT MPI images.
- The EfficientNet-V2 and DeepSMOTE integration effectively assesses CAD severity and differentiates MVD.
- This approach enables early MVD prediction, potentially improving patient outcomes and reducing costs.
Background:
Coronary artery disease (CAD) is a global health concern. Conventional single photon emission computed tomography myocardial perfusion imaging (SPECT MPI) is a noninvasive method for assessing the severity of CAD. However, it relies on manual classification by clinicians, which can lead to visual fatigue and potential errors. Deep learning techniques have displayed promising results in CAD diagnosis and prediction, providing efficient and accurate analysis of medical images.
Methods:
In this study, we explore the application of deep learning methods for assessing the severity of CAD and identifying cases of multivessel disease (MVD). We utilized the EfficientNet-V2 model in combination with DeepSMOTE to evaluate CAD severity using SPECT MPI images.
Results:
Utilizing a dataset consisting of 254 patients (176 with MVD and 78 with single-vessel disease [SVD]), our model achieved an accuracy rate of 84.31% and area under the receiver operating characteristic curve (AUC) value of 0.8714 in predicting cases of MVD. These results underline the promising potential of our approach in MVD prediction, offering valuable diagnostic insights and the prospect of reducing medical costs.
Conclusion:
This study emphasizes the feasibility of employing deep learning techniques for predicting MVD based on SPECT MPI images. The integration of Efficient-Net-V2 and DeepSMOTE methods effectively evaluates CAD severity and distinguishes MVD from SVD. Our research presents a practical approach to the early prediction and diagnosis of MVD, ultimately leading to enhanced patient outcomes and reduced healthcare costs.
