1
|
Guo X, Shi L, Chen X, Liu Q, Zhou B, Xie H, Liu YH, Palyo R, Miller EJ, Sinusas AJ, Staib L, Spottiswoode B, Liu C, Dvornek NC. TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction. Med Image Anal 2024; 96:103190. [PMID: 38820677 PMCID: PMC11180595 DOI: 10.1016/j.media.2024.103190] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 04/12/2024] [Accepted: 05/01/2024] [Indexed: 06/02/2024]
Abstract
Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82Rb) 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 82Rb 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. The code is available at https://github.com/gxq1998/TAI-GAN.
Collapse
Affiliation(s)
- Xueqi Guo
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
| | | | - Xiongchao Chen
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
| | - Qiong Liu
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
| | - Bo Zhou
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
| | - Huidong Xie
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
| | - Yi-Hwa Liu
- Department of Internal Medicine, Yale University, New Haven, CT, USA
| | | | - Edward J Miller
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Internal Medicine, Yale University, New Haven, CT, USA; Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Albert J Sinusas
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Internal Medicine, Yale University, New Haven, CT, USA; Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Lawrence Staib
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | | | - Chi Liu
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.
| | - Nicha C Dvornek
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.
| |
Collapse
|
2
|
Guo X, Zhou B, Pigg D, Spottiswoode B, Casey ME, Liu C, Dvornek NC. Unsupervised inter-frame motion correction for whole-body dynamic PET using convolutional long short-term memory in a convolutional neural network. Med Image Anal 2022; 80:102524. [PMID: 35797734 PMCID: PMC10923189 DOI: 10.1016/j.media.2022.102524] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2021] [Revised: 06/08/2022] [Accepted: 06/24/2022] [Indexed: 11/24/2022]
Abstract
Subject motion in whole-body dynamic PET introduces inter-frame mismatch and seriously impacts parametric imaging. Traditional non-rigid registration methods are generally computationally intense and time-consuming. Deep learning approaches are promising in achieving high accuracy with fast speed, but have yet been investigated with consideration for tracer distribution changes or in the whole-body scope. In this work, we developed an unsupervised automatic deep learning-based framework to correct inter-frame body motion. The motion estimation network is a convolutional neural network with a combined convolutional long short-term memory layer, fully utilizing dynamic temporal features and spatial information. Our dataset contains 27 subjects each under a 90-min FDG whole-body dynamic PET scan. Evaluating performance in motion simulation studies and a 9-fold cross-validation on the human subject dataset, compared with both traditional and deep learning baselines, we demonstrated that the proposed network achieved the lowest motion prediction error, obtained superior performance in enhanced qualitative and quantitative spatial alignment between parametric Ki and Vb images, and significantly reduced parametric fitting error. We also showed the potential of the proposed motion correction method for impacting downstream analysis of the estimated parametric images, improving the ability to distinguish malignant from benign hypermetabolic regions of interest. Once trained, the motion estimation inference time of our proposed network was around 460 times faster than the conventional registration baseline, showing its potential to be easily applied in clinical settings.
Collapse
Affiliation(s)
- Xueqi Guo
- Department of Biomedical Engineering, Yale University, New Haven, CT 06511, USA
| | - Bo Zhou
- Department of Biomedical Engineering, Yale University, New Haven, CT 06511, USA
| | - David Pigg
- Siemens Medical Solutions USA, Inc., Knoxville, TN, 37932, USA
| | | | - Michael E Casey
- Siemens Medical Solutions USA, Inc., Knoxville, TN, 37932, USA
| | - Chi Liu
- Department of Biomedical Engineering, Yale University, New Haven, CT 06511, USA; Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06511, USA.
| | - Nicha C Dvornek
- Department of Biomedical Engineering, Yale University, New Haven, CT 06511, USA; Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT 06511, USA.
| |
Collapse
|