Iterative framework for image registration and partial volume correction in brain positron emission tomography

A cycle-consistent adversarial network for brain PET partial volume correction without prior anatomical information

PURPOSE

Partial volume effect (PVE) is a consequence of the limited spatial resolution of PET scanners. PVE can cause the intensity values of a particular voxel to be underestimated or overestimated due to the effect of surrounding tracer uptake. We propose a novel partial volume correction (PVC) technique to overcome the adverse effects of PVE on PET images.

METHODS

Two hundred and twelve clinical brain PET scans, including 50 18F-Fluorodeoxyglucose (18F-FDG), 50 18F-Flortaucipir, 36 18F-Flutemetamol, and 76 18F-FluoroDOPA, and their corresponding T1-weighted MR images were enrolled in this study. The Iterative Yang technique was used for PVC as a reference or surrogate of the ground truth for evaluation. A cycle-consistent adversarial network (CycleGAN) was trained to directly map non-PVC PET images to PVC PET images. Quantitative analysis using various metrics, including structural similarity index (SSIM), root mean squared error (RMSE), and peak signal-to-noise ratio (PSNR), was performed. Furthermore, voxel-wise and region-wise-based correlations of activity concentration between the predicted and reference images were evaluated through joint histogram and Bland and Altman analysis. In addition, radiomic analysis was performed by calculating 20 radiomic features within 83 brain regions. Finally, a voxel-wise two-sample t-test was used to compare the predicted PVC PET images with reference PVC images for each radiotracer.

RESULTS

The Bland and Altman analysis showed the largest and smallest variance for 18F-FDG (95% CI: - 0.29, + 0.33 SUV, mean = 0.02 SUV) and 18F-Flutemetamol (95% CI: - 0.26, + 0.24 SUV, mean =  - 0.01 SUV), respectively. The PSNR was lowest (29.64 ± 1.13 dB) for 18F-FDG and highest (36.01 ± 3.26 dB) for 18F-Flutemetamol. The smallest and largest SSIM were achieved for 18F-FDG (0.93 ± 0.01) and 18F-Flutemetamol (0.97 ± 0.01), respectively. The average relative error for the kurtosis radiomic feature was 3.32%, 9.39%, 4.17%, and 4.55%, while it was 4.74%, 8.80%, 7.27%, and 6.81% for NGLDM_contrast feature for 18F-Flutemetamol, 18F-FluoroDOPA, 18F-FDG, and 18F-Flortaucipir, respectively.

CONCLUSION

An end-to-end CycleGAN PVC method was developed and evaluated. Our model generates PVC images from the original non-PVC PET images without requiring additional anatomical information, such as MRI or CT. Our model eliminates the need for accurate registration or segmentation or PET scanner system response characterization. In addition, no assumptions regarding anatomical structure size, homogeneity, boundary, or background level are required.

DeepPVC: prediction of a partial volume-corrected map for brain positron emission tomography studies via a deep convolutional neural network

Background

Partial volume correction with anatomical magnetic resonance (MR) images (MR-PVC) is useful for accurately quantifying tracer uptake on brain positron emission tomography (PET) images. However, MR segmentation processes for MR-PVC are time-consuming and prevent the widespread clinical use of MR-PVC. Here, we aimed to develop a deep learning model to directly predict PV-corrected maps from PET and MR images, ultimately improving the MR-PVC throughput.

Methods

We used MR T1-weighted and [¹¹C]PiB PET images as input data from 192 participants from the Alzheimer’s Disease Neuroimaging Initiative database. We calculated PV-corrected maps as the training target using the region-based voxel-wise PVC method. Two-dimensional U-Net model was trained and validated by sixfold cross-validation with the dataset from the 156 participants, and then tested using MR T1-weighted and [¹¹C]PiB PET images from 36 participants acquired at sites other than the training dataset. We calculated the structural similarity index (SSIM) of the PV-corrected maps and intraclass correlation (ICC) of the PV-corrected standardized uptake value between the region-based voxel-wise (RBV) PVC and deepPVC as indicators for validation and testing.

Results

A high SSIM (0.884 ± 0.021) and ICC (0.921 ± 0.042) were observed in the validation and test data (SSIM, 0.876 ± 0.028; ICC, 0.894 ± 0.051). The computation time required to predict a PV-corrected map for a participant (48 s without a graphics processing unit) was much shorter than that for the RBV PVC and MR segmentation processes.

Conclusion

These results suggest that the deepPVC model directly predicts PV-corrected maps from MR and PET images and improves the throughput of MR-PVC by skipping the MR segmentation processes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40658-022-00478-8.

Brain partial volume correction with point spreading function reconstruction in high-resolution digital PET: comparison with an MR-based method in FDG imaging

OBJECTIVE

In quantitative positron emission tomography (PET) of the brain, partial volume effect due mainly to the finite spatial resolution of the PET scanner (> 3 mm full width at half maximum [FWHM]) is a primary source of error in the measurement of tracer uptake, especially in small structures such as the cerebral cortex (typically < 3 mm thickness). The aim of this study was to evaluate the partial volume correction (PVC) performance of point spread function-incorporated reconstruction (PSF reconstruction) in combination with the latest digital PET scanner. This evaluation was performed through direct comparisons with magnetic resonance imaging (MR)-based PVC (used as a reference method) in a human brain study.

METHODS

Ten healthy subjects underwent brain ¹⁸F-FDG PET (30-min acquisition) on a digital PET/CT system (Siemens Biograph Vision, 3.5-mm FWHM scanner resolution at the center of the field of view) and anatomical T1-weighted MR imaging for MR-based PVC. PSF reconstruction was applied with a wide range of iterations (4 to 256; 5 subsets). FDG uptake in the cerebral cortex was evaluated using the standardized uptake value ratio (SUVR) and compared between PSF reconstruction and MR-based PVC.

RESULTS

Cortical structures were visualized by PSF reconstruction with several tens of iterations and were anatomically well matched with the MR-derived cortical segments. Higher numbers of iterations resulted in higher cortical SUVRs, which approached those of MR-based PVC (1.76), although even with the maximum number of iterations they were still smaller by 16% (1.47), corresponding to approximately 1.5-mm FWHM of the effective spatial resolution.

CONCLUSION

With the latest digital PET scanner, PSF reconstruction can be used as a PVC technique in brain PET, albeit with suboptimal resolution recovery. A relative advantage of PSF reconstruction is that it can be applied not only to cerebral cortical regions, but also to various small structures such as small brain nuclei that are hardly visualized on anatomical T1-weighted imaging, and thus hardly recovered by MR-based PVC.

Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application

Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in the United States of America and globally. Carotid arterial plaque, a cause and also a marker of such CVD, can be detected by various non-invasive imaging modalities such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US). Characterization and classification of carotid plaque-type in these imaging modalities, especially into symptomatic and asymptomatic plaque, helps in the planning of carotid endarterectomy or stenting. It can be challenging to characterize plaque components due to (I) partial volume effect in magnetic resonance imaging (MRI) or (II) varying Hausdorff values in plaque regions in CT, and (III) attenuation of echoes reflected by the plaque during US causing acoustic shadowing. Artificial intelligence (AI) methods have become an indispensable part of healthcare and their applications to the non-invasive imaging technologies such as MRI, CT, and the US. In this narrative review, three main types of AI models (machine learning, deep learning, and transfer learning) are analyzed when applied to MRI, CT, and the US. A link between carotid plaque characteristics and the risk of coronary artery disease is presented. With regard to characterization, we review tools and techniques that use AI models to distinguish carotid plaque types based on signal processing and feature strengths. We conclude that AI-based solutions offer an accurate and robust path for tissue characterization and classification for carotid artery plaque imaging in all three imaging modalities. Due to cost, user-friendliness, and clinical effectiveness, AI in the US has dominated the most.