Deep learning-assisted PET imaging achieves fast scan/low-dose examination
Abstract Purpose This study aimed to investigate the impact of a deep learning (DL)-based denoising method on the image quality and lesion detectability of 18F-FDG positron emission tomography (PET) images. Methods Fifty-two oncological patients undergoing an 18F-FDG PET/CT imaging with an acquisiti...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-02-01
|
| Series: | EJNMMI Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40658-022-00431-9 |
| _version_ | 1818486461455925248 |
|---|---|
| author | Yan Xing Wenli Qiao Taisong Wang Ying Wang Chenwei Li Yang Lv Chen Xi Shu Liao Zheng Qian Jinhua Zhao |
| author_facet | Yan Xing Wenli Qiao Taisong Wang Ying Wang Chenwei Li Yang Lv Chen Xi Shu Liao Zheng Qian Jinhua Zhao |
| author_sort | Yan Xing |
| collection | DOAJ |
| description | Abstract Purpose This study aimed to investigate the impact of a deep learning (DL)-based denoising method on the image quality and lesion detectability of 18F-FDG positron emission tomography (PET) images. Methods Fifty-two oncological patients undergoing an 18F-FDG PET/CT imaging with an acquisition of 180 s per bed position were retrospectively included. The list-mode data were rebinned into four datasets: 100% (reference), 75%, 50%, and 33.3% of the total counts, and then reconstructed by OSEM algorithm and post-processed with the DL and Gaussian filter (GS). The image quality was assessed using a 5-point Likert scale, and FDG-avid lesions were counted to measure lesion detectability. Standardized uptake values (SUVs) in livers and lesions, liver signal-to-noise ratio (SNR) and target-to-background ratio (TBR) values were compared between the methods. Subgroup analyses compared TBRs after categorizing lesions based on parameters like lesion diameter, uptake or patient habitus. Results The DL method showed superior performance regarding image noise and inferior performance regarding lesion contrast in the qualitative assessment. More than 96.8% of the lesions were successfully identified in DL images. Excellent agreements on SUV in livers and lesions were found. The DL method significantly improved the liver SNR for count reduction down to 33.3% (p < 0.001). Lesion TBR was not significantly different between DL and reference images of the 75% dataset; furthermore, there was no significant difference either for lesions of > 10 mm or lesions in BMIs of > 25. For the 50% dataset, there was no significant difference between DL and reference images for TBR of lesion with > 15 mm or higher uptake than liver. Conclusions The developed DL method improved both liver SNR and lesion TBR indicating better image quality and lesion conspicuousness compared to GS method. Compared with the reference, it showed non-inferior image quality with reduced counts by 25–50% under various conditions. |
| first_indexed | 2024-12-10T16:23:20Z |
| format | Article |
| id | doaj.art-e882610be8094d0aa26ca846772dadff |
| institution | Directory Open Access Journal |
| issn | 2197-7364 |
| language | English |
| last_indexed | 2024-12-10T16:23:20Z |
| publishDate | 2022-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EJNMMI Physics |
| spelling | doaj.art-e882610be8094d0aa26ca846772dadff2022-12-22T01:41:46ZengSpringerOpenEJNMMI Physics2197-73642022-02-019111710.1186/s40658-022-00431-9Deep learning-assisted PET imaging achieves fast scan/low-dose examinationYan Xing0Wenli Qiao1Taisong Wang2Ying Wang3Chenwei Li4Yang Lv5Chen Xi6Shu Liao7Zheng Qian8Jinhua Zhao9Department of Nuclear Medicine, Shanghai General Hospital, Shanghai Jiaotong UniversityDepartment of Nuclear Medicine, Shanghai General Hospital, Shanghai Jiaotong UniversityDepartment of Nuclear Medicine, Shanghai General Hospital, Shanghai Jiaotong UniversityUnited Imaging HealthcareUnited Imaging HealthcareUnited Imaging HealthcareUnited Imaging HealthcareShanghai United Imaging Intelligence Co. LtdUnited Imaging HealthcareDepartment of Nuclear Medicine, Shanghai General Hospital, Shanghai Jiaotong UniversityAbstract Purpose This study aimed to investigate the impact of a deep learning (DL)-based denoising method on the image quality and lesion detectability of 18F-FDG positron emission tomography (PET) images. Methods Fifty-two oncological patients undergoing an 18F-FDG PET/CT imaging with an acquisition of 180 s per bed position were retrospectively included. The list-mode data were rebinned into four datasets: 100% (reference), 75%, 50%, and 33.3% of the total counts, and then reconstructed by OSEM algorithm and post-processed with the DL and Gaussian filter (GS). The image quality was assessed using a 5-point Likert scale, and FDG-avid lesions were counted to measure lesion detectability. Standardized uptake values (SUVs) in livers and lesions, liver signal-to-noise ratio (SNR) and target-to-background ratio (TBR) values were compared between the methods. Subgroup analyses compared TBRs after categorizing lesions based on parameters like lesion diameter, uptake or patient habitus. Results The DL method showed superior performance regarding image noise and inferior performance regarding lesion contrast in the qualitative assessment. More than 96.8% of the lesions were successfully identified in DL images. Excellent agreements on SUV in livers and lesions were found. The DL method significantly improved the liver SNR for count reduction down to 33.3% (p < 0.001). Lesion TBR was not significantly different between DL and reference images of the 75% dataset; furthermore, there was no significant difference either for lesions of > 10 mm or lesions in BMIs of > 25. For the 50% dataset, there was no significant difference between DL and reference images for TBR of lesion with > 15 mm or higher uptake than liver. Conclusions The developed DL method improved both liver SNR and lesion TBR indicating better image quality and lesion conspicuousness compared to GS method. Compared with the reference, it showed non-inferior image quality with reduced counts by 25–50% under various conditions.https://doi.org/10.1186/s40658-022-00431-9Positron emission tomography and computed tomography (PET/CT)Deep learningDenoising techniqueImage quality |
| spellingShingle | Yan Xing Wenli Qiao Taisong Wang Ying Wang Chenwei Li Yang Lv Chen Xi Shu Liao Zheng Qian Jinhua Zhao Deep learning-assisted PET imaging achieves fast scan/low-dose examination EJNMMI Physics Positron emission tomography and computed tomography (PET/CT) Deep learning Denoising technique Image quality |
| title | Deep learning-assisted PET imaging achieves fast scan/low-dose examination |
| title_full | Deep learning-assisted PET imaging achieves fast scan/low-dose examination |
| title_fullStr | Deep learning-assisted PET imaging achieves fast scan/low-dose examination |
| title_full_unstemmed | Deep learning-assisted PET imaging achieves fast scan/low-dose examination |
| title_short | Deep learning-assisted PET imaging achieves fast scan/low-dose examination |
| title_sort | deep learning assisted pet imaging achieves fast scan low dose examination |
| topic | Positron emission tomography and computed tomography (PET/CT) Deep learning Denoising technique Image quality |
| url | https://doi.org/10.1186/s40658-022-00431-9 |
| work_keys_str_mv | AT yanxing deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT wenliqiao deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT taisongwang deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT yingwang deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT chenweili deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT yanglv deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT chenxi deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT shuliao deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT zhengqian deeplearningassistedpetimagingachievesfastscanlowdoseexamination AT jinhuazhao deeplearningassistedpetimagingachievesfastscanlowdoseexamination |