TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914679710810112 |
|---|---|
| author | Guo, Xueqi Shi, Luyao Chen, Xiongchao Liu, Qiong Zhou, Bo Xie, Huidong Liu, Yi-Hwa Palyo, Richard Miller, Edward J. Sinusas, Albert J. Staib, Lawrence H. Spottiswoode, Bruce Liu, Chi Dvornek, Nicha C. |
| author_facet | Guo, Xueqi Shi, Luyao Chen, Xiongchao Liu, Qiong Zhou, Bo Xie, Huidong Liu, Yi-Hwa Palyo, Richard Miller, Edward J. Sinusas, Albert J. Staib, Lawrence H. Spottiswoode, Bruce Liu, Chi Dvornek, Nicha C. |
| contents | Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82-Rb) myocardial perfusion imaging impacts myocardial blood flow (MBF) quantification and the diagnosis accuracy of coronary artery diseases. However, the high cross-frame distribution variation due to rapid tracer kinetics poses a considerable challenge for inter-frame motion correction, especially for early frames where intensity-based image registration techniques often fail. To address this issue, we propose a novel method called Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) that utilizes an all-to-one mapping to convert early frames into those with tracer distribution similar to the last reference frame. The TAI-GAN consists of a feature-wise linear modulation layer that encodes channel-wise parameters generated from temporal information and rough cardiac segmentation masks with local shifts that serve as anatomical information. Our proposed method was evaluated on a clinical 82-Rb PET dataset, and the results show that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, the motion estimation accuracy and subsequent myocardial blood flow (MBF) quantification with both conventional and deep learning-based motion correction methods were improved compared to using the original frames. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09567 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction Guo, Xueqi Shi, Luyao Chen, Xiongchao Liu, Qiong Zhou, Bo Xie, Huidong Liu, Yi-Hwa Palyo, Richard Miller, Edward J. Sinusas, Albert J. Staib, Lawrence H. Spottiswoode, Bruce Liu, Chi Dvornek, Nicha C. Image and Video Processing Computer Vision and Pattern Recognition Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82-Rb) myocardial perfusion imaging impacts myocardial blood flow (MBF) quantification and the diagnosis accuracy of coronary artery diseases. However, the high cross-frame distribution variation due to rapid tracer kinetics poses a considerable challenge for inter-frame motion correction, especially for early frames where intensity-based image registration techniques often fail. To address this issue, we propose a novel method called Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) that utilizes an all-to-one mapping to convert early frames into those with tracer distribution similar to the last reference frame. The TAI-GAN consists of a feature-wise linear modulation layer that encodes channel-wise parameters generated from temporal information and rough cardiac segmentation masks with local shifts that serve as anatomical information. Our proposed method was evaluated on a clinical 82-Rb PET dataset, and the results show that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, the motion estimation accuracy and subsequent myocardial blood flow (MBF) quantification with both conventional and deep learning-based motion correction methods were improved compared to using the original frames. |
| title | TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.09567 |