CT-based Attenuation Correction Research Articles

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.

Effect of kilovoltage and quality reference mAs on CT-based attenuation correction in 177Lu SPECT/CT imaging: a phantom study

IntroductionCT-based attenuation correction (CT-AC) plays a major role in accurate activity quantification by SPECT/CT imaging. However, the effect of kilovoltage peak (kVp) and quality-reference mAs (QRM) on the attenuation coefficient image (μ-map) and volume CT dose index (CTDIvol) have not yet been systematically evaluated. Therefore, the aim of this study was to fill this gap and investigate the influence of kVp and QRM on CT-AC in 177Lu SPECT/CT imaging.MethodsSeventy low-dose CT acquisitions of an Electron Density Phantom (seventeen inserts of nine tissue-equivalent materials) were acquired using various kVp and QRM combinations on a Siemens Symbia Intevo Bold SPECT/CT system. Using manufacturer reconstruction software, 177Lu μ-maps were generated for each CT image, and three low-dose CT related aspects were examined. First, the μ-map-based attenuation values (μmeasured) were compared with theoretical values (μtheoretical). Second, changes in 177Lu activity expected due to changes in the μ-map were calculated using a modified Chang method. Third, the noise in the μ-map was assessed by measuring the coefficient of variation in a volume of interest in the homogeneous section of the Electron Density Phantom. Lastly, two phantoms were designed to simulate attenuation in four tissue-equivalent materials for two different source geometries (1-mL and 10-mL syringes). 177Lu SPECT/CT imaging was performed using three different reconstruction algorithms (xSPECT Quant, Flash3D, STIR), and the SPECT-based activities were compared against the nominal activities in the sources.ResultsThe largest relative errors between μmeasured and μtheoretical were observed in the lung inhale insert (range: 18%-36%), while it remained below 6% for all other inserts. The resulting changes in 177Lu activity quantification were -3.5% in the lung inhale insert and less than -2.3% in all other inserts. Coefficient of variation and CTDIvol ranged from 0.3% and 3.6 mGy (130 kVp, 35 mAs) to 0.4% and 0.9 mGy (80 kVp, 20 mAs), respectively. The SPECT-based activity quantification using xSPECT Quant reconstructions outperformed all other reconstruction algorithms.ConclusionThis study shows that kVp and QRM values in low-dose CT imaging have a minimum effect on quantitative 177Lu SPECT/CT imaging, while the selection of low values of kVp and QRM reduce the CTDIvol.

Clinical Feasibility of Deep Learning-Based Attenuation Correction Models for Tl-201 Myocardial Perfusion SPECT.

We aimed to develop deep learning (DL)-based attenuation correction models for Tl-201 myocardial perfusion SPECT (MPS) images and evaluate their clinical feasibility. We conducted a retrospective study of patients with suspected or known coronary artery disease. We proposed a DL-based image-to-image translation technique to transform non-attenuation-corrected images into CT-based attenuation-corrected (CT AC ) images. The model was trained using a modified U-Net with structural similarity index (SSIM) loss and mean squared error (MSE) loss and compared with other models. Segment-wise analysis using a polar map and visual assessment for the generated attenuation-corrected (GEN AC ) images were also performed to evaluate clinical feasibility. This study comprised 657 men and 328 women (age, 65 ± 11 years). Among the various models, the modified U-Net achieved the highest performance with an average mean absolute error of 0.003, an SSIM of 0.990, and a peak signal-to-noise ratio of 33.658. The performance of the model was not different between the stress and rest datasets. In the segment-wise analysis, the myocardial perfusion of the inferior wall was significantly higher in GEN AC images than in the non-attenuation-corrected images in both the rest and stress test sets ( P < 0.05). In the visual assessment of patients with diaphragmatic attenuation, scores of 4 (similar to CT AC images) or 5 (indistinguishable from CT AC images) were assigned to most GEN AC images (65/68). Our clinically feasible DL-based attenuation correction models can replace the CT-based method in Tl-201 MPS, and it would be useful in case SPECT/CT is unavailable for MPS.

The determination of the optimal threshold on measurement of thyroid volume using quantitative SPECT/CT for Graves' hyperthyroidism

PurposeTo investigate the optimal threshold for measuring thyroid volume in patients with Grave's hyperthyroidism (GH) by SPECT/CT.Materials and methodsA 53 mL butterfly-shaped hollow container made of two 45-degree transparent elbows was put into a NEMA IEC phantom tank. The butterfly-shaped container and the tank were then filled with Na99mTcO4 of different radioactive concentrations, respectively, which could simulate thyroid gland with GH by different target-to-background ratios (T/B) (200:1, 600:1, 1000:1). The different T/B of planar imaging and SPECT/CT were acquired by a Discovery NM/CT 670 Pro SPECT/CT. With Thyroid software (Version 4.0) of GE-Xeleris workstation, the region of the thyroid gland in planar imaging was delineated. The thyroid area and average long diameter of both lobes were substituted into the Allen formula to calculate the thyroid volume. The calculation error was compared with the actual volume. Q-Metrix software was used to perform CT-based attenuation correction, scatter correction, resolution recovery. Ordered-subsets expectation maximization was used to reconstruct SPECT data. 20%, 25%, 30%, 40%, 50%, 60% thresholds were selected to automatically delineate the volume of interest and compared with the real volume, which determinated the optimal threshold. We measured the thyroid volume of 40 GH patients using the threshold and compared the volumes obtained by planar imaging and ultrasound three-dimensional. The differences of the volumes with different T/B and thresholds were compared by the ANOVA and least significant difference t test. The volumes delineated by SPECT/CT were evaluated using ANOVA, least significant difference t test, correlation analysis and, linear regression and Bland–Altman concordance test plot. The differences and consistency of thyroid volume were compared among the above three methods.ResultsThere was no significant difference in the results between different T/B models (P > 0.05). The thyroid volume calculated by the planar imaging formula method was higher than the real volume, with an average overestimation of 22.81%. The volumes delineated by SPECT/CT threshold automatically decreased while the threshold increased. There were significant differences between groups with different thresholds (P < 0.001). With an average error of 3.73%, the thyroid volume analyzed by the threshold of 25% was close to the results of ultrasound measurement (P > 0.05). Thyroid volume measured by planar imaging method was significantly higher than ultrasound and SPECT/CT threshold automatic delineation method (P < 0.05). The agreement between the SPECT/CT 25% threshold and ultrasound (r = 0.956, b = 0.961) was better than that between the planar imaging and ultrasound (r = 0.590, b = 0.574). The Bland–Altman plot also showed that the thyroid volume measured by the 25% threshold automatic delineation method was in good agreement with the ultrasound measurement.ConclusionsThe T/B has no effect on the measurement of thyroid volume in GH patients; planar imaging method can significantly overestimate thyroid volume in GH patients, and 25% threshold automatic delineation method can obtain more accurate thyroid volume in GH patients.

Time-of-flight PET/CT suppresses CT based attenuation correction and scatter coincidence correction errors due to misalignment of the gastrointestinal tract.

This study aimed to examine the influence of changes in CT values on PET images, specifically focusing on errors in CT-based attenuation correction and scatter coincidence correction (CTAC/SC) caused by gastrointestinal gas. Furthermore, it aimed to demonstrate the effectiveness of time-of-flight (TOF) PET in reducing CTAC/SC errors. PET images were reconstructed using multiple CT images with varying CT values. The study then compared the fluctuations in pixel values of the PET images corresponding to the different CT values utilized for CTAC/SC between non-TOF and TOF acquisitions. PET pixel values fluctuated with changes in CT values. In the phantom study, TOF showed a significantly smaller change in PET pixel value of 1.00±0.27 kBq/mL compared to 3.72±1.33 kBq/mL in the non-TOF at sites with a CT change of +1000 HU. In the patient study, a linear regression analysis was performed to determine the effect of changes in CT values due to gastrointestinal gas migration on standard uptake value (SUV).The results showed that the TOF group had a lower ratio of change in SUV to change in CT values compared to the non-TOF group. These findings revealed that PET pixel values exhibited fluctuations in response to changes in CT values, and TOF-PET effectively mitigated CTAC/SC errors arising from gastrointestinal gas. TOF-PET has the potential to reduce the occurrence of suspicious accumulation.

Feasibility of direct brain 18F-fluorodeoxyglucose-positron emission tomography attenuation and high-resolution correction methods using deep learning.

To develop the following three attenuation correction (AC) methods for brain 18F-fluorodeoxyglucose-positron emission tomography (PET), using deep learning, and to ascertain their precision levels: (i) indirect method; (ii) direct method; and (iii) direct and high-resolution correction (direct+HRC) method. We included 53 patients who underwent cranial magnetic resonance imaging (MRI) and computed tomography (CT) and 27 patients who underwent cranial MRI, CT, and PET. After fusion of the magnetic resonance, CT, and PET images, resampling was performed to standardize the field of view and matrix size and prepare the data set. In the indirect method, synthetic CT (SCT) images were generated, whereas in the direct and direct+HRC methods, a U-net structure was used to generate AC images. In the indirect method, attenuation correction was performed using SCT images generated from MRI findings using U-net instead of CT images. In the direct and direct+HRC methods, AC images were generated directly from non-AC images using U-net, followed by image evaluation. The precision levels of AC images generated using the indirect and direct methods were compared based on the normalized mean squared error (NMSE) and structural similarity (SSIM). Visual inspection revealed no difference between the AC images prepared using CT-based attenuation correction and those prepared using the three methods. The NMSE increased in the order indirect, direct, and direct+HRC methods, with values of 0.281×10-3, 4.62×10-3, and 12.7×10-3, respectively. Moreover, the SSIM of the direct+HRC method was 0.975. The direct+HRC method enables accurate attenuation without CT exposure and high-resolution correction without dedicated correction programs.

Impact of Attenuation Correction, Collimator, and Iterative Reconstruction Protocols on 67Ga SPECT/CT Quantification

Purpose: The main goal of this study was to determine the optimal collimator in the absence of medium energy collimators along with the impact of Attenuation Correction (AC) and different iterative reconstruction protocols on the quantitative evaluation of Gallium-67 (67Ga) SPECT/CT imaging.&#x0D; Materials and Methods: A GE Discovery 670 dual-head SPECT/CT scanner and a NEMA phantom filled with 67Ga solution were used to scan the patients. The projections were acquired with both Low Energy High Resolution (LEHR) and High Energy General Purpose (HEGP) collimators, and CT images were acquired to evaluate the effect of attenuation correction. SPECT data were reconstructed using the ordered subset expectation maximization (OSEM) method with various combinations of iterations and subsets. The performance was quantified, and a clinical study validated the phantom study.&#x0D; Results: Acquired images by the HEGP collimator yielded higher Contrast Recovery (CR) and Contrast to Noise Ratio (CNR) in images with AC than those without non-AC (41.6% and 74.2%, respectively). The CNR in all spheres after AC was increased by 80.4% (82.1%) for the HEGP collimator against the LEHR collimator. Also, an increase in iterations × subsets from 16 to 48 led to the Coefficient of Variation (COV) increasing by 17.2%, 16.67%, 15.50%, 14.4%, 14.2%, and 14.1% for 10 mm to 37 mm sphere diameter, respectively.&#x0D; Conclusion: CT-based AC and HEGP collimators can yield improved 67Ga SPECT quantification compared to Non-AC and LEHR collimators. The choice of the optimal collimator with the reconstruction protocol led to changes in the image quality and quantitative accuracy, emphasizing the need to carefully select the appropriate combination of data acquisition factors.&#x0D;

The effects of kilovoltage (kV) and milliampere seconds (mAs) values for SPECT attenuation correction: An anthropomorphic phantom study

The purpose of SPECT/CT imaging to be used in dosimetric calculations is to perform accurate attenuation correction by giving the patient the minimum radiation dose. in accordance with ALARA principles (as low as reasonably achievable), it is critical to limit the amount of radiation given to the patient as far as possible in medical fields where radiation therapy is applied. The goal of this study is to determine the optimum kV and mAs values needed to keep the radiation dose that can be given to the patient in CT scans at a minimum level for attenuation correction, as well as to determine the CT-induced radiation doses on patients with different kV and mAs values using an anthropomorphic phantom.Radionuclides 177Lu and 131I were used in SPECT imaging. For CT-based attenuation correction, images were taken with various values between 80 kV × 30 mAs and 140 kV × 300 mAs using the anthropomorphic phantom. After that attenuation correction was performed with the obtained CT images for SPECT images. Then, CT-derived radiation doses were calculated.Our results showed that 80 kV × 30 mAs values can be used in scans after radionuclide treatment for CT attenuation correction. It was determined that the patient was exposed to a radiation dose of 0.432 mSv as a result of the CT scanning with the full detector width area of gamma camera detector. Thus, scanning with these values (80 kV × 30 mAs) resulted in approximately 95% less radiation exposure (0,432 mSv) than the value (9,38 mSv) with scanning of the manufacturer's recommended value (120 kV × 200 mAs).

Artificial Intelligence-Driven Single-Shot PET Image Artifact Detection and Disentanglement: Toward Routine Clinical Image Quality Assurance.

Medical imaging artifacts compromise image quality and quantitative analysis and might confound interpretation and misguide clinical decision-making. The present work envisions and demonstrates a new paradigm PET image Quality Assurance NETwork (PET-QA-NET) in which various image artifacts are detected and disentangled from images without prior knowledge of a standard of reference or ground truth for routine PET image quality assurance. The network was trained and evaluated using training/validation/testing data sets consisting of 669/100/100 artifact-free oncological 18 F-FDG PET/CT images and subsequently fine-tuned and evaluated on 384 (20% for fine-tuning) scans from 8 different PET centers. The developed DL model was quantitatively assessed using various image quality metrics calculated for 22 volumes of interest defined on each scan. In addition, 200 additional 18 F-FDG PET/CT scans (this time with artifacts), generated using both CT-based attenuation and scatter correction (routine PET) and PET-QA-NET, were blindly evaluated by 2 nuclear medicine physicians for the presence of artifacts, diagnostic confidence, image quality, and the number of lesions detected in different body regions. Across the volumes of interest of 100 patients, SUV MAE values of 0.13 ± 0.04, 0.24 ± 0.1, and 0.21 ± 0.06 were reached for SUV mean , SUV max , and SUV peak , respectively (no statistically significant difference). Qualitative assessment showed a general trend of improved image quality and diagnostic confidence and reduced image artifacts for PET-QA-NET compared with routine CT-based attenuation and scatter correction. We developed a highly effective and reliable quality assurance tool that can be embedded routinely to detect and correct for 18 F-FDG PET image artifacts in clinical setting with notably improved PET image quality and quantitative capabilities.

Pre-acquired CT-based attenuation correction with automated headrest removal for a brain-dedicated PET system.

Attenuation correction (AC) is essential for quantitative positron emission tomography (PET) images. Attenuation coefficient maps (μ-maps) are usually generated from computed tomography (CT) images when PET-CT combined systems are used. If CT has been performed prior to PET imaging, pre-acquired CT can be used for brain PET AC, because the human head is almost rigid. This pre-acquired CT-based AC approach is suitable for stand-alone brain-dedicated PET, such as VRAIN (ATOX Co. Ltd., Tokyo, Japan). However, the headrest of PET is different from the headrest in pre-acquired CT images, which may degrade the PET image quality. In this study, we prepared three different types of μ-maps: (1) based on the pre-acquired CT, where namely the headrest is different from the PET system (μ-map-diffHr); (2) manually removing the headrest from the pre-acquired CT (μ-map-noHr); and (3) artificially replacing the headrest region with the headrest of the PET system (μ-map-sameHr). Phantom images by VRAIN using each μ-map were investigated for uniformity, noise, and quantitative accuracy. Consequently, only the uniformity of the images using μ-map-diffHr was out of the acceptance criteria. We then proposed an automated method for removing the headrest from pre-acquired CT images. In comparisons of standardized uptake values in nine major brain regions from the 18F-fluoro-2-deoxy-D-glucose-PET of 10 healthy volunteers, no significant differences were found between the μ-map-noHr and the μ-map-sameHr. In conclusion, pre-acquired CT-based AC with automated headrest removal is useful for brain-dedicated PET such as VRAIN.

Comparison of positional artifacts in myocardial perfusion imaging in supine and semi-reclining position using dedicated D-SPECT cardiac camera: validation using CT based attenuation correction

BackgroundSoft-tissue attenuation remains a major limitation of SPECT-MPI which interferes with the diagnosis of CAD. The current study aims to evaluate the pattern of attenuation artifacts in supine and semi-reclining positions on CZT cardiac camera and their interaction with gender, BMI and stress protocols. MethodsWe prospectively analysed 150 patients acquired in supine and semi-reclining positions on CZT camera. The images were evaluated for severity and extent of defect using 17-segment model. An additional CT scan was acquired to generate AC image in the first 50 patients studied to assist investigator learning for comparison of artifact vs true defects in the two SPECT systems. The defects present in one position or showing change in severity within two positions were considered as positional artifacts and further validated using CTAC supine image. ResultsIn overall analysis, higher extent and severity of positional artifacts were observed more in semi-reclining position affecting the apex, apico-inferior, inferolateral and inferoseptal segments. Females showed more positional artifacts than males with inferior wall attenuation in the semireclining position and anterior wall attenuation in the supine position. A positive correlation of the extent and severity of positional artifacts was noted with an increasing BMI. In patients with BMI > 30, mid inferior and inferolateral segments were most affected followed by anterior wall segments. Highest correction of artifactual perfusion defects by CTAC was noted in inferior wall followed by inferolateral segments. ConclusionThe incidence of positional artifacts was greater in semi-reclining position in females, higher BMI groups and adenosine stress subsets. Knowledge of the pattern of positional artifacts appears to be a reliable alternative of CTAC for correct interpretation of myocardial perfusion images.

Deep-learning-based methods of attenuation correction for SPECT and PET

Attenuation correction (AC) is essential for quantitative analysis and clinical diagnosis of single-photon emission computed tomography (SPECT) and positron emission tomography (PET). In clinical practice, computed tomography (CT) is utilized to generate attenuation maps (μ-maps) for AC of hybrid SPECT/CT and PET/CT scanners. However, CT-based AC methods frequently produce artifacts due to CT artifacts and misregistration of SPECT-CT and PET-CT scans. Segmentation-based AC methods using magnetic resonance imaging (MRI) for PET/MRI scanners are inaccurate and complicated since MRI does not contain direct information of photon attenuation. Computational AC methods for SPECT and PET estimate attenuation coefficients directly from raw emission data, but suffer from low accuracy, cross-talk artifacts, high computational complexity, and high noise level. The recently evolving deep-learning-based methods have shown promising results in AC of SPECT and PET, which can be generally divided into two categories: indirect and direct strategies. Indirect AC strategies apply neural networks to transform emission, transmission, or MR images into synthetic μ-maps or CT images which are then incorporated into AC reconstruction. Direct AC strategies skip the intermediate steps of generating μ-maps or CT images and predict AC SPECT or PET images from non-attenuation-correction (NAC) SPECT or PET images directly. These deep-learning-based AC methods show comparable and even superior performance to non-deep-learning methods. In this article, we first discussed the principles and limitations of non-deep-learning AC methods, and then reviewed the status and prospects of deep-learning-based methods for AC of SPECT and PET.

Myocardial perfusion imaging with retrospective gating and integrated correction of attenuation, scatter, respiration, motion, and arrhythmia

BackgroundAbsolute quantitative myocardial perfusion SPECT requires addressing of aleatory and epistemic uncertainties in conjunction with providing image quality sufficient for lesion detection and characterization. Iterative reconstruction methods enable the mitigation of the root causes of image degradation. This study aimed to determine the feasibility of a new SPECT/CT method with integrated corrections attempting to enable absolute quantitative cardiac imaging (xSPECT Cardiac; xSC).MethodsWe compared images of prototype xSC and conventional SPECT (Flash3DTM) acquired at rest from 56 patients aged 71 ± 12 y with suspected coronary heart disease. The xSC prototype comprised list-mode acquisitions with continuous rotation and subsequent iterative reconstructions with retrospective electrocardiography (ECG) gating. Besides accurate image formation modeling, patient-specific CT-based attenuation and energy window-based scatter correction, additionally we applied mitigation for patient and organ motion between views (inter-view), and within views (intra-view) for both the gated and ungated reconstruction. We then assessed image quality, semiquantitative regional values, and left ventricular function in the images.ResultsThe quality of all xSC images was acceptable for clinical purposes. A polar map showed more uniform distribution for xSC compared with Flash3D, while lower apical count and higher defect contrast of myocardial infarction (p = 0.0004) were observed on xSC images. Wall motion, 16-gate volume curve, and ejection fraction were at least acceptable, with indication of improvements. The clinical prospectively gated method rejected beats ≥20% in 6 patients, whereas retrospective gating used an average of 98% beats, excluding 2% of beats. We used the list-mode data to create a product equivalent prospectively gated dataset. The dataset showed that the xSC method generated 18% higher count data and images with less noise, with comparable functional variables of volume and LVEF (p = ns).ConclusionsQuantitative myocardial perfusion imaging with the list-mode-based prototype xSPECT Cardiac is feasible, resulting in images of at least acceptable image quality.

Performance study of a 360° CZT camera for monitoring 177Lu-PSMA treatment

BackgroundThe aim of this study was to investigate the quantification performance of a 360° CZT camera for 177Lu-based treatment monitoring.MethodsThree phantoms with known 177Lu activity concentrations were acquired: (1) a uniform cylindrical phantom for calibration, (2) a NEMA IEC body phantom for analysis of different-sized spheres to optimise quantification parameters and (3) a phantom containing two large vials simulating organs at risk for tests. Four sets of reconstruction parameters were tested: (1) Scatter, (2) Scatter and Point Spread Function Recovery (PSFR), (3) PSFR only and (4) Penalised likelihood option and Scatter, varying the number of updates (iterations × subsets) with CT-based attenuation correction only. For each, activity concentration (ARC) and contrast recovery coefficients (CRC) were estimated as well as root mean square. Visualisation and quantification parameters were applied to reconstructed patient image data.ResultsOptimised quantification parameters were determined to be: CT-based attenuation correction, scatter correction, 12 iterations, 8 subsets and no filter. ARC, CRC and RMS results were dependant on the methodology used for calculations. Two different reconstruction parameters were recommended for visualisation and for quantification. 3D whole-body SPECT images were acquired and reconstructed for 177Lu-PSMA patients in 2–3 times faster than the time taken for a conventional gamma camera.ConclusionQuantification of whole-body 3D images of patients treated with 177Lu-PSMA is feasible and an optimised set of parameters has been determined. This camera greatly reduces procedure time for whole-body SPECT.

Differential privacy preserved federated transfer learning for multi-institutional 68Ga-PET image artefact detection and disentanglement

PurposeImage artefacts continue to pose challenges in clinical molecular imaging, resulting in misdiagnoses, additional radiation doses to patients and financial costs. Mismatch and halo artefacts occur frequently in gallium-68 (68Ga)-labelled compounds whole-body PET/CT imaging. Correcting for these artefacts is not straightforward and requires algorithmic developments, given that conventional techniques have failed to address them adequately. In the current study, we employed differential privacy-preserving federated transfer learning (FTL) to manage clinical data sharing and tackle privacy issues for building centre-specific models that detect and correct artefacts present in PET images.MethodsAltogether, 1413 patients with 68Ga prostate-specific membrane antigen (PSMA)/DOTA-TATE (TOC) PET/CT scans from 3 countries, including 8 different centres, were enrolled in this study. CT-based attenuation and scatter correction (CT-ASC) was used in all centres for quantitative PET reconstruction. Prior to model training, an experienced nuclear medicine physician reviewed all images to ensure the use of high-quality, artefact-free PET images (421 patients’ images). A deep neural network (modified U2Net) was trained on 80% of the artefact-free PET images to utilize centre-based (CeBa), centralized (CeZe) and the proposed differential privacy FTL frameworks. Quantitative analysis was performed in 20% of the clean data (with no artefacts) in each centre. A panel of two nuclear medicine physicians conducted qualitative assessment of image quality, diagnostic confidence and image artefacts in 128 patients with artefacts (256 images for CT-ASC and FTL-ASC).ResultsThe three approaches investigated in this study for 68Ga-PET imaging (CeBa, CeZe and FTL) resulted in a mean absolute error (MAE) of 0.42 ± 0.21 (CI 95%: 0.38 to 0.47), 0.32 ± 0.23 (CI 95%: 0.27 to 0.37) and 0.28 ± 0.15 (CI 95%: 0.25 to 0.31), respectively. Statistical analysis using the Wilcoxon test revealed significant differences between the three approaches, with FTL outperforming CeBa and CeZe (p-value < 0.05) in the clean test set. The qualitative assessment demonstrated that FTL-ASC significantly improved image quality and diagnostic confidence and decreased image artefacts, compared to CT-ASC in 68Ga-PET imaging. In addition, mismatch and halo artefacts were successfully detected and disentangled in the chest, abdomen and pelvic regions in 68Ga-PET imaging.ConclusionThe proposed approach benefits from using large datasets from multiple centres while preserving patient privacy. Qualitative assessment by nuclear medicine physicians showed that the proposed model correctly addressed two main challenging artefacts in 68Ga-PET imaging. This technique could be integrated in the clinic for 68Ga-PET imaging artefact detection and disentanglement using multicentric heterogeneous datasets.

Pelvic PET/MR attenuation correction in the image space using deep learning.

The five-class Dixon-based PET/MR attenuation correction (AC) model, which adds bone information to the four-class model by registering major bones from a bone atlas, has been shown to be error-prone. In this study, we introduce a novel method of accounting for bone in pelvic PET/MR AC by directly predicting the errors in the PET image space caused by the lack of bone in four-class Dixon-based attenuation correction. A convolutional neural network was trained to predict the four-class AC error map relative to CT-based attenuation correction. Dixon MR images and the four-class attenuation correction µ-map were used as input to the models. CT and PET/MR examinations for 22 patients ([18F]FDG) were used for training and validation, and 17 patients were used for testing (6 [18F]PSMA-1007 and 11 [68Ga]Ga-PSMA-11). A quantitative analysis of PSMA uptake using voxel- and lesion-based error metrics was used to assess performance. In the voxel-based analysis, the proposed model reduced the median root mean squared percentage error from 12.1% and 8.6% for the four- and five-class Dixon-based AC methods, respectively, to 6.2%. The median absolute percentage error in the maximum standardized uptake value (SUVmax) in bone lesions improved from 20.0% and 7.0% for four- and five-class Dixon-based AC methods to 3.8%. The proposed method reduces the voxel-based error and SUVmax errors in bone lesions when compared to the four- and five-class Dixon-based AC models.

Generative adversarial network-based attenuation correction for 99mTc-TRODAT-1 brain SPECT.

Attenuation correction (AC) is an important correction method to improve the quantification accuracy of dopamine transporter (DAT) single photon emission computed tomography (SPECT). Chang's method was developed for AC (Chang-AC) when CT-based AC was not available, assuming uniform attenuation coefficients inside the body contour. This study aims to evaluate Chang-AC and different deep learning (DL)-based AC approaches on 99mTc-TRODAT-1 brain SPECT using clinical patient data on two different scanners. Two hundred and sixty patients who underwent 99mTc-TRODAT-1 SPECT/CT scans from two different scanners (scanner A and scanner B) were retrospectively recruited. The ordered-subset expectation-maximization (OS-EM) method reconstructed 120 projections with dual-energy scatter correction, with or without CT-AC. We implemented a 3D conditional generative adversarial network (cGAN) for the indirect deep learning-based attenuation correction (DL-ACμ) and direct deep learning-based attenuation correction (DL-AC) methods, estimating attenuation maps (μ-maps) and attenuation-corrected SPECT images from non-attenuation-corrected (NAC) SPECT, respectively. We further applied cross-scanner training (cross-scanner indirect deep learning-based attenuation correction [cull-ACμ] and cross-scanner direct deep learning-based attenuation correction [call-AC]) and merged the datasets from two scanners for ensemble training (ensemble indirect deep learning-based attenuation correction [eDL-ACμ] and ensemble direct deep learning-based attenuation correction [eDL-AC]). The estimated μ-maps from (c/e)DL-ACμ were then used in reconstruction for AC purposes. Chang's method was also implemented for comparison. Normalized mean square error (NMSE), structural similarity index (SSIM), specific uptake ratio (SUR), and asymmetry index (%ASI) of the striatum were calculated for different AC methods. The NMSE for Chang's method, DL-ACμ, DL-AC, cDL-ACμ, cDL-AC, eDL-ACμ, and eDL-AC is 0.0406 ± 0.0445, 0.0059 ± 0.0035, 0.0099 ± 0.0066, 0.0253 ± 0.0102, 0.0369 ± 0.0124, 0.0098 ± 0.0035, and 0.0162 ± 0.0118 for scanner A and 0.0579 ± 0.0146, 0.0055 ± 0.0034, 0.0063 ± 0.0028, 0.0235 ± 0.0085, 0.0349 ± 0.0086, 0.0115 ± 0.0062, and 0.0117 ± 0.0038 for scanner B, respectively. The SUR and %ASI results for DL-ACμ are closer to CT-AC, Followed by DL-AC, eDL-ACμ, cDL-ACμ, cDL-AC, eDL-AC, Chang's method, and NAC. All DL-based AC methods are superior to Chang-AC. DL-ACμ is superior to DL-AC. Scanner-specific training is superior to cross-scanner and ensemble training. DL-based AC methods are feasible and robust for 99mTc-TRODAT-1 brain SPECT.

Effects of CT-based attenuation correction on quantitative SPECT/CT of jawbone.

With single photon emission computed tomography (SPECT)/computed tomography (CT) quantitative examinations, CT-based attenuation correction (CTAC) is considered necessary, though its effect on the quantitative values of an examined area close to the body surface, such as the jawbone, has not been elucidated. We performed an investigation to determine whether quantitative evaluation using a bone SPECT standalone device without CT is possible. The calculated indices were maximum standardized uptake value (SUVmax) and SUVpeak. Grouping was performed based on the presence or absence of CTAC. The CTAC group underwent CTAC, while the noAC group did not.Validation was performed using clinical data of patients who underwent a jawbone SPECT/CT examination. Becquerel calibration factor (BCF) is required for calculation of SUV, and was determined with values obtained with both phantom and syringe methods. The index for the uptake areas in each group was assessed using a paired t-test. Using BCF obtained with the phantom method, both SUVmax and SUVpeak were higher in the noAC group. In contrast, BCF obtained with the syringe method showed no significant difference between the CTAC and noAC groups in regard to SUVmax and SUVpeak. This tendency was found regardless of the device used. Also, a high correlation was observed between the groups for both devices (r=0.95 and 0.93). Our findings show that BCF obtained with a syringe method should be used when performing quantitative evaluation without CTAC. They also indicate that quantitative evaluation using a SPECT standalone device may be possible for jawbone SPECT/CT examinations.

Synthetic Attenuation Correction Maps for SPECT Imaging Using Deep Learning: A Study on Myocardial Perfusion Imaging.

(1) Background: The CT-based attenuation correction of SPECT images is essential for obtaining accurate quantitative images in cardiovascular imaging. However, there are still many SPECT cameras without associated CT scanners throughout the world, especially in developing countries. Performing additional CT scans implies troublesome planning logistics and larger radiation doses for patients, making it a suboptimal solution. Deep learning (DL) offers a revolutionary way to generate complementary images for individual patients at a large scale. Hence, we aimed to generate linear attenuation coefficient maps from SPECT emission images reconstructed without attenuation correction using deep learning. (2) Methods: A total of 384 SPECT myocardial perfusion studies that used 99mTc-sestamibi were included. A DL model based on a 2D U-Net architecture was trained using information from 312 patients. The quality of the generated synthetic attenuation correction maps (ACMs) and reconstructed emission values were evaluated using three metrics and compared to standard-of-care data using Bland-Altman plots. Finally, a quantitative evaluation of myocardial uptake was performed, followed by a semi-quantitative evaluation of myocardial perfusion. (3) Results: In a test set of 66 test patients, the ACM quality metrics were MSSIM = 0.97 ± 0.001 and NMAE = 3.08 ± 1.26 (%), and the reconstructed emission quality metrics were MSSIM = 0.99 ± 0.003 and NMAE = 0.23 ± 0.13 (%). The 95% limits of agreement (LoAs) at the voxel level for reconstructed SPECT images were: [-9.04; 9.00]%, and for the segment level, they were [-11; 10]%. The 95% LoAs for the Summed Stress Score values between the images reconstructed were [-2.8, 3.0]. When global perfusion scores were assessed, only 2 out of 66 patients showed changes in perfusion categories. (4) Conclusion: Deep learning can generate accurate attenuation correction maps from non-attenuation-corrected cardiac SPECT images. These high-quality attenuation maps are suitable for attenuation correction in myocardial perfusion SPECT imaging and could obviate the need for additional imaging in standalone SPECT scanners.

Effect of Gaussian Smoothing Filter Size for CT-Based Attenuation Correction on Quantitative Assessment of Bone SPECT/CT: A Phantom Study.

This study aims to determine the effect of Gaussian filter size for CT-based attenuation correction (CTAC) on the quantitative assessment of bone SPECT. An experiment was performed using a cylindrical phantom containing six rods, of which one was filled with water and five were filled with various concentrations of K2HPO4 solution (120-960mg/cm3) to simulate different bone densities. 99mTc-solution of 207kBq/ml was also included within the rods. SPECT data were acquired at 120 views for 30s/view. CT for attenuation correction were obtained at 120 kVp and 100mA. Sixteen different CTAC maps processed with different Gaussian filter sizes (ranging from 0 to 30mm in 2mm increments) were generated. SPECT images were reconstructed for each of the 16 CTAC maps. Attenuation coefficients and radioactivity concentrations in the rods were compared with those in the water-filled rod without K2HPO4 solution as a reference. Gaussian filter sizes below 14-16mm resulted in an overestimation of radioactivity concentrations for rods with high concentrations of K2HPO4 (≥ 666mg/cm3). The overestimation of radioactivity concentration measurement was 3.8% and 5.5% for 666mg/cm3 and 960mg/cm3 K2HPO4 solutions, respectively. The difference in radioactivity concentration between the water rod and the K2HPO4 rods was minimal at 18-22mm. The use of Gaussian filter sizes smaller than 14-16mm caused an overestimation of radioactivity concentration in regions of high CT values. Setting the Gaussian filter size to 18-22mm enables radioactivity concentration to be measured with the least influence on bone density.