Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept
Abstract Background To generate high-quality bone scan SPECT images from only 1/7 scan time SPECT images using deep learning-based enhancement method. Materials and methods Normal-dose (925–1110 MBq) clinical technetium 99 m-methyl diphosphonate (99mTc-MDP) SPECT/CT images and corresponding SPECT/CT...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-06-01
|
| Series: | EJNMMI Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40658-022-00472-0 |
| _version_ | 1818237403041628160 |
|---|---|
| author | Boyang Pan Na Qi Qingyuan Meng Jiachen Wang Siyue Peng Chengxiao Qi Nan-Jie Gong Jun Zhao |
| author_facet | Boyang Pan Na Qi Qingyuan Meng Jiachen Wang Siyue Peng Chengxiao Qi Nan-Jie Gong Jun Zhao |
| author_sort | Boyang Pan |
| collection | DOAJ |
| description | Abstract Background To generate high-quality bone scan SPECT images from only 1/7 scan time SPECT images using deep learning-based enhancement method. Materials and methods Normal-dose (925–1110 MBq) clinical technetium 99 m-methyl diphosphonate (99mTc-MDP) SPECT/CT images and corresponding SPECT/CT images with 1/7 scan time from 20 adult patients with bone disease and a phantom were collected to develop a lesion-attention weighted U2-Net (Qin et al. in Pattern Recognit 106:107404, 2020), which produces high-quality SPECT images from fast SPECT/CT images. The quality of synthesized SPECT images from different deep learning models was compared using PSNR and SSIM. Clinic evaluation on 5-point Likert scale (5 = excellent) was performed by two experienced nuclear physicians. Average score and Wilcoxon test were constructed to assess the image quality of 1/7 SPECT, DL-enhanced SPECT and the standard SPECT. SUVmax, SUVmean, SSIM and PSNR from each detectable sphere filled with imaging agent were measured and compared for different images. Results U2-Net-based model reached the best PSNR (40.8) and SSIM (0.788) performance compared with other advanced deep learning methods. The clinic evaluation showed the quality of the synthesized SPECT images is much higher than that of fast SPECT images (P < 0.05). Compared to the standard SPECT images, enhanced images exhibited the same general image quality (P > 0.999), similar detail of 99mTc-MDP (P = 0.125) and the same diagnostic confidence (P = 0.1875). 4, 5 and 6 spheres could be distinguished on 1/7 SPECT, DL-enhanced SPECT and the standard SPECT, respectively. The DL-enhanced phantom image outperformed 1/7 SPECT in SUVmax, SUVmean, SSIM and PSNR in quantitative assessment. Conclusions Our proposed method can yield significant image quality improvement in the noise level, details of anatomical structure and SUV accuracy, which enabled applications of ultra fast SPECT bone imaging in real clinic settings. |
| first_indexed | 2024-12-12T12:25:12Z |
| format | Article |
| id | doaj.art-934d1084dd4447a4ad6337acf8fc3de1 |
| institution | Directory Open Access Journal |
| issn | 2197-7364 |
| language | English |
| last_indexed | 2024-12-12T12:25:12Z |
| publishDate | 2022-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EJNMMI Physics |
| spelling | doaj.art-934d1084dd4447a4ad6337acf8fc3de12022-12-22T00:24:34ZengSpringerOpenEJNMMI Physics2197-73642022-06-019111510.1186/s40658-022-00472-0Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of conceptBoyang Pan0Na Qi1Qingyuan Meng2Jiachen Wang3Siyue Peng4Chengxiao Qi5Nan-Jie Gong6Jun Zhao7RadioDynamic HealthcareDepartment of Nuclear Medicine, Shanghai East Hospital, Tongji University School of MedicineDepartment of Nuclear Medicine, Shanghai East Hospital, Tongji University School of MedicineRadioDynamic HealthcareRadioDynamic HealthcareRadioDynamic HealthcareVector Lab for Intelligent Medical Imaging and Neural Engineering, International Innovation Center of Tsinghua UniversityDepartment of Nuclear Medicine, Shanghai East Hospital, Tongji University School of MedicineAbstract Background To generate high-quality bone scan SPECT images from only 1/7 scan time SPECT images using deep learning-based enhancement method. Materials and methods Normal-dose (925–1110 MBq) clinical technetium 99 m-methyl diphosphonate (99mTc-MDP) SPECT/CT images and corresponding SPECT/CT images with 1/7 scan time from 20 adult patients with bone disease and a phantom were collected to develop a lesion-attention weighted U2-Net (Qin et al. in Pattern Recognit 106:107404, 2020), which produces high-quality SPECT images from fast SPECT/CT images. The quality of synthesized SPECT images from different deep learning models was compared using PSNR and SSIM. Clinic evaluation on 5-point Likert scale (5 = excellent) was performed by two experienced nuclear physicians. Average score and Wilcoxon test were constructed to assess the image quality of 1/7 SPECT, DL-enhanced SPECT and the standard SPECT. SUVmax, SUVmean, SSIM and PSNR from each detectable sphere filled with imaging agent were measured and compared for different images. Results U2-Net-based model reached the best PSNR (40.8) and SSIM (0.788) performance compared with other advanced deep learning methods. The clinic evaluation showed the quality of the synthesized SPECT images is much higher than that of fast SPECT images (P < 0.05). Compared to the standard SPECT images, enhanced images exhibited the same general image quality (P > 0.999), similar detail of 99mTc-MDP (P = 0.125) and the same diagnostic confidence (P = 0.1875). 4, 5 and 6 spheres could be distinguished on 1/7 SPECT, DL-enhanced SPECT and the standard SPECT, respectively. The DL-enhanced phantom image outperformed 1/7 SPECT in SUVmax, SUVmean, SSIM and PSNR in quantitative assessment. Conclusions Our proposed method can yield significant image quality improvement in the noise level, details of anatomical structure and SUV accuracy, which enabled applications of ultra fast SPECT bone imaging in real clinic settings.https://doi.org/10.1186/s40658-022-00472-0SPECTBoneImage quality enhancementDeep learning |
| spellingShingle | Boyang Pan Na Qi Qingyuan Meng Jiachen Wang Siyue Peng Chengxiao Qi Nan-Jie Gong Jun Zhao Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept EJNMMI Physics SPECT Bone Image quality enhancement Deep learning |
| title | Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept |
| title_full | Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept |
| title_fullStr | Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept |
| title_full_unstemmed | Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept |
| title_short | Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept |
| title_sort | ultra high speed spect bone imaging enabled by a deep learning enhancement method a proof of concept |
| topic | SPECT Bone Image quality enhancement Deep learning |
| url | https://doi.org/10.1186/s40658-022-00472-0 |
| work_keys_str_mv | AT boyangpan ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT naqi ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT qingyuanmeng ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT jiachenwang ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT siyuepeng ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT chengxiaoqi ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT nanjiegong ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept AT junzhao ultrahighspeedspectboneimagingenabledbyadeeplearningenhancementmethodaproofofconcept |