Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei
PurposeTo test the feasibility and consistency of a deep-learning (DL) accelerated QSM method for deep brain nuclei evaluation.MethodsParticipants were scanned with both parallel imaging (PI)-QSM and DL-QSM methods. The PI- and DL-QSM scans had identical imaging parameters other than acceleration fa...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2025.1522227/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591717773082624 |
|---|---|
| author | Ying Zhou Ying Zhou Lingyun Liu Shan Xu Yongquan Ye Ruiting Zhang Minming Zhang Jianzhong Sun Peiyu Huang |
| author_facet | Ying Zhou Ying Zhou Lingyun Liu Shan Xu Yongquan Ye Ruiting Zhang Minming Zhang Jianzhong Sun Peiyu Huang |
| author_sort | Ying Zhou |
| collection | DOAJ |
| description | PurposeTo test the feasibility and consistency of a deep-learning (DL) accelerated QSM method for deep brain nuclei evaluation.MethodsParticipants were scanned with both parallel imaging (PI)-QSM and DL-QSM methods. The PI- and DL-QSM scans had identical imaging parameters other than acceleration factors (AF). The DL-QSM employed Poisson disk style under-sampling scheme and a previously developed cascaded CNN based reconstruction model, with acquisition time of 4:35, 3:15, and 2:11 for AF of 3, 4, and 5, respectively. For PI-QSM acquisition, the AF was 2 and the acquisition time was 6:46. The overall image similarity was assessed between PI- and DL-QSM images using the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). QSM values from 7 deep brain nuclei were extracted and agreements between images with different Afs were assessed. Finally, the correlations between age and QSM values in the selected deep brain nuclei were evaluated.Results59 participants were recruited. Compared to PI-QSM images, the mean SSIM of DL images were 0.87, 0.86, and 0.85 for AF of 3, 4, and 5. The mean PSNR were 44.56, 44.53, and 44.23. Susceptibility values from DL-QSM were highly consistent with routine PI-QSM images, with differences of less than 5% at the group level. Furthermore, the associations between age and QSM values could be consistently revealed.ConclusionDL-QSM could be used for measuring susceptibility values of deep brain nucleus. An AF up to 5 did not significantly impact the correlation between age and susceptibility in deep brain nuclei. |
| format | Article |
| id | doaj-art-97f79dd22f1f401faa2f21a73bdb44a9 |
| institution | Kabale University |
| issn | 1662-453X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj-art-97f79dd22f1f401faa2f21a73bdb44a92025-01-22T07:11:07ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-01-011910.3389/fnins.2025.15222271522227Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nucleiYing Zhou0Ying Zhou1Lingyun Liu2Shan Xu3Yongquan Ye4Ruiting Zhang5Minming Zhang6Jianzhong Sun7Peiyu Huang8Taizhou Central Hospital (Taizhou University Hospital), Taizhou, ChinaThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaUnited Imaging, Houston, TX, United StatesThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaThe Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaPurposeTo test the feasibility and consistency of a deep-learning (DL) accelerated QSM method for deep brain nuclei evaluation.MethodsParticipants were scanned with both parallel imaging (PI)-QSM and DL-QSM methods. The PI- and DL-QSM scans had identical imaging parameters other than acceleration factors (AF). The DL-QSM employed Poisson disk style under-sampling scheme and a previously developed cascaded CNN based reconstruction model, with acquisition time of 4:35, 3:15, and 2:11 for AF of 3, 4, and 5, respectively. For PI-QSM acquisition, the AF was 2 and the acquisition time was 6:46. The overall image similarity was assessed between PI- and DL-QSM images using the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). QSM values from 7 deep brain nuclei were extracted and agreements between images with different Afs were assessed. Finally, the correlations between age and QSM values in the selected deep brain nuclei were evaluated.Results59 participants were recruited. Compared to PI-QSM images, the mean SSIM of DL images were 0.87, 0.86, and 0.85 for AF of 3, 4, and 5. The mean PSNR were 44.56, 44.53, and 44.23. Susceptibility values from DL-QSM were highly consistent with routine PI-QSM images, with differences of less than 5% at the group level. Furthermore, the associations between age and QSM values could be consistently revealed.ConclusionDL-QSM could be used for measuring susceptibility values of deep brain nucleus. An AF up to 5 did not significantly impact the correlation between age and susceptibility in deep brain nuclei.https://www.frontiersin.org/articles/10.3389/fnins.2025.1522227/fullquantitative susceptibility mappingaccelerationbrain nucleideep learningparallel imaging |
| spellingShingle | Ying Zhou Ying Zhou Lingyun Liu Shan Xu Yongquan Ye Ruiting Zhang Minming Zhang Jianzhong Sun Peiyu Huang Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei Frontiers in Neuroscience quantitative susceptibility mapping acceleration brain nuclei deep learning parallel imaging |
| title | Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei |
| title_full | Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei |
| title_fullStr | Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei |
| title_full_unstemmed | Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei |
| title_short | Validation of deep-learning accelerated quantitative susceptibility mapping for deep brain nuclei |
| title_sort | validation of deep learning accelerated quantitative susceptibility mapping for deep brain nuclei |
| topic | quantitative susceptibility mapping acceleration brain nuclei deep learning parallel imaging |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2025.1522227/full |
| work_keys_str_mv | AT yingzhou validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT yingzhou validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT lingyunliu validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT shanxu validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT yongquanye validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT ruitingzhang validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT minmingzhang validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT jianzhongsun validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei AT peiyuhuang validationofdeeplearningacceleratedquantitativesusceptibilitymappingfordeepbrainnuclei |