PET Attenuation Correction Research Articles

Evaluation of the prostate cancer and its metastases in the [ 68 Ga]Ga-PSMA PET/CT images: deep learning method vs. conventional PET/CT processing.

This study demonstrates the feasibility and benefits of using a deep learning-based approach for attenuation correction in [ 68 Ga]Ga-PSMA PET scans. A dataset of 700 prostate cancer patients (mean age: 67.6 ± 5.9 years, range: 45-85 years) who underwent [ 68 Ga]Ga-PSMA PET/computed tomography was collected. A deep learning model was trained to perform attenuation correction on these images. Quantitative accuracy was assessed using clinical data from 92 patients, comparing the deep learning-based attenuation correction (DLAC) to computed tomography-based PET attenuation correction (PET-CTAC) using mean error, mean absolute error, and root mean square error based on standard uptake value. Clinical evaluation was conducted by three specialists who performed a blinded assessment of lesion detectability and overall image quality in a subset of 50 subjects, comparing DLAC and PET-CTAC images. The DLAC model yielded mean error, mean absolute error, and root mean square error values of -0.007 ± 0.032, 0.08 ± 0.033, and 0.252 ± 125 standard uptake value, respectively. Regarding lesion detection and image quality, DLAC showed superior performance in 16 of the 50 cases, while in 56% of the cases, the images generated by DLAC and PET-CTAC were found to have closely comparable quality and lesion detectability. This study highlights significant improvements in image quality and lesion detection capabilities through the integration of DLAC in [ 68 Ga]Ga-PSMA PET imaging. This innovative approach not only addresses challenges such as bladder radioactivity but also represents a promising method to minimize patient radiation exposure by integrating low-dose computed tomography and DLAC, ultimately improving diagnostic accuracy and patient outcomes.

Artificial intelligence-based joint attenuation and scatter correction strategies for multi-tracer total-body PET

BackgroundLow-dose ungated CT is commonly used for total-body PET attenuation and scatter correction (ASC). However, CT-based ASC (CT-ASC) is limited by radiation dose risks of CT examinations, propagation of CT-based artifacts and potential mismatches between PET and CT. We demonstrate the feasibility of direct ASC for multi-tracer total-body PET in the image domain.MethodsClinical uEXPLORER total-body PET/CT datasets of [18F]FDG (N = 52), [18F]FAPI (N = 46) and [68Ga]FAPI (N = 60) were retrospectively enrolled in this study. We developed an improved 3D conditional generative adversarial network (cGAN) to directly estimate attenuation and scatter-corrected PET images from non-attenuation and scatter-corrected (NASC) PET images. The feasibility of the proposed 3D cGAN-based ASC was validated using four training strategies: (1) Paired 3D NASC and CT-ASC PET images from three tracers were pooled into one centralized server (CZ-ASC). (2) Paired 3D NASC and CT-ASC PET images from each tracer were individually used (DL-ASC). (3) Paired NASC and CT-ASC PET images from one tracer ([18F]FDG) were used to train the networks, while the other two tracers were used for testing without fine-tuning (NFT-ASC). (4) The pre-trained networks of (3) were fine-tuned with two other tracers individually (FT-ASC). We trained all networks in fivefold cross-validation. The performance of all ASC methods was evaluated by qualitative and quantitative metrics using CT-ASC as the reference.ResultsCZ-ASC, DL-ASC and FT-ASC showed comparable visual quality with CT-ASC for all tracers. CZ-ASC and DL-ASC resulted in a normalized mean absolute error (NMAE) of 8.51 ± 7.32% versus 7.36 ± 6.77% (p < 0.05), outperforming NASC (p < 0.0001) in [18F]FDG dataset. CZ-ASC, FT-ASC and DL-ASC led to NMAE of 6.44 ± 7.02%, 6.55 ± 5.89%, and 7.25 ± 6.33% in [18F]FAPI dataset, and NMAE of 5.53 ± 3.99%, 5.60 ± 4.02%, and 5.68 ± 4.12% in [68Ga]FAPI dataset, respectively. CZ-ASC, FT-ASC and DL-ASC were superior to NASC (p < 0.0001) and NFT-ASC (p < 0.0001) in terms of NMAE results.ConclusionsCZ-ASC, DL-ASC and FT-ASC demonstrated the feasibility of providing accurate and robust ASC for multi-tracer total-body PET, thereby reducing the radiation hazards to patients from redundant CT examinations. CZ-ASC and FT-ASC could outperform DL-ASC for cross-tracer total-body PET AC.

Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.

Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans. A deep learning algorithm based on 2D Pix-2-Pix generative adversarial network (GAN) architecture was developed from paired AC-PET and NAC-PET images. 18F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (n = 183, 60, 59, respectively). Models were trained with two normalization strategies: Standard Uptake Value (SUV)-based and SUV-Nyul-based. Scan-level performance was evaluated by normalized mean square error (NMSE), mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Lesion-level analysis was performed in regions-of-interest prospectively from nuclear medicine physicians. SUV metrics were evaluated using intraclass correlation coefficient (ICC), repeatability coefficient (RC), and linear mixed-effects modeling. Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUVmax and SUVmean were 0.88 and 0.89, which indicated a high correlation between original and AI-generated quantitative imaging markers. Lesion location, density (Hounsfield units), and lesion uptake were all shown to impact relative error in generated SUV metrics (all p < 0.05). The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.

DSG-GAN:A dual-stage-generator-based GAN for cross-modality synthesis from PET to CT

PET/CT devices typically use CT images for PET attenuation correction, leading to additional radiation exposure. Alternatively, in a standalone PET imaging system, attenuation and scatter correction cannot be performed due to the absence of CT images. Therefore, it is necessary to explore methods for generating pseudo-CT images from PET images. However, traditional PET-to-CT synthesis models encounter conflicts in multi-objective optimization, leading to disparities between synthetic and real images in overall structure and texture. To address this issue, we propose a staged image generation model. Firstly, we construct a dual-stage generator, which synthesizes the overall structure and texture details of images by decomposing optimization objectives and employing multiple loss functions constraints. Additionally, in each generator, we employ improved deep perceptual skip connections, which utilize cross-layer information interaction and deep perceptual selection to effectively and selectively leverage multi-level deep information and avoid interference from redundant information. Finally, we construct a context-aware local discriminator, which integrates context information and extracts local features to generate fine local details of images and reasonably maintain the overall coherence of the images. Experimental results demonstrate that our approach outperforms other methods, with SSIM, PSNR, and FID metrics reaching 0.8993, 29.6108, and 29.7489, respectively, achieving the state-of-the-art. Furthermore, we conduct visual experiments on the synthesized pseudo-CT images in terms of image structure and texture. The results indicate that the pseudo-CT images synthesized in this study are more similar to real CT images, providing accurate structure information for clinical disease analysis and lesion localization.

Supplemental Transmission Aided Attenuation Correction for Quantitative Cardiac PET.

Quantitative PET attenuation correction (AC) for cardiac PET/CT and PET/MR is a challenging problem. We propose and evaluate an AC approach that uses coincidences from a relatively weak and physically fixed sparse external source, in combination with that from the patient, to reconstruct μ -maps based on physics principles alone. The low 30 cm3 volume of the source makes it easy to fill and place, and the method does not use prior image data or attenuation map assumptions. Our supplemental transmission aided maximum likelihood reconstruction of attenuation and activity (sTX-MLAA) algorithm contains an attenuation map update that maximizes the likelihood of terms representing coincidences originating from tracer in the patient and a weighted expression of counts segmented from the external source alone. Both external source and patient scatter and randoms are fully corrected. We evaluated performance of sTX-MLAA compared to reference standard CT-based AC with FDG PET/CT phantom studies; including modeling a patient with myocardial inflammation. Through an ROI analysis we measured ≤ 5 % bias in activity concentrations for PET images generated with sTX-MLAA and a TX source strength ≥ 12.7 MBq, relative to CT-AC. PET background variability (from noise and sparse sampling) was substantially reduced with sTX-MLAA compared to using counts segmented from the transmission source alone for AC. Results suggest that sTX-MLAA will enable quantitative PET during cardiac PET/CT and PET/MR of human patients.

Learning CT-free attenuation-corrected total-body PET images through deep learning.

Total-body PET/CT scanners with long axial fields of view have enabled unprecedented image quality and quantitative accuracy. However, the ionizing radiation from CT is a major issue in PET imaging, which is more evident with reduced radiopharmaceutical doses in total-body PET/CT. Therefore, we attempted to generate CT-free attenuation-corrected (CTF-AC) total-body PET images through deep learning. Based on total-body PET data from 122 subjects (29 females and 93 males), a well-established cycle-consistent generative adversarial network (Cycle-GAN) was employed to generate CTF-AC total-body PET images directly while introducing site structures as prior information. Statistical analyses, including Pearson correlation coefficient (PCC) and t-tests, were utilized for the correlation measurements. The generated CTF-AC total-body PET images closely resembled real AC PET images, showing reduced noise and good contrast in different tissue structures. The obtained peak signal-to-noise ratio and structural similarity index measure values were 36.92 ± 5.49 dB (p < 0.01) and 0.980 ± 0.041 (p < 0.01), respectively. Furthermore, the standardized uptake value (SUV) distribution was consistent with that of real AC PET images. Our approach could directly generate CTF-AC total-body PET images, greatly reducing the radiation risk to patients from redundant anatomical examinations. Moreover, the model was validated based on a multidose-level NAC-AC PET dataset, demonstrating the potential of our method for low-dose PET attenuation correction. In future work, we will attempt to validate the proposed method with total-body PET/CT systems in more clinical practices. The ionizing radiation from CT is a major issue in PET imaging, which is more evident with reduced radiopharmaceutical doses in total-body PET/CT. Our CT-free PET attenuation correction method would be beneficial for a wide range of patient populations, especially for pediatric examinations and patients who need multiple scans or who require long-term follow-up. • CT is the main source of radiation in PET/CT imaging, especially for total-body PET/CT devices, and reduced radiopharmaceutical doses make the radiation burden from CT more obvious. • The CT-free PET attenuation correction method would be beneficial for patients who need multiple scans or long-term follow-up by reducing additional radiation from redundant anatomical examinations. • The proposed method could directly generate CT-free attenuation-corrected (CTF-AC) total-body PET images, which is beneficial for PET/MRI or PET-only devices lacking CT image poses.

Attenuation correction and truncation completion for breast PET/MR imaging using deep learning.

Objective. Simultaneous PET/MR scanners combine the high sensitivity of MR imaging with the functional imaging of PET. However, attenuation correction of breast PET/MR imaging is technically challenging. The purpose of this study is to establish a robust attenuation correction algorithm for breast PET/MR images that relies on deep learning (DL) to recreate the missing portions of the patient's anatomy (truncation completion), as well as to provide bone information for attenuation correction from only the PET data.Approach. Data acquired from 23 female subjects with invasive breast cancer scanned with18F-fluorodeoxyglucose PET/CT and PET/MR localized to the breast region were used for this study. Three DL models, U-Net with mean absolute error loss (DLMAE) model, U-Net with mean squared error loss (DLMSE) model, and U-Net with perceptual loss (DLPerceptual) model, were trained to predict synthetic CT images (sCT) for PET attenuation correction (AC) given non-attenuation corrected (NAC) PETPET/MRimages as inputs. The DL and Dixon-based sCT reconstructed PET images were compared against those reconstructed from CT images by calculating the percent error of the standardized uptake value (SUV) and conducting Wilcoxon signed rank statistical tests.Main results. sCT images from the DLMAEmodel, the DLMSEmodel, and the DLPerceptualmodel were similar in mean absolute error (MAE), peak-signal-to-noise ratio, and normalized cross-correlation. No significant difference in SUV was found between the PET images reconstructed using the DLMSEand DLPerceptualsCTs compared to the reference CT for AC in all tissue regions. All DL methods performed better than the Dixon-based method according to SUV analysis.Significance. A 3D U-Net with MSE or perceptual loss model can be implemented into a reconstruction workflow, and the derived sCT images allow successful truncation completion and attenuation correction for breast PET/MR images.

Attenuation Correction of Long Axial Field-of-View Positron Emission Tomography Using Synthetic Computed Tomography Derived from the Emission Data: Application to Low-Count Studies and Multiple Tracers.

Recent advancements in PET/CT, including the emergence of long axial field-of-view (LAFOV) PET/CT scanners, have increased PET sensitivity substantially. Consequently, there has been a significant reduction in the required tracer activity, shifting the primary source of patient radiation dose exposure to the attenuation correction (AC) CT scan during PET imaging. This study proposes a parameter-transferred conditional generative adversarial network (PT-cGAN) architecture to generate synthetic CT (sCT) images from non-attenuation corrected (NAC) PET images, with separate networks for [18F]FDG and [15O]H2O tracers. The study includes a total of 1018 subjects (n = 972 [18F]FDG, n = 46 [15O]H2O). Testing was performed on the LAFOV scanner for both datasets. Qualitative analysis found no differences in image quality in 30 out of 36 cases in FDG patients, with minor insignificant differences in the remaining 6 cases. Reduced artifacts due to motion between NAC PET and CT were found. For the selected organs, a mean average error of 0.45% was found for the FDG cohort, and that of 3.12% was found for the H2O cohort. Simulated low-count images were included in testing, which demonstrated good performance down to 45 s scans. These findings show that the AC of total-body PET is feasible across tracers and in low-count studies and might reduce the artifacts due to motion and metal implants.

An automatic pipeline for PET/MRI attenuation correction validation in the brain

PurposeChallenges in PET/MRI quantitative accuracy for neurological uses arise from PET attenuation correction accuracy. We proposed and evaluated an automatic pipeline to assess the quantitative accuracy of four MRI-derived PET AC methods using analytically simulated PET brain lesions and ROIs as ground truth for PET activity.MethodsOur proposed pipeline, integrating a synthetic lesion insertion tool and the FreeSurfer neuroimaging framework, inserts simulated spherical and brain ROIs into PET projection space, reconstructing them via four PET MRAC techniques. Utilizing an 11-patient brain PET dataset, we compared the quantitative accuracy of four MRACs (DIXON, DIXONbone, UTE AC, and DL-DIXON) against the gold standard PET CTAC, evaluating MRAC to CTAC activity bias in spherical lesions and brain ROIs with and without background activity against original (lesion free) PET reconstructed images.ResultsThe proposed pipeline yielded accurate results for spherical lesions and brain ROIs, adhering to the MRAC to CTAC pattern of original brain PET images. Among the MRAC methods, DIXON AC exhibited the highest bias, followed by UTE, DIXONBone, and DL-DIXON showing the least. DIXON, DIXONbone, UTE, and DL-DIXON showed MRAC to CTAC biases of − 5.41%, − 1.85%, − 2.74%, and 0.08% respectively for ROIs inserted in background activity; − 7.02%, − 2.46%, − 3.56%, and − 0.05% for lesion ROIs without background; and − 6.82%, − 2.08%, − 2.29%, and 0.22% for the original brain PET images’ 16 FreeSurfer brain ROIs.ConclusionThe proposed pipeline delivers accurate results for synthetic spherical lesions and brain ROIs, with and without background activity consideration, enabling the evaluation of new attenuation correction approaches without utilizing measured PET emission data. Additionally, it offers a consistent method to generate realistic lesion ROIs, potentially applicable in assessing further PET correction techniques.

New Data-Driven Gated (DDG) PET/CT for Radiation Treatment Planning of NSCLC

PET/CT for RT simulation of NSCLC is typically conducted in two separate imaging sessions of gated 4D-CT in radiation oncology and fusion with non-gated PET/CT in diagnostic imaging, making treatment response assessment (TRA) with PET/CT and radiation treatment planning (RTP) challenging. To remedy this short-coming, we designed a new data-driven gated (DDG) PET/CT, based on the self-gated PET and self-gated CT data to derive the gated PET/CT data free of tumor blurring and misregistration artifacts without any respiratory monitoring device (ease of use and cost reduction). The new DDG PET/CT also provides the important 4D-CT information of end-inspiratory (EI), end-expiratory (EE), maximum-intensity-projection (MIP) and average-intensity-projection (AIP) CT's. The total imaging time is < 15 min, which makes DDG PET/CT simulation in a single session without any respiratory monitoring device possible. Acquisition is standard PET/CT imaging protocol followed by a cine CT imaging of the tumor area. We utilized the commercial DDG PET from GE Discovery PET/CT and designed a new DDG CT for attenuation correction of the DDG PET for reduction of tumor motion and mis-registration. The AIP and MIP images were from the average and maximum pixel values of the cine CT images, respectively. The cine CT images with the largest and smallest average CT number in the lung region were identified as the EE and EI CT images, respectively. For the image slices without any lung region present, the largest and smallest expansions of the body outline contour were selected to be the EE and EI CT phases, respectively. The AIP and EE CT images were used for attenuation correction of the PET and DDG PET data, respectively. Both DDG PET/CT and 4D-CT of (EI, EE, AIP and MIP) are for RT simulation of NSCLC. 38 4D-CT patient data sets were compared at the EE and EI phases between our DDG CT and 4D-CT to demonstrate the applicability of the newly designed DDG CT. A prototype software on a Dell PC of i5-6500 CPU has been successfully developed to enable DDG PET/CT and 4D-CT on seven GE Discovery PET/CT scanners. The operating system was Ubuntu and the computer language was Python. In the EE phase, the images selected by DDG CT and 4D CT were identical 62.5±21.6% of the time. In the EI phase, the images selected by DDG CT and 4D CT were identical 68.2±18.9% of the time. Inspection of the EE and EI phases of DDG CT and 50% and 0% of 4D-CT demonstrated both data sets of DDG CT and 4D CT were almost identical. A new DDG PET/CT and 4D-CT in a single imaging session without any hardware gating has been developed for TRA and RTP of NSCLC. The utility is available on the network and it enables all PET/CT scanners on the network for TRA and RTP. The new DDG CT provides the benefits of 4D-CT without any requirement of external hardware gating and make possible DDG PET/CT free of tumor motion and misregistration artifacts.

Transfer learning-based attenuation correction for static and dynamic cardiac PET using a generative adversarial network.

The goal of this work is to demonstrate the feasibility of directly generating attenuation-corrected PET images from non-attenuation-corrected (NAC) PET images for both rest and stress-state static or dynamic [13N]ammonia MP PET based on a generative adversarial network. We recruited 60 subjects for rest-only scans and 14 subjects for rest-stress scans, all of whom underwent [13N]ammonia cardiac PET/CT examinations to acquire static and dynamic frames with both 3D NAC and CT-based AC (CTAC) PET images. We developed a 3D pix2pix deep learning AC (DLAC) framework via a U-net + ResNet-based generator and a convolutional neural network-based discriminator. Paired static or dynamic NAC and CTAC PET images from 60 rest-only subjects were used as network inputs and labels for static (S-DLAC) and dynamic (D-DLAC) training, respectively. The pre-trained S-DLAC network was then fine-tuned by paired dynamic NAC and CTAC PET frames of 60 rest-only subjects to derive an improved D-DLAC-FT for dynamic PET images. The 14 rest-stress subjects were used as an internal testing dataset and separately tested on different network models without training. The proposed methods were evaluated using visual quality and quantitative metrics. The proposed S-DLAC, D-DLAC, and D-DLAC-FT methods were consistent with clinical CTAC in terms of various images and quantitative metrics. The S-DLAC (slope = 0.9423, R2 = 0.947) showed a higher correlation with the reference static CTAC as compared to static NAC (slope = 0.0992, R2 = 0.654). D-DLAC-FT yielded lower myocardial blood flow (MBF) errors in the whole left ventricular myocardium than D-DLAC, but with no significant difference, both for the 60 rest-state subjects (6.63 ± 5.05% vs. 7.00 ± 6.84%, p = 0.7593) and the 14 stress-state subjects (1.97 ± 2.28% vs. 3.21 ± 3.89%, p = 0.8595). The proposed S-DLAC, D-DLAC, and D-DLAC-FT methods achieve comparable performance with clinical CTAC. Transfer learning shows promising potential for dynamic MP PET.

Deep learning for improving PET/CT attenuation correction by elastic registration of anatomical data.

For PET/CT, the CT transmission data are used to correct the PET emission data for attenuation. However, subject motion between the consecutive scans can cause problems for the PET reconstruction. A method to match the CT to the PET would reduce resulting artifacts in the reconstructed images. This work presents a deep learning technique for inter-modality, elastic registration of PET/CT images for improving PET attenuation correction (AC). The feasibility of the technique is demonstrated for two applications: general whole-body (WB) imaging and cardiac myocardial perfusion imaging (MPI), with a specific focus on respiratory and gross voluntary motion. A convolutional neural network (CNN) was developed and trained for the registration task, comprising two distinct modules: a feature extractor and a displacement vector field (DVF) regressor. It took as input a non-attenuation-corrected PET/CT image pair and returned the relative DVF between them-it was trained in a supervised fashion using simulated inter-image motion. The 3D motion fields produced by the network were used to resample the CT image volumes, elastically warping them to spatially match the corresponding PET distributions. Performance of the algorithm was evaluated in different independent sets of WB clinical subject data: for recovering deliberate misregistrations imposed in motion-free PET/CT pairs and for improving reconstruction artifacts in cases with actual subject motion. The efficacy of this technique is also demonstrated for improving PET AC in cardiac MPI applications. A single registration network was found to be capable of handling a variety of PET tracers. It demonstrated state-of-the-art performance in the PET/CT registration task and was able to significantly reduce the effects of simulated motion imposed in motion-free, clinical data. Registering the CT to the PET distribution was also found to reduce various types of AC artifacts in the reconstructed PET images of subjects with actual motion. In particular, liver uniformity was improved in the subjects with significant observable respiratory motion. For MPI, the proposed approach yielded advantages for correcting artifacts in myocardial activity quantification and potentially for reducing the rate of the associated diagnostic errors. This study demonstrated the feasibility of using deep learning for registering the anatomical image to improve AC in clinical PET/CT reconstruction. Most notably, this improved common respiratory artifacts occurring near the lung/liver border, misalignment artifacts due to gross voluntary motion, and quantification errors in cardiac PET imaging.

Ultra-low-dose CT reconstructed with the artificial intelligence iterative reconstruction algorithm (AIIR) in 18F-FDG total-body PET/CT examination: a preliminary study

PurposeTo investigate the feasibility of ultra-low-dose CT (ULDCT) reconstructed with the artificial intelligence iterative reconstruction (AIIR) algorithm in total-body PET/CT imaging.MethodsThe study included both the phantom and clinical parts. An anthropomorphic phantom underwent CT imaging with ULDCT (10mAs) and standard-dose CT (SDCT) (120mAs), respectively. ULDCT was reconstructed with AIIR and hybrid iterative reconstruction (HIR) (expressed as ULDCT-AIIRphantom and ULDCT-HIRphantom), respectively, and SDCT was reconstructed with HIR (SDCT-HIRphantom) as control. In the clinical part, 52 patients with malignant tumors underwent the total-body PET/CT scan. ULDCT with AIIR (ULDCT-AIIR) and HIR (ULDCT-HIR), respectively, was reconstructed for PET attenuation correction, followed by the SDCT reconstructed with HIR (SDCT-HIR) for anatomical location. PET/CT images’ quality was qualitatively assessed by two readers. The CTmean, as well as the CT standard deviation (CTsd), SUVmax, SUVmean, and the SUV standard deviation (SUVsd), was recorded. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated and compared.ResultsThe image quality of ULDCT-HIRphantom was inferior to the SDCT-HIRphantom, but no significant difference was found between the ULDCT-AIIRphantom and SDCT-HIRphantom. The subjective score of ULDCT-AIIR in the neck, chest and lower limb was equivalent to that of SDCT-HIR. Besides the brain and lower limb, the change rates of CTmean in thyroid, neck muscle, lung, mediastinum, back muscle, liver, lumbar muscle, first lumbar spine and sigmoid colon were −2.15, −1.52, 0.66, 2.97, 0.23, 8.91, 0.06, −4.29 and 8.78%, respectively, while all CTsd of ULDCT-AIIR was lower than that of SDCT-HIR. Except for the brain, the CNR of ULDCT-AIIR was the same as the SDCT-HIR, but the SNR was higher. The change rates of SUVmax, SUVmean and SUVsd were within pm 3% in all ROIs. For the lesions, the SUVmax, SUVsd and TBR showed no significant difference between PET-AIIR and PET-HIR.ConclusionThe SDCT-HIR could not be replaced by the ULDCT-AIIR at date, but the AIIR algorithm decreased the image noise and increased the SNR, which can be implemented under special circumstances in PET/CT examination.

EFOMP’s protocol quality controls in PET/CT and PET/MR

This article presents the protocol on Quality Controls in PET/CT and PET/MRI published online in May 2022 by the European Federation of Organisations for Medical Physics (EFOMP), which was developed by the Working group for PET/CT and PET/MRI Quality Control (QC) protocol.The main objective of this protocol was to comprehensively provide simple and practical procedures that may be integrated into clinical practice to identify changes in the PET/CT/MRI system's performance and avoid short- and long-term quality deterioration.The protocol describes the quality control procedures on radionuclide calibrators, weighing scales, PET, CT and MRI systems using selected and measurable parameters that are directly linked to clinical images quality. It helps to detect problems before they can impact clinical studies in terms of safety, image quality, quantification accuracy and patient radiation dose.CT and MRI QCs are described only in the context of their use for PET (attenuation correction and anatomical localization) imaging.Detailed step-by-step instructions have been provided, limiting any misinterpretations or interpersonal variations as much as possible.This paper presents the main characteristics of the protocol illustrated together with a brief summary of the content of each chapter.A regular QC based on the proposed protocol would guarantee that PET/CT and PET/MRI systems operate under optimal conditions, resulting in the best performance for routine clinical tasks.

Left Ventricular Strain from Myocardial Perfusion PET Imaging: Method Development and Comparison to 2-Dimensional Echocardiography.

This study aimed to develop a measure of longitudinal, radial, and circumferential myocardial strain at rest and regadenoson during pharmacologic stress using 82Rb PET electrocardiography-gated myocardial perfusion imaging (MPI). Methods: We retrospectively identified 80 patients who underwent rest and regadenoson-stress CT attenuation-corrected 82Rb PET and had a standard resting transthoracic echocardiogram (TTE) with global longitudinal strain (GLS) analysis within 3 mo. A method was developed to compute longitudinal, radial, and circumferential strain from PET MPI at stress and rest. PET MPI-derived strain and left ventricular function were compared with resting TTE measures as the clinical reference standard. Interobserver agreement of PET MPI strain and left ventricular ejection fraction processing was reported. Results: Longitudinal strain assessed with resting TTE GLS showed good correlation with PET MPI at stress (r = 0.68, P < 0.001) and rest (r = 0.58, P < 0.001). Resting TTE GLS also correlated with PET MPI radial strain at stress (r = -0.70, P < 0.001) and rest (r = -0.59, P < 0.001) and circumferential strain at stress (r = 0.67, P < 0.001) and rest (r = 0.69, P < 0.001). The left ventricular ejection fraction showed good correlation between resting TTE and PET MPI at stress (r = 0.83, P < 0.001) and rest (r = 0.80, P < 0.001). Bland-Altman analysis indicated positive bias of TTE GLS compared with PET MPI longitudinal strain at stress (mean difference = 5.1%, 95% CI = [-2.5, 12.7]) and rest (mean difference = 4.2%, 95% CI = [-4.3, 12.8]). Reproducibility of PET MPI longitudinal strain showed good agreement at stress (concordance correlation coefficient = 0.73, P < 0.001) and rest (concordance correlation coefficient = 0.74, P < 0.001), with Bland-Altman analysis showing a small bias in the longitudinal direction at stress (mean difference = -0.2%) and rest (mean difference = -1.0%). Conclusion: Strain measured with PET MPI using an automated technique correlated well with resting GLS strain obtained by TTE, and the measure is reproducible. Strain from PET MPI should be investigated further to establish reference ranges and assess its value in routine clinical practice.

Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning

PurposeAttenuation correction and scatter compensation (AC/SC) are two main steps toward quantitative PET imaging, which remain challenging in PET-only and PET/MRI systems. These can be effectively tackled via deep learning (DL) methods. However, trustworthy, and generalizable DL models commonly require well-curated, heterogeneous, and large datasets from multiple clinical centers. At the same time, owing to legal/ethical issues and privacy concerns, forming a large collective, centralized dataset poses significant challenges. In this work, we aimed to develop a DL-based model in a multicenter setting without direct sharing of data using federated learning (FL) for AC/SC of PET images.MethodsNon-attenuation/scatter corrected and CT-based attenuation/scatter corrected (CT-ASC) 18F-FDG PET images of 300 patients were enrolled in this study. The dataset consisted of 6 different centers, each with 50 patients, with scanner, image acquisition, and reconstruction protocols varying across the centers. CT-based ASC PET images served as the standard reference. All images were reviewed to include high-quality and artifact-free PET images. Both corrected and uncorrected PET images were converted to standardized uptake values (SUVs). We used a modified nested U-Net utilizing residual U-block in a U-shape architecture. We evaluated two FL models, namely sequential (FL-SQ) and parallel (FL-PL) and compared their performance with the baseline centralized (CZ) learning model wherein the data were pooled to one server, as well as center-based (CB) models where for each center the model was built and evaluated separately. Data from each center were divided to contribute to training (30 patients), validation (10 patients), and test sets (10 patients). Final evaluations and reports were performed on 60 patients (10 patients from each center).ResultsIn terms of percent SUV absolute relative error (ARE%), both FL-SQ (CI:12.21–14.81%) and FL-PL (CI:11.82–13.84%) models demonstrated excellent agreement with the centralized framework (CI:10.32–12.00%), while FL-based algorithms improved model performance by over 11% compared to CB training strategy (CI: 22.34–26.10%). Furthermore, the Mann–Whitney test between different strategies revealed no significant differences between CZ and FL-based algorithms (p-value > 0.05) in center-categorized mode. At the same time, a significant difference was observed between the different training approaches on the overall dataset (p-value < 0.05). In addition, voxel-wise comparison, with respect to reference CT-ASC, exhibited similar performance for images predicted by CZ (R2 = 0.94), FL-SQ (R2 = 0.93), and FL-PL (R2 = 0.92), while CB model achieved a far lower coefficient of determination (R2 = 0.74). Despite the strong correlations between CZ and FL-based methods compared to reference CT-ASC, a slight underestimation of predicted voxel values was observed.ConclusionDeep learning-based models provide promising results toward quantitative PET image reconstruction. Specifically, we developed two FL models and compared their performance with center-based and centralized models. The proposed FL-based models achieved higher performance compared to center-based models, comparable with centralized models. Our work provided strong empirical evidence that the FL framework can fully benefit from the generalizability and robustness of DL models used for AC/SC in PET, while obviating the need for the direct sharing of datasets between clinical imaging centers.

Using domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction

Despite the potential of deep learning (DL)-based methods in substituting CT-based PET attenuation and scatter correction for CT-free PET imaging, a critical bottleneck is their limited capability in handling large heterogeneity of tracers and scanners of PET imaging. This study employs a simple way to integrate domain knowledge in DL for CT-free PET imaging. In contrast to conventional direct DL methods, we simplify the complex problem by a domain decomposition so that the learning of anatomy-dependent attenuation correction can be achieved robustly in a low-frequency domain while the original anatomy-independent high-frequency texture can be preserved during the processing. Even with the training from one tracer on one scanner, the effectiveness and robustness of our proposed approach are confirmed in tests of various external imaging tracers on different scanners. The robust, generalizable, and transparent DL development may enhance the potential of clinical translation.

A deep learning-based whole-body solution for PET/MRI attenuation correction

BackgroundDeep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems. However, its whole-body implementation is still challenging due to anatomical variations and the limited MRI field of view. The aim of this study is to investigate a deep learning (DL) method to generate voxel-based synthetic CT (sCT) from Dixon MRI and use it as a whole-body solution for PET AC in a PET/MRI system.Materials and methodsFifteen patients underwent PET/CT followed by PET/MRI with whole-body coverage from skull to feet. We performed MRI truncation correction and employed co-registered MRI and CT images for training and leave-one-out cross-validation. The network was pretrained with region-specific images. The accuracy of the AC maps and reconstructed PET images were assessed by performing a voxel-wise analysis and calculating the quantification error in SUV obtained using DL-based sCT (PETsCT) and a vendor-provided atlas-based method (PETAtlas), with the CT-based reconstruction (PETCT) serving as the reference. In addition, region-specific analysis was performed to compare the performances of the methods in brain, lung, liver, spine, pelvic bone, and aorta.ResultsOur DL-based method resulted in better estimates of AC maps with a mean absolute error of 62 HU, compared to 109 HU for the atlas-based method. We found an excellent voxel-by-voxel correlation between PETCT and PETsCT (R2 = 0.98). The absolute percentage difference in PET quantification for the entire image was 6.1% for PETsCT and 11.2% for PETAtlas. The regional analysis showed that the average errors and the variability for PETsCT were lower than PETAtlas in all regions. The largest errors were observed in the lung, while the smallest biases were observed in the brain and liver.ConclusionsExperimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. Further evaluation using a larger training cohort is required for more accurate and robust performance.

Grad-CAM Guided U-Net for MRI-based Pseudo-CT Synthesis.

In this paper, we address the task of image-to-image translation from MRI to CT domain. We propose a 2D U-Net-based deep learning approach for pseudo-CT synthesis that incorporates an additional Grad-CAM guided attention mechanism for superior image translation of bone regions. The suggested architecture consists of image-to-image translation and image classification modules. We first train our classifier to distinguish between MR and CT images. After that, we utilize it in combination with the Grad-CAM technique to provide additional guidance to our image-to-image translation network. We generate CT-class-specific localization maps for both CT and pseudo-CT images and then compare them. Thus, we force the image-to-image translation network to focus on relevant attributes of the CT class, such as bone structures, while learning to synthesize pseudo-CTs. The performance of the proposed approach is evaluated on the publicly available RIRE data set. Since MR and CT images in this data set are not correctly aligned with each other, we also briefly describe the applied image registration procedure. The experimental results are compared to the baseline U-Net model and demonstrate both qualitative and quantitative improvements, whereas significant performance gain is achieved for bone regions. Clinical Relevance- MRI-based pseudo-CT synthesis is essential for attenuation correction of PET in combined PET/MRI systems and plays a vital role in MRI-only radiotherapy planning. Accurate pseudo-CTs can prevent patients from harmful and unnecessary radiation exposure.

Eliminating CT radiation for clinical PET examination using deep learning

Clinical PET/CT examinations rely on CT modality for anatomical localization and attenuation correction of the PET data. However, the use of CT significantly increases the risk of ionizing radiation exposure for patients. We propose a deep learning framework to learn the relationship mapping between attenuation corrected (AC) PET and non-attenuation corrected (NAC) PET images to estimate PET attenuation maps and generate pseudo-CT images for medical observation. In this study, 5760, 1608 and 1351 pairs of transverse PET-CT slices were used as the training, validation, and testing sets, respectively, to implement the proposed framework. A pix2pix model was adopted to predict AC PET images from NAC PET images, which allowed the calculation of PET attenuation maps (µ-maps). The same model was then applied to generate realistic CT images from the calculated µ-maps. The quality of predicted AC PET and CT was assessed using normalized root mean square error (NRMSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and Pearson correlation coefficient (PCC). Relative to true AC PET, the synthetic AC PET achieved superior quantitative performances with 2.20 ± 1.17% NRMSE, 34.03 ± 4.73 dB PSNR, 97.90 ± 1.22% SSIM and 98.45 ± 1.31% PCC. The synthetic CT and synthetic AC PET images were deemed acceptable by radiologists who rated the images, as they provided sufficient anatomical and functional information, respectively. This work demonstrates that the proposed deep learning framework is a promising method in clinical applications, such as radiotherapy and low-dose imaging.