Perfusion Single Photon Emission Computed Tomography Imaging Research Articles

Deep learning approach using SPECT-to-PET translation for attenuation correction in CT-less myocardial perfusion SPECT imaging

ObjectiveDeep learning approaches have attracted attention for improving the scoring accuracy in computed tomography-less single photon emission computed tomography (SPECT). In this study, we proposed a novel deep learning approach referring to positron emission tomography (PET). The aims of this study were to analyze the agreement of representative voxel values and perfusion scores of SPECT-to-PET translation model-generated SPECT (SPECTSPT) against PET in 17 segments according to the American Heart Association (AHA).MethodsThis retrospective study evaluated the patient-to-patient stress, resting SPECT, and PET datasets of 71 patients. The SPECTSPT generation model was trained (stress: 979 image pairs, rest: 987 image pairs) and validated (stress: 421 image pairs, rest: 425 image pairs) using 31 cases of SPECT and PET image pairs using an image-to-image translation network. Forty of 71 cases of left ventricular base-to-apex short-axis images were translated to SPECTSPT in the stress and resting state (stress: 1830 images, rest: 1856 images). Representative voxel values of SPECT and SPECTSPT in the 17 AHA segments against PET were compared. The stress, resting, and difference scores of 40 cases of SPECT and SPECTSPT were also compared in each of the 17 segments.ResultsFor AHA 17-segment-wise analysis, stressed SPECT but not SPECTSPT voxel values showed significant error from PET at basal anterior regions (segments #1, #6), and at mid inferoseptal regions (segments #8, #9, and #10). SPECT, but not SPECTSPT, voxel values at resting state showed significant error at basal anterior regions (segments #1, #2, and #6), and at mid inferior regions (segments #8, #9, and #11). Significant SPECT overscoring was observed against PET in basal-to-apical inferior regions (segments #4, #10, and #15) during stress. No significant overscoring was observed in SPECTSPT at stress, and only moderate over and underscoring in the basal inferior region (segment #4) was found in the resting and difference states.ConclusionsOur PET-supervised deep learning model is a new approach to correct well-known inferior wall attenuation in SPECT myocardial perfusion imaging. As standalone SPECT systems are used worldwide, the SPECTSPT generation model may be applied as a low-cost and practical clinical tool that provides powerful auxiliary information for the diagnosis of myocardial blood flow.

Stress Perfusion Cardiac Magnetic Resonance vs SPECT Imaging for Detection of Coronary Artery Disease

BackgroundGadaCAD2 was 1 of 2 international, multicenter, prospective, Phase 3 clinical trials that led to U.S. Food and Drug Administration approval of gadobutrol to assess myocardial perfusion and late gadolinium enhancement (LGE) in adults with known or suspected coronary artery disease (CAD). ObjectivesA prespecified secondary objective was to determine if stress perfusion cardiovascular magnetic resonance (CMR) was noninferior to single-photon emission computed tomography (SPECT) for detecting significant CAD and for excluding significant CAD. MethodsParticipants with known or suspected CAD underwent a research rest and stress perfusion CMR that was compared with a gated SPECT performed using standard clinical protocols. For CMR, adenosine or regadenoson served as vasodilators. The total dose of gadobutrol was 0.1 mmol/kg body weight. The standard of reference was a 70% stenosis defined by quantitative coronary angiography (QCA). A negative coronary computed tomography angiography could exclude CAD. Analysis was per patient. CMR, SPECT, and QCA were evaluated by independent central core lab readers blinded to clinical information. ResultsParticipants were predominantly male (61.4% male; mean age 58.9 ± 10.2 years) and were recruited from the United States (75.0%), Australia (14.7%), Singapore (5.7%), and Canada (4.6%). The prevalence of significant CAD was 24.5% (n = 72 of 294). Stress perfusion CMR was statistically superior to gated SPECT for specificity (P = 0.002), area under the receiver operating characteristic curve (P < 0.001), accuracy (P = 0.003), positive predictive value (P < 0.001), and negative predictive value (P = 0.041). The sensitivity of CMR for a 70% QCA stenosis was noninferior and nonsuperior to gated SPECT. ConclusionsVasodilator stress perfusion CMR, as performed with gadobutrol 0.1 mmol/kg body weight, had superior diagnostic accuracy for diagnosis and exclusion of significant CAD vs gated SPECT.

Myocardial Perfusion Single-Photon Emission Computed Tomography (SPECT) Image Denoising: A Comparative Study

The present study aimed to evaluate the effectiveness of different filters in improving the quality of myocardial perfusion single-photon emission computed tomography (SPECT) images. Data were collected using the Siemens Symbia T2 dual-head SPECT/Computed tomography (CT) scanner. Our dataset included more than 900 images from 30 patients. The quality of the SPECT was evaluated after applying filters such as the Butterworth, Hamming, Gaussian, Wiener, and median-modified Wiener filters with different kernel sizes, by calculating indicators such as the signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), and contrast-to-noise ratio (CNR). SNR and CNR were highest with the Wiener filter with a kernel size of 5 × 5. Additionally, the Gaussian filter achieved the highest PSNR. The results revealed that the Wiener filter, with a kernel size of 5 × 5, outperformed the other filters for denoising images of our dataset. The novelty of this study includes comparison of different filters to improve the quality of myocardial perfusion SPECT. As far as we know, this is the first study to compare the mentioned filters on myocardial perfusion SPECT images, using our datasets with specific noise structures and mentioning all the elements necessary for its presentation within one document.

Comparing Different Algorithms for the Pseudo-Coloring of Myocardial Perfusion Single-Photon Emission Computed Tomography Images.

Single-photon emission computed tomography (SPECT) images can significantly help physicians in diagnosing patients with coronary artery or suspected coronary artery diseases. However, these images are grayscale with qualities that are not readily visible. The objective of this study was to evaluate the effectiveness of different pseudo-coloring algorithms of myocardial perfusion SPECT images. Data were collected using a Siemens Symbia T2 dual-head SPECT/computed tomography (CT) scanner. After pseudo-coloring, the images were assessed both qualitatively and quantitatively. The qualities of different pseudo-color images were examined by three experts, while the images were evaluated quantitatively by obtaining indices such as mean squared error (MSE), peak signal-to-noise ratio (PSNR), normalized color difference (NCD), and structure similarity index metric (SSIM). The qualitative evaluation demonstrated that the warm color map (WCM), followed by the jet color map, outperformed the remaining algorithms in terms of revealing the non-visible qualities of the images. Furthermore, the quantitative evaluation results demonstrated that the WCM had the highest PSNR and SSIM but the lowest MSE. Overall, the WCM could outperform the other color maps both qualitatively and quantitatively. The novelty of this study includes comparing different pseudo-coloring methods to improve the quality of myocardial perfusion SPECT images and utilizing our collected datasets.

"Virtual" attenuation correction: improving stress myocardial perfusion SPECT imaging using deep learning.

Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is widely used for coronary artery disease (CAD) evaluation. Although attenuation correction is recommended to diminish image artifacts and improve diagnostic accuracy, approximately 3/4ths of clinical MPI worldwide remains non-attenuation-corrected (NAC). In this work, we propose a novel deep learning (DL) algorithm to provide "virtual" DL attenuation-corrected (DLAC) perfusion polar maps solely from NAC data without concurrent computed tomography (CT) imaging or additional scans. SPECT MPI studies (N = 11,532) with paired NAC and CTAC images were retrospectively identified. A convolutional neural network-based DL algorithm was developed and trained on half of the population to predict DLAC polar maps from NAC polar maps. Total perfusion deficit (TPD) was evaluated for all polar maps. TPDs from NAC and DLAC polar maps were compared to CTAC TPDs in linear regression analysis. Moreover, receiver-operating characteristic analysis was performed on NAC, CTAC, and DLAC TPDs to predict obstructive CAD as diagnosed from invasive coronary angiography. DLAC TPDs exhibited significantly improved linear correlation (p < 0.001) with CTAC (R2 = 0.85) compared to NAC vs. CTAC (R2 = 0.68). The diagnostic performance of TPD was also improved with DLAC compared to NAC with an area under the curve (AUC) of 0.827 vs. 0.780 (p = 0.012) with no statistically significant difference between AUC for CTAC and DLAC. At 88% sensitivity, specificity was improved by 18.9% for DLAC and 25.6% for CTAC. The proposed DL algorithm provided attenuation correction comparable to CTAC without the need for additional scans. Compared to conventional NAC perfusion imaging, DLAC significantly improved diagnostic accuracy.

Deep learning-guided attenuation correction in the image domain for myocardial perfusion SPECT imaging

Abstract We investigate the accuracy of direct attenuation correction (AC) in the image domain for myocardial perfusion SPECT (single-photon emission computed tomography) imaging (MPI-SPECT) using residual (ResNet) and UNet deep convolutional neural networks. MPI-SPECT 99mTc-sestamibi images of 99 patients were retrospectively included. UNet and ResNet networks were trained using non-attenuation-corrected SPECT images as input, whereas CT-based attenuation-corrected (CT-AC) SPECT images served as reference. Chang’s calculated AC approach considering a uniform attenuation coefficient within the body contour was also implemented. Clinical and quantitative evaluations of the proposed methods were performed considering SPECT CT-AC images of 19 subjects (external validation set) as reference. Image-derived metrics, including the voxel-wise mean error (ME), mean absolute error, relative error, structural similarity index (SSI), and peak signal-to-noise ratio, as well as clinical relevant indices, such as total perfusion deficit (TPD), were utilized. Overall, AC SPECT images generated using the deep learning networks exhibited good agreement with SPECT CT-AC images, substantially outperforming Chang’s method. The ResNet and UNet models resulted in an ME of −6.99 ± 16.72 and −4.41 ± 11.8 and an SSI of 0.99 ± 0.04 and 0.98 ± 0.05, respectively. Chang’s approach led to ME and SSI of 25.52 ± 33.98 and 0.93 ± 0.09, respectively. Similarly, the clinical evaluation revealed a mean TPD of 12.78 ± 9.22% and 12.57 ± 8.93% for ResNet and UNet models, respectively, compared to 12.84 ± 8.63% obtained from SPECT CT-AC images. Conversely, Chang’s approach led to a mean TPD of 16.68 ± 11.24%. The deep learning AC methods have the potential to achieve reliable AC in MPI-SPECT imaging.

"Ebstein's Anomaly" a Potential Cause of Misinterpretation on Myocardial Perfusion Imaging.

Ebstein's anomaly is a rare congenital heart disease. We present the case of a 47-year-old woman with history of Ebstein's anomaly who was referred to nuclear medicine department for a myocardial perfusion single-photon emission computed tomography (SPECT) imaging during pre-anesthetic check-up. Myocardial SPECT perfusion images with (99mTc)-Sestamibi demonstrated medium sizes fixed perfusion defect in the mid and proximal infero-septal wall adjacent inferior wall. This is a cause of potential misinterpretation on myocardial SPECT perfusion imaging as this perfusion defect was due to fibrosis rather than scarred myocardium.

A myocardial extraction method using deep learning for 99mTc myocardial perfusion SPECT images: A basic study to reduce the effects of extra-myocardial activity

AimThe purpose of this study was to automatically extract myocardial regions from transaxial single-photon emission computed tomography (SPECT) images using deep learning to reduce the effects of extracardiac activity, which has been problematic in cardiac nuclear imaging. Method: Myocardial region extraction was performed using two deep neural network architectures, U-Net and U-Net ++, and 694 myocardial SPECT images manually labeled with myocardial regions were used as the training data. In addition, a multi-slice input method was introduced during the learning session while taking the relationships to adjacent slices into account. Accuracy was assessed using Dice coefficients at both the slice and pixel levels, and the most effective number of input slices was determined. Results: The Dice coefficient was 0.918 at the pixel level, and there were no false positives at the slice level using U-Net++ with 9 input slices. Conclusion: The proposed system based on U-Net++ with multi-slice input provided highly accurate myocardial region extraction and reduced the effects of extracardiac activity in myocardial SPECT images.

Data-driven respiratory signal estimation from temporally finely sampled projection data in conventional cardiac perfusion SPECT imaging.

The aim of this work was to revisit the data-driven approach of axial center-of-mass (COM) measurements to recover a surrogate respiratory signal from finely sampled (100ms) single photon emission computed tomography (SPECT) projection data derived from list-mode acquisitions. For our initial evaluation, we acquired list-mode projection data from an anthropomorphic cardiac phantom mounted on a Quasar respiratory motion platform simulating 15mm amplitude respiratory motion. We also selected 302 consecutive patients (138 males, 164 females) with list-mode acquisitions, external respiratory motion tracking, and written consent to evaluate the clinical efficacy of our data-driven approach. Linear regression, Pearson's correlation coefficient (r), and standard error of the estimates (SEE) between the respiratory signals obtained with a visual tracking system (VTS) and COM measurements were calculated for individual projection data sets and for the patient group as a whole. Both the VTS- and COM-derived respiratory signals were used to estimate and correct respiratory motion. The reconstruction for six-degree of freedom rigid-body motion estimation was done in two ways: (1) using three iterations of ordered-subsets expectation-maximization (OSEM) with four subsets (16 projection angles per subset), or 12 iterations of maximum-likelihood expectation-maximization (MLEM). Respiratory motion compensation was done employing either OSEM with 16 subsets (four projection angles per subset) and five iterations or MLEM and 80 iterations, using the two respiratory estimates, respectively. Polar map quantification was also performed, calculating the percentage count difference (%Diff) between polar maps without and with respiratory motion included. Average % Diff was calculated in 17 segments (defined according to ASNC Guidelines). Paired t-tests were used to determine significance (p-values). The r-value calculated when comparing the VTS and COM respiratory signals varied widely between -0.01 and 0.96 with an average of 0.70, while the SEE varied between 0.80 and 6.48mm with an average of 2.05mm for our patient set, while the same values for the one anthropomorphic phantom acquisition are 0.91 and 1.11mm, respectively. A comparison between the respiratory motion estimates for VTS and COM in the S-I direction yielded an r=0.90 (0.94), and an SEE of 1.56mm (1.20mm) for OSEM (MLEM), respectively. Bland-Altman plots and calculated intraclass correlation coefficients also showed excellent agreement between the VTS and COM respiratory motion estimates. Average S-I respiratory estimates for the VTS (COM) were 9.04 (9.2mm) and 9.01mm (9.14mm) for the OSEM and MLEM, respectively. The paired t-test approached significance when comparing VTS and COM estimated respiratory signals with p-values of 0.069 and 0.051 for OSEM and MLEM. The respiratory estimates from the anthropomorphic cardiac phantom experiment using the VTS (COM) were 12.62 (14.10mm) and 12.55mm (14.29mm) for OSEM and MLEM, respectively. Polar map quantification yielded average % Diff consistently better when employing VTS-derived respiratory estimates to correct for respiration compared to the COM-derived estimates. The results indicate that our COM method has the potential to provide an automated data-driven correction of cardiac respiratory motion without the drawbacks of our VTS methodology. However, it is not generally equivalent to the VTS method in extent of correction.

Post-reconstruction attenuation correction for SPECT myocardium perfusion imaging facilitated by deep learning-based attenuation map generation

BackgroundAttenuation correction can improve the quantitative accuracy of single-photon emission computed tomography (SPECT) images. Existing SPECT-only systems normally can only provide non-attenuation corrected (NC) images which are susceptible to attenuation artifacts. In this work, we developed a post-reconstruction attenuation correction (PRAC) approach facilitated by a deep learning-based attenuation map for myocardial perfusion SPECT imaging. MethodsIn the PRAC method, new projection data were estimated via forwardly projecting the scanner-generated NC image. Then an attenuation map, generated from NC image using a pretrained deep learning (DL) convolutional neural network, was incorporated into an offline reconstruction algorithm to obtain the attenuation-corrected images from the forwardly projected projections. We evaluated the PRAC method using 30 subjects with a DL network trained with 40 subjects, using the vendor-generated AC images and CT-based attenuation maps as the ground truth. ResultsThe PRAC methods using DL-generated and CT-based attenuation maps were both highly consistent with the scanner-generated AC image. The globally normalized mean absolute errors were 1.1% ± .6% and .7% ± .4% and the localized absolute percentage errors were 8.9% ± 13.4% and 7.8% ± 11.4% in the left ventricular (LV) blood pool, respectively, and − 1.3% ± 8.0% and − 3.8% ± 4.5% in the LV myocardium for PRAC methods using DL-generated and CT-based attenuation maps, respectively. The summed stress scores after PRAC using both attenuation maps were more consistent with the ground truth than those of the NC images. ConclusionWe developed a PRAC approach facilitated by deep learning-based attenuation maps for SPECT myocardial perfusion imaging. It may be feasible for this approach to provide AC images for SPECT-only scanner data.

Regional cerebral perfusion in patients with amnestic mild cognitive impairment: effect of cerebral small vessel disease.

To explore the effort of cerebral small vessel disease (CSVD) on regional cerebral perfusion in patients with mild cognitive impairment (MCI) using NeuroGam™ software and evaluate the capability of brain perfusion single photon emission computed tomography (SPECT) in distinguishing MCI with and without CSVD. 34 amnestic MCI subjects entered this study, conducting neuropsychological tests, MRI and 99mTechnetium ethyl cystine dimer brain perfusion SPECT imaging. All subjects were divided into those with CSVD and those without CSVD. Perfusion value was measured with Brodmann area (BA) mapping in these two groups. Automated software (NeuroGam™) was used for semi-quantitative analyses of perfusion value and comparison with normal database. Compared with normal database, perfusion levels in BAs 23-left, 28 and 36-left of MCI without CSVD group had great deviations, while perfusion levels in BAs 21, 23, 24, 25, 28, 36, 38 and 47-left of MCI with CSVD group had great deviations. Furthermore, compared with CSVD group, there was significantly lower perfusion value in BA 7-left (P < 0.001) in MCI without CSVD group. CSVD could interact with pathological changes related to AD, exacerbating hypoperfusion in BAs 21, 23, 28, 36, 38 while compensating for cerebral blood perfusion disorder in BA 7-left in MCI patients. Meanwhile, MCI patients with CSVD shared similar hypoperfusion with vascular cognitive impairment (VCI) in BAs 24, 25 and 47L. Brain perfusion SPECT may help improve our ability to differentiate MCI with and without CSVD.

Radiomics analysis of myocardial perfusion SPECT images in patients with cardiomyopathy and heart failure

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): JSPS KAKENHI Grants Background Although myocardial perfusion heterogeneity due to focally damaged cardiomyocytes is observed in single−photon emission computed tomography (SPECT) imaging, a current perfusion defect scoring system does not allow us to provide sufficient diagnostic information for heterogeneity. Purpose The aim of this study was to perform radiomics analysis of myocardial perfusion SPECT (MPS) images to investigate the potential to detect myocardial perfusion heterogeneity. Methods Patients with hypertrophic cardiomyopathy (n = 3), heart failure (n = 9), and with a low likelihood of coronary artery disease (n =15) (Figure 1), who underwent a rest 99mTc-MIBI myocardial perfusion SPECT, were assessed using a LIFEx software. Four shape−based features, 6 histogram−based features, and 32 textural features were computed. The relevant features for the classification of the patients were selected using the Boruta algorithm, and hierarchical clustering of the selected features using the Spearman correlation coefficient was also performed for the feature reduction. The receiver operating characteristics (ROC) analysis was performed by the support vector machine to calculate the area under the ROC curve (AUC) for the selected features. Results Of 40 features, 17 were selected by the classification analysis, and these features were classified into 7 classes by the correlation analysis (Figure 2). The ROC AUCs for 7 features extracted from each class were 0.99, 0.97, 0.96, 0.92, 0.90, 0.86, and 0.83 for the contrast of NDGLDM, the entropy of histogram, ZLNU of GLZLM, the energy of GLCM, the energy of histogram, SZLGE of GLZLM, and the correlation of GLCM, respectively, as compared to 0.39 for a summed rest score. Conclusions Radiomics analysis successfully determined the myocardial perfusion heterogeneity in patients with cardiomyopathy and heart failure. It might be promising for the evaluation of myocardial damages that cannot be analyzed by the conventional scoring method.

Attenuation correction using deep learning for brain perfusion SPECT images

Non-uniform attenuation correction using computed tomography (CT) improves the image quality and quantification of single-photon emission computed tomography (SPECT). However, it is not widely used because it requires a SPECT/CT scanner. This study constructs a convolutional neural network (CNN) to generate attenuation-corrected SPECT images directly from non-attenuation-corrected SPECT images. We constructed an auto-encoder (AE) using a CNN to correct the attenuation in brain perfusion SPECT images. SPECT image datasets of 270 (44,528 slices including augmentation), 60 (5002 slices), and 30 (2558 slices) cases were used for training, validation, and testing, respectively. The acquired projection data were reconstructed in three patterns: uniform attenuation correction using Chang's method (Chang-AC), non-uniform attenuation correction using CT (CT-AC), and no attenuation correction (No-AC). The AE learned an end-to-end mapping between the No-AC and CT-AC images. The No-AC images in the test dataset were loaded into the trained AE, which generated images simulating the CT-AC images as output. The generated SPECT images were employed as attenuation-corrected images using the AE (AE-AC). The accuracy of the AE-AC images was evaluated in terms of the peak signal-to-noise ratio (PSNR) and the structural similarity metric (SSIM). The intensities of the AE-AC and CT-AC images were compared by voxel-by-voxel and region-by-region analysis. The PSNRs of the AE-AC and Chang-AC images, compared using CT-AC images, were 62.2, and 57.9, and their SSIM values were 0.9995 and 0.9985, respectively. The AE-AC and CT-AC images were visually and statistically in good agreement. The proposed AE-AC method yields highly accurate attenuation-corrected brain perfusion SPECT images.

Deep Learning-Based Computed Tomography Perfusion Mapping (DL-CTPM) for Pulmonary CT-to-Perfusion Translation.

Our purpose was to develop a deep learning-based computed tomography (CT) perfusion mapping (DL-CTPM) method that synthesizes lung perfusion images from CT images. This paper presents a retrospective analysis of the pulmonary technetium-99m-labeled macroaggregated albumin single-photon emission CT (SPECT)/CT scans obtained from 73 patients at Queen Mary Hospital in Hong Kong in 2019. The left and right lung scans were separated to double the size of the data set to 146. A 3-dimensional attention residual neural network was constructed to extract textural features from the CT images and reconstruct corresponding functional images. Eighty-four samples were randomly selected for training and cross-validation, and the remaining 62 were used for model testing in terms of voxel-wise agreement and function-wise concordance. To assess the voxel-wise agreement, the Spearman's correlation coefficient (R) and structural similarity index measure between the images predicted by the DL-CTPM and the corresponding SPECT perfusion images were computed to assess the statistical and perceptual image similarities,respectively. To assess the function-wise concordance, the Dice similarity coefficient (DSC) was computed to determine the similarity of the low/high functional lung volumes. The evaluation of the voxel-wise agreement showed a moderate-to-high voxel value correlation (0.6733 ± 0.1728) and high structural similarity (0.7635 ± 0.0697) between the SPECT and DL-CTPM predicted perfusions. The evaluation of the function-wise concordance obtained an average DSC value of 0.8183 ± 0.0752 for high-functional lungs (range, 0.5819-0.9255) and 0.6501 ± 0.1061 for low-functional lungs (range, 0.2405-0.8212). Ninety-four percent of the test cases demonstrated high concordance (DSC >0.7) between the high-functional volumes contoured from the predicted and ground-truth perfusions. We developed a novel DL-CTPM method for estimating perfusion-based lung functional images from the CT domain using a 3-dimensional attention residual neural network, which yielded moderate-to-high voxel-wise approximations of lung perfusion. To further contextualize these results toward future clinical application, a multi-institutional large-cohort study is warranted.

Development of a new Python-based cardiac phantom for myocardial SPECT imaging.

The aim of this work was to develop a digital dynamic cardiac phantom able to mimic gated myocardial perfusion single photon emission computed tomography (SPECT) images. A software code package was written to construct a cardiac digital phantom based on mathematical ellipsoidal model utilizing powerful numerical and mathematic libraries of python programing language. An ellipsoidal mathematical model was adopted to create the left ventricle geometrical volume including myocardial boundaries, left ventricular cavity, with incorporation of myocardial wall thickening and motion. Realistic myocardial count density from true patient studies was used to simulate statistical intensity variation during myocardial contraction. A combination of different levels of defect extent and severity were precisely modeled taking into consideration defect size variation during cardiac contraction. Wall thickening was also modeled taking into account the effect of partial volume. It has been successful to build a python-based software code that is able to model gated myocardial perfusion SPECT images with variable left ventricular volumes and ejection fraction. The recent flexibility of python programming enabled us to manipulate the shape and control the functional parameters in addition to creating variable sized-defects, extents and severities in different locations. Furthermore, the phantom code also provides different levels of image filtration mimicking those filters used in image reconstruction and their influence on image quality. Defect extent and severity were found to impact functional parameter estimation in consistence to clinical examinations. A python-based gated myocardial perfusion SPECT phantom has been successfully developed. The phantom proved to be reliable to assess cardiac software analysis tools in terms of perfusion and functional parameters. The software code is under further development and refinement so that more functionalities and features can be added.

Functional lung volume mapping with perfusion Single-Photon Emission Computed Tomography scan for radiotherapy planning in patients with locally advanced nonsmall cell lung cancer

Radical chemotherapy-radiotherapy represents the standard treatment for locally-advanced nonsmall cell lung cancer (NSCLC). Conventional radiotherapy achieves limited local tumor control, but dose escalation to the primary tumor is prevented by radiotherapy-induced toxicity. The aim of this study was to evaluate feasibility of tailored intensity-modulated radiotherapy (IMRT) planning based on lung single-photon emission computed tomography (SPECT) perfusion data and to compare functional and conventional dose-volume parameters. A total of 21 patients were prospectively enrolled. Patients underwent IMRT treatment with 2 Gy/fraction (median total dose of 60 Gy). Lung perfusion SPECT images were acquired before radiotherapy and 3 and 6 months after radiotherapy completion. SPECT and planning computed tomography images were co-registered using MIM-MAESTRO software with 3D-PET Edge algorithm. Lung volumes were defined anatomically as total lung and functionally as total not functional lung and total functional lung. Dose-volume histograms were calculated using QUANTEC constraints [mean lung dose (MLD)<20 Gy, V20<20%]. For each patient, conventional and functional radiotherapy plans were generated and compared. A total of 19 of 21 patients with NSCLC were included (mean age 66 years, 11 stage IIIA, 8 stage IIIB), 12/19 patients completed the 6-months follow-up. A significant reduction of mean V20 was observed in functional radiotherapy planning compared to conventional plan (405.9 cc, P < 0.001). Mean MLD was also lower in the SPECT-based plans, but the difference was not statistically relevant (0.8 Gy, P = 0.299). G2 radiation pneumonitis was observed in two patients. Functional radiotherapy planning allowed to decrease functional lung irradiation compared to conventional planning. The possibility to limit radiotherapy-induced toxicity could allow us to perform an effective dose-escalation to target volume.

Deep learning-based interpretation of basal/acetazolamide brain perfusion SPECT leveraging unstructured reading reports.

Basal/acetazolamide brain perfusion single-photon emission computed tomography (SPECT) has been used to evaluate functional hemodynamics in patients with carotid artery stenosis. We aimed to develop a deep learning model as a support system for interpreting brain perfusion SPECT leveraging unstructured text reports. In total, 7345 basal/acetazolamide brain perfusion SPECT images and their text reports were retrospectively collected. A long short-term memory (LSTM) network was trained using 500 randomly selected text reports to predict manually labeled structured information, including abnormalities of basal perfusion and vascular reserve for each vascular territory. Using this trained LSTM model, we extracted structured information from the remaining 6845 text reports to develop a deep learning model for interpreting SPECT images. The model was based on a 3D convolutional neural network (CNN), and the performance was tested on the other 500 cases by measuring the area under the receiver-operating characteristic curve (AUC). We then applied the model to patients who underwent revascularization (n = 33) to compare the estimated output of the CNN model for pre- and post-revascularization SPECT and clinical outcomes. The AUC of the LSTM model for extracting structured labels was 1.00 for basal perfusion and 0.99 for vascular reserve for all 9 brain regions. The AUC of the CNN model designed to identify abnormal perfusion was 0.83 for basal perfusion and 0.89 for vascular reserve. The output of the CNN model was significantly improved according to the revascularization in the target vascular territory, and its changes in brain territories were concordant with clinical outcomes. We developed a deep learning model to support the interpretation of brain perfusion SPECT by converting unstructured text reports into structured labels. This model can be used as a support system not only to identify perfusion abnormalities but also to provide quantitative scores of abnormalities, particularly for patients who require revascularization.

Validation of Automated Perfusion-Weighted Phase-Resolved Functional Lung (PREFUL)-MRI in Patients With Pulmonary Diseases.

Perfusion-weighted (Qw) noncontrast-enhanced proton lung MRI is a promising technique for assessment of pulmonary perfusion, but still requires validation. To improve perfusion-weighted phase-resolved functional lung (PREFUL)-MRI, to validate PREFUL with perfusion single photon emission computed tomography (SPECT) as a gold standard, and to compare PREFUL with dynamic contrast-enhanced (DCE)-MRI as a reference. Retrospective. Twenty patients with chronic obstructive pulmonary disease (COPD), 14 patients with cystic fibrosis (CF), and 21 patients with chronic thromboembolic pulmonary hypertension (CTEPH) were included. For PREFUL-MRI, a spoiled gradient echo sequence and for DCE-MRI a 3D time-resolved angiography with stochastic trajectories sequence were used at 1.5T. PREFUL-MRI coronal slices were acquired in free-breathing. DCE-MRI was performed in breath-hold with injection of 0.03 mmol/kg bodyweight of gadoteric acid at a rate of 4 cc/s. Perfusion SPECT images were obtained for six CTEPH patients. Images were coregistered. An algorithm to define the appropriate PREFUL perfusion phase was developed using perfusion SPECT data. Perfusion defect percentages (QDP) and Qw-values were calculated for all methods. For PREFUL quantitative perfusion values (PREFULQ ) and for DCE pulmonary blood flow (PBF) was calculated. Obtained parameters were assessed using Pearson correlation and Bland-Altman analysis. Qw-SPECT correlated with Qw-DCE (r = 0.50, P < 0.01) and Qw-PREFUL (r = 0.47, P < 0.01). Spatial overlap of QDP maps showed an agreement ≥67.7% comparing SPECT and DCE, ≥64.1% for SPECT and PREFUL, and ≥60.2% comparing DCE and PREFUL. Significant correlations of Qw-PREFUL and Qw-DCE were found (COPD: r = 0.79, P < 0.01; CF: r = 0.77, P < 0.01; CTEPH: r = 0.73, P < 0.01). PREFULQ /PBF correlations were similar/lower (CF, CTEPH: P > 0.12; COPD: P < 0.01) compared to Qw-PREFUL/DCE correlations. PREFULQ -values were higher/similar compared to PBF-values (COPD, CF: P < 0.01; CTEPH: P = 0.026). The automated PREFUL algorithm may allow for noncontrast-enhanced pulmonary perfusion assessment in COPD, CF, and CTEPH patients comparable to DCE-MRI. Level of Evidence 3 Technical Efficacy Stage 2 J. Magn. Reson. Imaging 2020;52:103-114.

Clinical utility of the normal database of 123I-iodoamphetamine brain perfusion single photon emission computed tomography for statistical analysis using computed tomography-based attenuation correction: a multicenter study

We have established a common normal database (NDB) with applicability in multicenter settings for the statistical analysis of brain perfusion single photon emission computed tomography (SPECT) with triple energy window scatter correction, computed tomography-based attenuation correction (CTAC), and spatial resolution compensation. This study aimed to compare the CTAC normal database (CTAC-NDB) with conventional normal databases for the statistical analysis of 123I-iodoamphetamine (123I-IMP) brain perfusion SPECT at three institutions and to assess the clinical efficiency of CTAC-NDB. We recruited 45 patients (26 men and 19 women; mean age, 74.2 ± 3.9years; Mini-Mental State Examination score, 19.8 ± 6.1) with Alzheimer's disease (AD, n = 26), dementia with Lewy bodies (DLB, n = 9), and mild cognitive impairment (n = 10) from three institutions. Three-dimensional stereotactic surface projection (3D-SSP) technique was used to analyze data obtained from the 123I-IMP brain perfusion SPECT images compared with both CTAC-NDB and conventional NDB. We visually assessed each 3D-SSP z score map to determine the changes in specific findings, such as AD/DLB pattern. Furthermore, the stereotactic extraction estimation analysis software was used to measure the regional z score severity and extent as a semiquantitative assessment. In the visual assessment, all cases exhibited clearer findings with CTAC-NDB than with conventional NDB in the parietotemporal association cortex as well as in the inferior temporal, frontal, and lateral occipital cortices. Contrarily, the findings from the medial cerebral regions, including the precuneus and the posterior cingulate, became indistinct in 71% of the cases and remained unchanged in 25% of the cases. In the semiquantitative analysis, a similar tendency was observed in the mean z score in the three institutions included in the study. Using the CTAC-NDB, the findings in the vicinity of the cranium became increasingly clear, whereas those in the medial surface of the brain became less defined or remained unchanged. These findings were confirmed via a semiquantitative analysis. Moreover, similar changes in the reduction pattern were observed in the three institutions. Therefore, the new database with CTAC might be applicable in other institutions. Data collected in this study may serve as a CTAC-NDB.

Ability of artificial intelligence to diagnose coronary artery stenosis using hybrid images of coronary computed tomography angiography and myocardial perfusion SPECT

BackgroundDetecting culprit coronary arteries in patients with ischemia using only myocardial perfusion single-photon emission computed tomography (SPECT) can be challenging. This study aimed to improve the detection of culprit regions using an artificial neural network (ANN) to analyze hybrid images of coronary computed tomography angiography (CCTA) and myocardial perfusion SPECT.MethodsThis study enrolled 59 patients with stable coronary artery disease (CAD) who had been assessed by coronary angiography within 60 days of myocardial perfusion SPECT. Two nuclear medicine physicians interpreted the myocardial perfusion SPECT and hybrid images with four grades of confidence, then drew regions on polar maps to identify culprit coronary arteries. The gold standard was determined by the consensus of two other nuclear cardiology specialist based on coronary angiography findings and clinical information. The ability to detect culprit coronary arteries was compared among experienced nuclear cardiologists and the ANN. Receiver operating characteristics (ROC) curves were analyzed and areas under the ROC curves (AUC) were determined.ResultsUsing hybrid images, observer A detected CAD in the right (RCA), left anterior descending (LAD), and left circumflex (LCX) coronary arteries with 83.6%, 89.3%, and 94.4% accuracy, respectively and observer B did so with 72.9%, 84.2%, and 89.3%, respectively. The ANN was 79.1%, 89.8%, and 89.3% accurate for each coronary artery. Diagnostic accuracy was comparable between the ANN and experienced nuclear medicine physicians. The AUC was significantly improved using hybrid images in the RCA region (observer A: from 0.715 to 0.835, p = 0.0031; observer B: from 0.771 to 0.843, p = 0.042). To detect culprit coronary arteries in perfusion defects of the inferior wall without using hybrid images was problematic because the perfused areas of the LCX and RCA varied among individuals.ConclusionsHybrid images of CCTA and myocardial perfusion SPECT are useful for detecting culprit coronary arteries. Diagnoses using artificial intelligence are comparable to that by nuclear medicine physicians.