Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach
Abstract Background Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, t...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01570-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861456729276416 |
|---|---|
| author | Pei Yang Zeao Zhang Jianan Wei Lisha Jiang Liqian Yu Huawei Cai Lin Li Quan Guo Zhen Zhao |
| author_facet | Pei Yang Zeao Zhang Jianan Wei Lisha Jiang Liqian Yu Huawei Cai Lin Li Quan Guo Zhen Zhao |
| author_sort | Pei Yang |
| collection | DOAJ |
| description | Abstract Background Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, these limitations have led to increasing interest in CT-free AC, with deep learning (DL) offering promising solutions. We proposed a new DL-based CT-free AC methods for cardiac SPECT. Methods We developed a feature alignment attenuation correction network (FA-ACNet) based on the 3D U-Net framework to generate predicted DL-based AC SPECT (Deep AC). The network was trained on 167 cardiac SPECT/CT studies using 5-fold cross validation and tested in an independent testing set (n = 35), with CTAC serving as the reference. During training, multi-scale features from non-attenuation-corrected (NAC) SPECT and CT were processed separately and then aligned with the encoded features from NAC SPECT using adversarial learning and distance metric learning techniques. The performance of FA-ACNet was evaluated using mean square error (MSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Additionally, semi-quantitative evaluation of Deep AC images was performed and compared to CTAC using Bland-Altman plots. Results FA-ACNet achieved an MSE of 16.94 ± 2.03 × 10− 6, SSIM of 0.9955 ± 0.0006 and PSNR of 43.73 ± 0.50 after 5-fold cross validation. Compared to U-Net, MSE and PSNR improved by aligning multi-scale features from NAC SPECT and CT with those from NAC SPECT. In the testing set, FA-ACNet achieved an MSE of 11.98 × 10− 6, SSIM of 0.9976 and PSNR of 45.54. The 95% limits of agreement (LoAs) between the Deep AC and CTAC images for the summed stress/rest scores (SSS/SRS) were [− 2.3, 2.8] and [-1.9,2.1] in the training set and testing set respectively. Changes in perfusion categories were observed in 4.19% and 5.9% of studies assessed for global perfusion scores in the training set and testing set. Conclusion We propose a novel DL-based CT-free AC approach for cardiac SPECT, which can generate AC images without the need for a CT scan. By leveraging multi-scale features from both NAC SPECT and CT, the performance of CT-free AC is significantly enhanced, offering a promising alternative for future DL-based AC strategies. |
| format | Article |
| id | doaj-art-34f5029994504ded972f18309c019b00 |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-34f5029994504ded972f18309c019b002025-02-09T12:59:58ZengBMCBMC Medical Imaging1471-23422025-02-0125111110.1186/s12880-025-01570-yDeep learning-based CT-free attenuation correction for cardiac SPECT: a new approachPei Yang0Zeao Zhang1Jianan Wei2Lisha Jiang3Liqian Yu4Huawei Cai5Lin Li6Quan Guo7Zhen Zhao8Department of Nuclear Medicine, West China Hospital of Sichuan UniversityMachine Intelligence Laboratory, College of Computer Science, Sichuan UniversityMachine Intelligence Laboratory, College of Computer Science, Sichuan UniversityDepartment of Nuclear Medicine, West China Hospital of Sichuan UniversityDepartment of Nuclear Medicine, West China Hospital of Sichuan UniversityDepartment of Nuclear Medicine, West China Hospital of Sichuan UniversityDepartment of Nuclear Medicine, West China Hospital of Sichuan UniversityMachine Intelligence Laboratory, College of Computer Science, Sichuan UniversityDepartment of Nuclear Medicine, West China Hospital of Sichuan UniversityAbstract Background Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, these limitations have led to increasing interest in CT-free AC, with deep learning (DL) offering promising solutions. We proposed a new DL-based CT-free AC methods for cardiac SPECT. Methods We developed a feature alignment attenuation correction network (FA-ACNet) based on the 3D U-Net framework to generate predicted DL-based AC SPECT (Deep AC). The network was trained on 167 cardiac SPECT/CT studies using 5-fold cross validation and tested in an independent testing set (n = 35), with CTAC serving as the reference. During training, multi-scale features from non-attenuation-corrected (NAC) SPECT and CT were processed separately and then aligned with the encoded features from NAC SPECT using adversarial learning and distance metric learning techniques. The performance of FA-ACNet was evaluated using mean square error (MSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Additionally, semi-quantitative evaluation of Deep AC images was performed and compared to CTAC using Bland-Altman plots. Results FA-ACNet achieved an MSE of 16.94 ± 2.03 × 10− 6, SSIM of 0.9955 ± 0.0006 and PSNR of 43.73 ± 0.50 after 5-fold cross validation. Compared to U-Net, MSE and PSNR improved by aligning multi-scale features from NAC SPECT and CT with those from NAC SPECT. In the testing set, FA-ACNet achieved an MSE of 11.98 × 10− 6, SSIM of 0.9976 and PSNR of 45.54. The 95% limits of agreement (LoAs) between the Deep AC and CTAC images for the summed stress/rest scores (SSS/SRS) were [− 2.3, 2.8] and [-1.9,2.1] in the training set and testing set respectively. Changes in perfusion categories were observed in 4.19% and 5.9% of studies assessed for global perfusion scores in the training set and testing set. Conclusion We propose a novel DL-based CT-free AC approach for cardiac SPECT, which can generate AC images without the need for a CT scan. By leveraging multi-scale features from both NAC SPECT and CT, the performance of CT-free AC is significantly enhanced, offering a promising alternative for future DL-based AC strategies.https://doi.org/10.1186/s12880-025-01570-yDeep learningSPECTMyocardial perfusion imagingAttenuation correction |
| spellingShingle | Pei Yang Zeao Zhang Jianan Wei Lisha Jiang Liqian Yu Huawei Cai Lin Li Quan Guo Zhen Zhao Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach BMC Medical Imaging Deep learning SPECT Myocardial perfusion imaging Attenuation correction |
| title | Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach |
| title_full | Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach |
| title_fullStr | Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach |
| title_full_unstemmed | Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach |
| title_short | Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach |
| title_sort | deep learning based ct free attenuation correction for cardiac spect a new approach |
| topic | Deep learning SPECT Myocardial perfusion imaging Attenuation correction |
| url | https://doi.org/10.1186/s12880-025-01570-y |
| work_keys_str_mv | AT peiyang deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT zeaozhang deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT jiananwei deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT lishajiang deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT liqianyu deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT huaweicai deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT linli deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT quanguo deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach AT zhenzhao deeplearningbasedctfreeattenuationcorrectionforcardiacspectanewapproach |