Direct inference of Patlak parametric images in whole-body PET/CT imaging using convolutional neural networks

Total Body PET/CT: A Role in Musculoskeletal Diseases

Recent advancements in PET technology have culminated in the development of total-body PET (TB-PET) systems, which overcome many limitations of traditional scanners. These TB-PET scanners, while still becoming widely available, represent the forefront of clinical imaging across numerous medical institutions worldwide. Early clinical applications have demonstrated their enhanced image quality, precise lesion quantification, and overall superior performance relative to conventional scanners. The capabilities of TB-PET technology, including extended scan range, ultrahigh sensitivity, exceptional temporal resolution, and dynamic imaging, offer significant potential to tackle unresolved clinical challenges in medical imaging. In this discussion, we aim to explore the emerging applications, opportunities, and future perspectives of TB-PET/CT in musculoskeletal disorders (MSDs). Clinical applications for both oncologic and non-oncologic musculoskeletal diseases are discussed, including inflammatory arthritis, infections, osteoarthritis, osteoporosis, and skeletal muscle disorders. From the ability to visualize small musculoskeletal structures and the entire axial and appendicular skeleton, TB-PET shows significant potential in the diagnosis and management of MSD conditions as it becomes more widely available.

The role of dynamic, static, and delayed total-body PET imaging in the detection and differential diagnosis of oncological lesions

OBJECTIVES

Commercialized total-body PET scanners can provide high-quality images due to its ultra-high sensitivity. We compared the dynamic, regular static, and delayed 18F-fluorodeoxyglucose (FDG) scans to detect lesions in oncologic patients on a total-body PET/CT scanner.

MATERIALS & METHODS

In all, 45 patients were scanned continuously for the first 60 min, followed by a delayed acquisition. FDG metabolic rate was calculated from dynamic data using full compartmental modeling, whereas regular static and delayed SUV images were obtained approximately 60- and 145-min post-injection, respectively. The retention index was computed from static and delayed measures for all lesions. Pearson's correlation and Kruskal-Wallis tests were used to compare parameters.

RESULTS

The number of lesions was largely identical between the three protocols, except MRFDG and delayed images on total-body PET only detected 4 and 2 more lesions, respectively (85 total). FDG metabolic rate (MRFDG) image-derived contrast-to-noise ratio and target-to-background ratio were significantly higher than those from static standardized uptake value (SUV) images (P < 0.01), but this is not the case for the delayed images (P > 0.05). Dynamic protocol did not significantly differentiate between benign and malignant lesions just like regular SUV, delayed SUV, and retention index.

CONCLUSION

The potential quantitative advantages of dynamic imaging may not improve lesion detection and differential diagnosis significantly on a total-body PET/CT scanner. The same conclusion applied to delayed imaging. This suggested the added benefits of complex imaging protocols must be weighed against the complex implementation in the future.

CLINICAL RELEVANCE

Total-body PET/CT was known to significantly improve the PET image quality due to its ultra-high sensitivity. However, whether the dynamic and delay imaging on total-body scanner could show additional clinical benefits is largely unknown. Head-to-head comparison between two protocols is relevant to oncological management.

Quantitation of dynamic total-body PET imaging: recent developments and future perspectives

BACKGROUND

Positron emission tomography (PET) scanning is an important diagnostic imaging technique used in disease diagnosis, therapy planning, treatment monitoring, and medical research. The standardized uptake value (SUV) obtained at a single time frame has been widely employed in clinical practice. Well beyond this simple static measure, more detailed metabolic information can be recovered from dynamic PET scans, followed by the recovery of arterial input function and application of appropriate tracer kinetic models. Many efforts have been devoted to the development of quantitative techniques over the last couple of decades.

CHALLENGES

The advent of new-generation total-body PET scanners characterized by ultra-high sensitivity and long axial field of view, i.e., uEXPLORER (United Imaging Healthcare), PennPET Explorer (University of Pennsylvania), and Biograph Vision Quadra (Siemens Healthineers), further stimulates valuable inspiration to derive kinetics for multiple organs simultaneously. But some emerging issues also need to be addressed, e.g., the large-scale data size and organ-specific physiology. The direct implementation of classical methods for total-body PET imaging without proper validation may lead to less accurate results.

CONCLUSIONS

In this contribution, the published dynamic total-body PET datasets are outlined, and several challenges/opportunities for quantitation of such types of studies are presented. An overview of the basic equation, calculation of input function (based on blood sampling, image, population or mathematical model), and kinetic analysis encompassing parametric (compartmental model, graphical plot and spectral analysis) and non-parametric (B-spline and piece-wise basis elements) approaches is provided. The discussion mainly focuses on the feasibilities, recent developments, and future perspectives of these methodologies for a diverse-tissue environment.

Utility of a simplified [18F] sodium fluoride PET imaging method to quantify bone metabolic flux for a wide range of clinical applications

We review the rationale, methodology, and clinical utility of quantitative [18F] sodium fluoride ([18F]NaF) positron emission tomography-computed tomography (PET-CT) imaging to measure bone metabolic flux (Ki, also known as bone plasma clearance), a measurement indicative of the local rate of bone formation at the chosen region of interest. We review the bone remodelling cycle and explain what aspects of bone remodelling are addressed by [18F]NaF PET-CT. We explain how the technique works, what measurements are involved, and what makes [18F]NaF PET-CT a useful tool for the study of bone remodelling. We discuss how these measurements can be simplified without loss of accuracy to make the technique more accessible. Finally, we briefly review some key clinical applications and discuss the potential for future developments. We hope that the simplified method described here will assist in promoting the wider use of the technique.

Prognostic value of whole-body dynamic 18F-FDG PET/CT Patlak in diffuse large B-cell lymphoma

Objective

This study aims to investigate the significance of interim whole-body dynamic 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) Patlak parameters for predicting the prognosis of patients with diffuse large B-cell lymphoma. To estimate the predictive value of the whole-body dynamic 18F-FDG PET/CT Patlak parameter for 2-year progression-free survival (PFS) and 2-year overall survival (OS).

Methods

This study reports the findings of 67 patients with diffuse large B-cell lymphoma (DLBCL). These patients underwent interim whole-body dynamic 18F-FDG PET/CT scans from June 2021 to January 2023 at the Department of Nuclear Medicine, First Affiliated Hospital of Anhui Medical University. The predictive values of maximum standard uptake value (SUVmax), maximum of net glucose uptake rate (Kimax) and the predictive model combining Kimax and interim treatment response on the prognosis of patients was analyzed using receiver operating characteristic (ROC) curves. Kaplan-Meier survival curves and log-rank tests were used for survival analysis. Univariate and multivariate analyses were performed to screen for independent prognostic risk factors.

Results

After a median follow-up of 18 months, 21 patients (31.3%) experienced disease recurrence or death. The cut-off values for the SUVmax and the Kimax were 6.1 and 0.13 μmol min-1·ml-1, respectively. Ann Arbor stage, IPI, SUVmax, Kimax and interim treatment response were associated with PFS and OS in the univariate analysis. However, only Kimax and interim treatment response were independent influences on PFS and OS in multivariate analysis.

Conclusion

Interim whole-body dynamic 18F-FDG PET/CT Patlak imaging has significant prognostic value in patients with DLBCL. Among them, the interim dynamic parameter Kimax showed the best predictive value for prognosis compared with the interim SUVmax and interim treatment response. The predictive model established by Kimax and the interim treatment response allowed for the accurate stratification of the prognostic risk of DLBCL.

An artificial intelligence-driven image quality assessment system for whole-body [18F]FDG PET/CT

PURPOSE

Image quality control is a prerequisite for applying PET/CT. This study aimed to develop an artificial intelligence-driven real-time and accurate whole-body [¹⁸F]FDG PET/CT image quality assessment system.

METHODS

This study included 173 patients (age, 59 ± 12 years; 66.3% males) with whole-body [¹⁸F]FDG PET/CT imaging. Images of ten patients were used as an educational set. Images of the rest 163 patients were reconstructed to 952 images by simulating several scanning times and randomly split into training (60%, 98 patients, 578 images), validation (20%, 33 patients, 192 images), and test (20%, 32 patients,182 images) sets. Two experienced physicians (R1 and R2) independently assessed the image quality of thorax, abdomen, and pelvis region twice (R1a and b; R2a and b), 1 month apart, using a 5-point Likert scale. Objective image quality metrics were extracted from the mediastinal blood pool, three liver levels, and the bilateral gluteus maximus. The developed convolutional neural networks for image quality assessment (IQA-CNNs) generated the subjective quality scores and objective image metrics. The IQA-CNNs and physicians' performances were compared for localization accuracy, score agreement, and process time.

RESULTS

The physicians demonstrated good inter- and intra-rater subjective assessment agreement, with kappa coefficients (R1a vs. R2a, R1a vs. R1b, R2a vs. R2b, and R1a vs. R2b) of 0.78, 0.77, 0.76, and 0.80. The IQA-CNNs and R1 or R2 agreed in the subjective assessments, with kappa coefficients of 0.79 and 0.78. IQA-CNNs and R1 or R2 also agreed in their objective image quality assessment (ICC > 0.60). The IQA-CNNs evaluation speed was 200 times faster than the manual assessment.

CONCLUSION

An automated system for rapid assessment of [¹⁸F]FDG PET/CT image quality was developed, showing comparable performance to senior physicians. The system generates a comprehensive and detailed image quality assessment report, including subjective visual scores and objective image metrics for various anatomical regions.

A deep neural network for parametric image reconstruction on a large axial field-of-view PET

PURPOSE

The PET scanners with long axial field of view (AFOV) having ~ 20 times higher sensitivity than conventional scanners provide new opportunities for enhanced parametric imaging but suffer from the dramatically increased volume and complexity of dynamic data. This study reconstructed a high-quality direct Patlak Ki image from five-frame sinograms without input function by a deep learning framework based on DeepPET to explore the potential of artificial intelligence reducing the acquisition time and the dependence of input function in parametric imaging.

METHODS

This study was implemented on a large AFOV PET/CT scanner (Biograph Vision Quadra) and twenty patients were recruited with ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) dynamic scans. During training and testing of the proposed deep learning framework, the last five-frame (25 min, 40-65 min post-injection) sinograms were set as input and the reconstructed Patlak Ki images by a nested EM algorithm on the vendor were set as ground truth. To evaluate the image quality of predicted Ki images, mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) were calculated. Meanwhile, a linear regression process was applied between predicted and true Ki means on avid malignant lesions and tumor volume of interests (VOIs).

RESULTS

In the testing phase, the proposed method achieved excellent MSE of less than 0.03%, high SSIM, and PSNR of ~ 0.98 and ~ 38 dB, respectively. Moreover, there was a high correlation (DeepPET: [Formula: see text]= 0.73, self-attention DeepPET: [Formula: see text]=0.82) between predicted Ki and traditionally reconstructed Patlak Ki means over eleven lesions.

CONCLUSIONS

The results show that the deep learning-based method produced high-quality parametric images from small frames of projection data without input function. It has much potential to address the dilemma of the long scan time and dependency on input function that still hamper the clinical translation of dynamic PET.