Automatic attenuation map estimation from SPECT data only for brain perfusion scans using convolutional neural networks

A Deep-Learning-Based Partial-Volume Correction Method for Quantitative 177Lu SPECT/CT Imaging

With the development of new radiopharmaceutical therapies, quantitative SPECT/CT has progressively emerged as a crucial tool for dosimetry. One major obstacle of SPECT is its poor resolution, which results in blurring of the activity distribution. Especially for small objects, this so-called partial-volume effect limits the accuracy of activity quantification. Numerous methods for partial-volume correction (PVC) have been proposed, but most methods have the disadvantage of assuming a spatially invariant resolution of the imaging system, which does not hold for SPECT. Furthermore, most methods require a segmentation based on anatomic information. Methods: We introduce DL-PVC, a methodology for PVC of 177Lu SPECT/CT imaging using deep learning (DL). Training was based on a dataset of 10,000 random activity distributions placed in extended cardiac-torso body phantoms. Realistic SPECT acquisitions were created using the SIMIND Monte Carlo simulation program. SPECT reconstructions without and with resolution modeling were performed using the CASToR and STIR reconstruction software, respectively. The pairs of ground-truth activity distributions and simulated SPECT images were used for training various U-Nets. Quantitative analysis of the performance of these U-Nets was based on metrics such as the structural similarity index measure or normalized root-mean-square error, but also on volume activity accuracy, a new metric that describes the fraction of voxels in which the determined activity concentration deviates from the true activity concentration by less than a certain margin. On the basis of this analysis, the optimal parameters for normalization, input size, and network architecture were identified. Results: Our simulation-based analysis revealed that DL-PVC (0.95/7.8%/35.8% for structural similarity index measure/normalized root-mean-square error/volume activity accuracy) outperforms SPECT without PVC (0.89/10.4%/12.1%) and after iterative Yang PVC (0.94/8.6%/15.1%). Additionally, we validated DL-PVC on 177Lu SPECT/CT measurements of 3-dimensionally printed phantoms of different geometries. Although DL-PVC showed activity recovery similar to that of the iterative Yang method, no segmentation was required. In addition, DL-PVC was able to correct other image artifacts such as Gibbs ringing, making it clearly superior at the voxel level. Conclusion: In this work, we demonstrate the added value of DL-PVC for quantitative 177Lu SPECT/CT. Our analysis validates the functionality of DL-PVC and paves the way for future deployment on clinical image data.

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.

No impact of attenuation and scatter correction on the interpretation of dopamine transporter SPECT in patients with clinically uncertain parkinsonian syndrome

PURPOSE

The benefit from attenuation and scatter correction (ASC) of dopamine transporter (DAT)-SPECT for the detection of nigrostriatal degeneration in clinical routine is still a matter of debate. The current study evaluated the impact of ASC on visual interpretation and semi-quantitative analysis of DAT-SPECT in a large patient sample.

METHODS

One thousand seven hundred forty consecutive DAT-SPECT with 123I-FP-CIT from clinical routine were included retrospectively. SPECT images were reconstructed iteratively without and with ASC. Attenuation correction was based on uniform attenuation maps, scatter correction on simulation. All SPECT images were categorized with respect to the presence versus the absence of Parkinson-typical reduction of striatal 123I-FP-CIT uptake by three independent readers. Image reading was performed twice to assess intra-reader variability. The specific 123I-FP-CIT binding ratio (SBR) was used for automatic categorization, separately with and without ASC.

RESULTS

The mean proportion of cases with discrepant categorization by the same reader between the two reading sessions was practically the same without and with ASC, about 2.2%. The proportion of DAT-SPECT with discrepant categorization without versus with ASC by the same reader was 1.66% ± 0.50% (1.09-1.95%), not exceeding the benchmark of 2.2% from intra-reader variability. This also applied to automatic categorization of the DAT-SPECT images based on the putamen SBR (1.78% discrepant cases between without versus with ASC).

CONCLUSION

Given the large sample size, the current findings provide strong evidence against a relevant impact of ASC with uniform attenuation and simulation-based scatter correction on the clinical utility of DAT-SPECT to detect nigrostriatal degeneration in patients with clinically uncertain parkinsonian syndrome.

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

Background

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.

Methods

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.

Results

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.

Conclusion

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.

Deep-learning-based estimation of attenuation map improves attenuation correction performance over direct attenuation estimation for myocardial perfusion SPECT

BACKGROUND

Deep learning (DL)-based attenuation correction (AC) is promising to improve myocardial perfusion (MP) SPECT. We aimed to optimize and compare the DL-based direct and indirect AC methods, with and without SPECT and CT mismatch.

METHODS

One hundred patients with different 99mTc-sestamibi activity distributions and anatomical variations were simulated by a population of XCAT phantoms. Additionally, 34 patients 99mTc-sestamibi stress/rest SPECT/CT scans were retrospectively recruited. Projections were reconstructed by OS-EM method with or without AC. Mismatch between SPECT and CT images was modeled. A 3D conditional generative adversarial network (cGAN) was optimized for two DL-based AC methods: (i) indirect approach, i.e., non-attenuation corrected (NAC) SPECT paired with the corresponding attenuation map for training. The projections were reconstructed with the DL-generated attenuation map for AC; (ii) direct approach, i.e., NAC SPECT paired with the corresponding AC SPECT for training to perform direct AC.

RESULTS

Mismatch between SPECT and CT degraded DL-based AC performance. The indirect approach is superior to direct approach for various physical and clinical indices, even with mismatch modeled.

CONCLUSION

DL-based estimation of attenuation map for AC is superior and more robust to direct generation of AC SPECT.

Mesh modeling of system geometry and anatomy phantoms for realistic GATE simulations and their inclusion in SPECT reconstruction

Objective.Monte-Carlo simulation studies have been essential for advancing various developments in single photon emission computed tomography (SPECT) imaging, such as system design and accurate image reconstruction. Among the simulation software available, Geant4 application for tomographic emission (GATE) is one of the most used simulation toolkits in nuclear medicine, which allows building systems and attenuation phantom geometries based on the combination of idealized volumes. However, these idealized volumes are inadequate for modeling free-form shape components of such geometries. Recent GATE versions alleviate these major limitations by allowing users to import triangulated surface meshes.Approach.In this study, we describe our mesh-based simulations of a next-generation multi-pinhole SPECT system dedicated to clinical brain imaging, called AdaptiSPECT-C. To simulate realistic imaging data, we incorporated in our simulation the XCAT phantom, which provides an advanced anatomical description of the human body. An additional challenge with the AdaptiSPECT-C geometry is that the default voxelized XCAT attenuation phantom was not usable in our simulation due to intersection of objects of dissimilar materials caused by overlap of the air containing regions of the XCAT beyond the surface of the phantom and the components of the imaging system.Main results.We validated our mesh-based modeling against the one constructed by idealized volumes for a simplified single vertex configuration of AdaptiSPECT-C through simulated projection data of123I-activity distributions. We resolved the overlap conflict by creating and incorporating a mesh-based attenuation phantom following a volume hierarchy. We then evaluated our reconstructions with attenuation and scatter correction for projections obtained from simulation consisting of mesh-based modeling of the system and the attenuation phantom for brain imaging. Our approach demonstrated similar performance as the reference scheme simulated in air for uniform and clinical-like123I-IMP brain perfusion source distributions.Significance.This work enables the simulation of complex SPECT acquisitions and reconstructions for emulating realistic imaging data close to those of actual patients.

CT-free quantitative SPECT for automatic evaluation of %thyroid uptake based on deep-learning

PURPOSE

Quantitative thyroid single-photon emission computed tomography/computed tomography (SPECT/CT) requires computed tomography (CT)-based attenuation correction and manual thyroid segmentation on CT for %thyroid uptake measurements. Here, we aimed to develop a deep-learning-based CT-free quantitative thyroid SPECT that can generate an attenuation map (μ-map) and automatically segment the thyroid.

METHODS

Quantitative thyroid SPECT/CT data (n = 650) were retrospectively analyzed. Typical 3D U-Nets were used for the μ-map generation and automatic thyroid segmentation. Primary emission and scattering SPECTs were inputted to generate a μ-map, and the original μ-map from CT was labeled (268 and 30 for training and validation, respectively). The generated μ-map and primary emission SPECT were inputted for the automatic thyroid segmentation, and the manual thyroid segmentation was labeled (280 and 36 for training and validation, respectively). Other thyroid SPECT/CT (n = 36) and salivary SPECT/CT (n = 29) were employed for verification.

RESULTS

The synthetic μ-map demonstrated a strong correlation (R² = 0.972) and minimum error (mean square error = 0.936 × 10^-4, %normalized mean absolute error = 0.999%) of attenuation coefficients when compared to the ground truth (n = 30). Compared to manual segmentation, the automatic thyroid segmentation was excellent with a Dice similarity coefficient of 0.767, minimal thyroid volume difference of - 0.72 mL, and a short 95% Hausdorff distance of 9.416 mm (n = 36). Additionally, %thyroid uptake by synthetic μ-map and automatic thyroid segmentation (CT-free SPECT) was similar to that by the original μ-map and manual thyroid segmentation (SPECT/CT) (3.772 ± 5.735% vs. 3.682 ± 5.516%, p = 0.1090) (n = 36). Furthermore, the synthetic μ-map generation and automatic thyroid segmentation were successfully performed in the salivary SPECT/CT using the deep-learning algorithms trained by thyroid SPECT/CT (n = 29).

CONCLUSION

CT-free quantitative SPECT for automatic evaluation of %thyroid uptake can be realized by deep-learning.

CT-free attenuation correction for dedicated cardiac SPECT using a 3D dual squeeze-and-excitation residual dense network

BACKGROUND

Attenuation correction (AC) using CT transmission scanning enables the accurate quantitative analysis of dedicated cardiac SPECT. However, AC is challenging for SPECT-only scanners. We developed a deep learning-based approach to generate synthetic AC images from SPECT images without AC.

METHODS

CT-free AC was implemented using our customized Dual Squeeze-and-Excitation Residual Dense Network (DuRDN). 172 anonymized clinical hybrid SPECT/CT stress/rest myocardial perfusion studies were used in training, validation, and testing. Additional body mass index (BMI), gender, and scatter-window information were encoded as channel-wise input to further improve the network performance.

RESULTS

Quantitative and qualitative analysis based on image voxels and 17-segment polar map showed the potential of our approach to generate consistent SPECT AC images. Our customized DuRDN showed superior performance to conventional network design such as U-Net. The averaged voxel-wise normalized mean square error (NMSE) between the predicted AC images by DuRDN and the ground-truth AC images was 2.01 ± 1.01%, as compared to 2.23 ± 1.20% by U-Net.

CONCLUSIONS

Our customized DuRDN facilitates dedicated cardiac SPECT AC without CT scanning. DuRDN can efficiently incorporate additional patient information and may achieve better performance compared to conventional U-Net.

The Legacy of the TTASAAN Report - Premature Conclusions and Forgotten Promises About SPECT Neuroimaging: A Review of Policy and Practice Part II

Brain perfusion single photon emission computed tomography (SPECT) scans were initially developed in 1970s. A key radiopharmaceutical, hexamethylpropyleneamine oxime (HMPAO), was not stabilized until 1993 and most early SPECT scans were performed on single-head gamma cameras. These early scans were of inferior quality. In 1996, the Therapeutics and Technology Assessment Subcommittee of the American Academy of Neurology (TTASAAN) issued a report regarding the use of SPECT in the evaluation of neurological disorders. This two-part series explores the policies and procedures related to perfusion SPECT functional neuroimaging. In Part I, the comparison between the quality of the SPECT scans and the depth of the data for key neurological and psychiatric indications at the time of the TTASAAN report vs. the intervening 25 years were presented. In Part II, the technical aspects of perfusion SPECT neuroimaging and image processing will be explored. The role of color scales will be reviewed and the process of interpreting a SPECT scan will be presented. Interpretation of a functional brain scans requires not only anatomical knowledge, but also technical understanding on correctly performing a scan, regardless of the scanning modality. Awareness of technical limitations allows the clinician to properly interpret a functional brain scan. With this foundation, four scenarios in which perfusion SPECT neuroimaging, together with other imaging modalities and testing, lead to a narrowing of the differential diagnoses and better treatment. Lastly, recommendations for the revision of current policies and practices are made.

Convolutional neural network based attenuation correction for123I-FP-CIT SPECT with focused striatum imaging

SPECT imaging with¹²³I-FP-CIT is used for diagnosis of neurodegenerative disorders like Parkinson's disease. Attenuation correction (AC) can be useful for quantitative analysis of¹²³I-FP-CIT SPECT. Ideally, AC would be performed based on attenuation maps (μ-maps) derived from perfectly registered CT scans. Suchμ-maps, however, are most times not available and possible errors in image registration can induce quantitative inaccuracies in AC corrected SPECT images. Earlier, we showed that a convolutional neural network (CNN) based approach allows to estimate SPECT-alignedμ-maps for full brain perfusion imaging using only emission data. Here we investigate the feasibility of similar CNN methods for axially focused¹²³I-FP-CIT scans. We tested our approach on a high-resolution multi-pinhole prototype clinical SPECT system in a Monte Carlo simulation study. Three CNNs that estimateμ-maps in a voxel-wise, patch-wise and image-wise manner were investigated. As the added value of AC on clinical¹²³I-FP-CIT scans is still debatable, the impact of AC was also reported to check in which cases CNN based AC could be beneficial. AC using the ground truthμ-maps (GT-AC) and CNN estimatedμ-maps (CNN-AC) were compared with the case when no AC was done (No-AC). Results show that the effect of using GT-AC versus CNN-AC or No-AC on striatal shape and symmetry is minimal. Specific binding ratios (SBRs) from localized regions show a deviation from GT-AC≤2.5% for all three CNN-ACs while No-AC systematically underestimates SBRs by 13.1%. A strong correlation (r≥0.99) was obtained between GT-AC based SBRs and SBRs from CNN-ACs and No-AC. Absolute quantification (in kBq ml^-1) shows a deviation from GT-AC within 2.2% for all three CNN-ACs and of 71.7% for No-AC. To conclude, all three CNNs show comparable performance in accurateμ-map estimation and¹²³I-FP-CIT quantification. CNN-estimatedμ-map can be a promising substitute for CT-basedμ-map.

Development of attenuation correction methods using deep learning in brain-perfusion single-photon emission computed tomography

PURPOSE

Computed tomography (CT)-based attenuation correction (CTAC) in single-photon emission computed tomography (SPECT) is highly accurate, but it requires hybrid SPECT/CT instruments and additional radiation exposure. To obtain attenuation correction (AC) without the need for additional CT images, a deep learning method was used to generate pseudo-CT images has previously been reported, but it is limited because of cross-modality transformation, resulting in misalignment and modality-specific artifacts. This study aimed to develop a deep learning-based approach using non-attenuation-corrected (NAC) images and CTAC-based images for training to yield AC images in brain-perfusion SPECT. This study also investigated whether the proposed approach is superior to conventional Chang's AC (ChangAC).

METHODS

In total, 236 patients who underwent brain-perfusion SPECT were randomly divided into two groups: the training group (189 patients; 80%) and the test group (47 patients; 20%). Two models were constructed using Autoencoder (AutoencoderAC) and U-Net (U-NetAC), respectively. ChangAC, AutoencoderAC, and U-NetAC approaches were compared with CTAC using qualitative analysis (visual evaluation) and quantitative analysis (normalized mean squared error [NMSE] and the percentage error in each brain region). Statistical analyses were performed using the Wilcoxon signed-rank sum test and Bland-Altman analysis.

RESULTS

U-NetAC had the highest visual evaluation score. The NMSE results for the U-NetAC were the lowest, followed by AutoencoderAC and ChangAC (P < 0.001). Bland-Altman analysis showed a fixed bias for ChangAC and AutoencoderAC and a proportional bias for ChangAC. ChangAC underestimated counts by 30-40% in all brain regions. AutoencoderAC and U-NetAC produced mean errors of <1% and maximum errors of 3%, respectively.

CONCLUSION

New deep learning-based AC methods for AutoencoderAC and U-NetAC were developed. Their accuracy was higher than that obtained by ChangAC. U-NetAC exhibited higher qualitative and quantitative accuracy than AutoencoderAC. We generated highly accurate AC images directly from NAC images without the need for intermediate pseudo-CT images. To verify our models' generalizability, external validation is required.