Imaging foundation model for universal enhancement of non-ideal measurement CT
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912976788783104 |
|---|---|
| author | Ge, Rongjun Liu, Yuxin Wu, Zhan Yang, Shangwen Gao, Yuan You, Chenyu Wang, Ge Li, Shuo He, Yuting Chen, Yang |
| author_facet | Ge, Rongjun Liu, Yuxin Wu, Zhan Yang, Shangwen Gao, Yuan You, Chenyu Wang, Ge Li, Shuo He, Yuting Chen, Yang |
| contents | Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We propose the multi-scale integrated Transformer AMPlifier (TAMP), the first imaging foundation model for universal NICT enhancement. Pre-trained on 10.8 million physics-driven simulated NICT images, TAMP generalizes effectively across various NICT settings, defect degrees, and body regions. Moreover, a parameter-efficient fine-tuning strategy enables TAMP to adapt to specific clinical scenarios using only few slices. Extensive experiments, including radiologists and real-world validations, demonstrate that TAMP consistently improves image quality and clinical acceptability, underscoring its significant potential to advance CT imaging and broaden NICT applications in clinical practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01591 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imaging foundation model for universal enhancement of non-ideal measurement CT Ge, Rongjun Liu, Yuxin Wu, Zhan Yang, Shangwen Gao, Yuan You, Chenyu Wang, Ge Li, Shuo He, Yuting Chen, Yang Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We propose the multi-scale integrated Transformer AMPlifier (TAMP), the first imaging foundation model for universal NICT enhancement. Pre-trained on 10.8 million physics-driven simulated NICT images, TAMP generalizes effectively across various NICT settings, defect degrees, and body regions. Moreover, a parameter-efficient fine-tuning strategy enables TAMP to adapt to specific clinical scenarios using only few slices. Extensive experiments, including radiologists and real-world validations, demonstrate that TAMP consistently improves image quality and clinical acceptability, underscoring its significant potential to advance CT imaging and broaden NICT applications in clinical practice. |
| title | Imaging foundation model for universal enhancement of non-ideal measurement CT |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.01591 |