Related Experiment Video
Updated: Oct 17, 2025
High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
Published on: December 16, 2022
Convolutional neural network-based automatic heart segmentation and quantitation in 123I-metaiodobenzylguanidine
Shintaro Saito1, Kenichi Nakajima2, Lars Edenbrandt3
1Department of Nuclear Medicine, Kanazawa University Graduate School of Medicine, 13-1 Takara-machi, Kanazawa, 920-8640, Japan. shintaro1515@stu.kanazawa-u.ac.jp.
Insights
A novel convolutional neural network (CNN) accurately segments cardiac regions in 123I-metaiodobenzylguanidine (MIBG) SPECT imaging. This method reliably quantifies heart counts and washout rates (WR) in 3D, offering a new approach for SPECT image analysis.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Nuclear Cardiology
Background:
- Three-dimensional (3D) cardiac segmentation in 123I-metaiodobenzylguanidine (MIBG) SPECT imaging is not well-established.
- Accurate quantification of cardiac MIBG uptake and washout rates (WR) is crucial for diagnosing cardiac autonomic neuropathy.
Purpose of the Study:
- To develop and validate a convolutional neural network (CNN) for automatic 3D cardiac segmentation in 123I-MIBG SPECT images.
- To compare CNN-derived heart counts and WR with conventional planar imaging quantitation.
Main Methods:
- A CNN was trained to segment lungs, liver, and subsequently the heart on early and late 123I-MIBG SPECT images from 48 patients.
- The CNN models were evaluated using fourfold cross-validation.
- CNN-based SPECT heart counts and WR were calculated and compared with planar imaging parameters, with corrections for physical decay, injected dose, and body weight.
Main Results:
- The CNN successfully segmented cardiac regions in patients with both normal and reduced MIBG uptake.
- CNN-based SPECT heart counts showed significant correlation with conventional planar heart counts (R² = 0.862).
- CNN-based and planar WRs also demonstrated strong correlation (R² = 0.584), with 87.2% agreement in high/low WR classification.
Conclusions:
- Convolutional neural networks can effectively perform 3D cardiac segmentation on 123I-MIBG SPECT images.
- The CNN-based method provides reliable 3D quantification of heart counts and WR.
- This approach represents a novel and potentially superior method for quantifying cardiac innervation using SPECT imaging.
Background:
Since three-dimensional segmentation of cardiac region in 123I-metaiodobenzylguanidine (MIBG) study has not been established, this study aimed to achieve organ segmentation using a convolutional neural network (CNN) with 123I-MIBG single photon emission computed tomography (SPECT) imaging, to calculate heart counts and washout rates (WR) automatically and to compare with conventional quantitation based on planar imaging.
Methods:
We assessed 48 patients (aged 68.4 ± 11.7 years) with heart and neurological diseases, including chronic heart failure, dementia with Lewy bodies, and Parkinson's disease. All patients were assessed by early and late 123I-MIBG planar and SPECT imaging. The CNN was initially trained to individually segment the lungs and liver on early and late SPECT images. The segmentation masks were aligned, and then, the CNN was trained to directly segment the heart, and all models were evaluated using fourfold cross-validation. The CNN-based average heart counts and WR were calculated and compared with those determined using planar parameters. The CNN-based SPECT and conventional planar heart counts were corrected by physical time decay, injected dose of 123I-MIBG, and body weight. We also divided WR into normal and abnormal groups from linear regression lines determined by the relationship between planar WR and CNN-based WR and then analyzed agreement between them.
Results:
The CNN segmented the cardiac region in patients with normal and reduced uptake. The CNN-based SPECT heart counts significantly correlated with conventional planar heart counts with and without background correction and a planar heart-to-mediastinum ratio (R2 = 0.862, 0.827, and 0.729, p < 0.0001, respectively). The CNN-based and planar WRs also correlated with and without background correction and WR based on heart-to-mediastinum ratios of R2 = 0.584, 0.568 and 0.507, respectively (p < 0.0001). Contingency table findings of high and low WR (cutoffs: 34% and 30% for planar and SPECT studies, respectively) showed 87.2% agreement between CNN-based and planar methods.
Conclusions:
The CNN could create segmentation from SPECT images, and average heart counts and WR were reliably calculated three-dimensionally, which might be a novel approach to quantifying SPECT images of innervation.
