Normal Databases for the Relative Quantification of Myocardial Perfusion

Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization

BACKGROUND

Coronary artery disease (CAD) has one of the highest mortality rates in humans worldwide. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) provides clinicians with myocardial metabolic information non-invasively. However, there are some limitations to interpreting SPECT images performed by physicians or automatic quantitative approaches. Radiomics analyzes images objectively by extracting quantitative features and can potentially reveal biological characteristics that the human eye cannot detect. However, the reproducibility and repeatability of some radiomic features can be highly susceptible to segmentation and imaging conditions.

PURPOSE

We aimed to assess the reproducibility of radiomic features extracted from uncorrected MPI-SPECT images reconstructed with 15 different settings before and after ComBat harmonization, along with evaluating the effectiveness of ComBat in realigning feature distributions.

MATERIALS AND METHODS

A total of 200 patients (50% normal and 50% abnormal) including rest and stress (without attenuation and scatter corrections) MPI-SPECT images were included. Images were reconstructed using 15 combinations of filter cut-off frequencies, filter orders, filter types, reconstruction algorithms, number of iterations and subsets resulting in 6000 images. Image segmentation was performed on the left ventricle in the first reconstruction for each patient and applied to 14 others. A total of 93 radiomic features were extracted from the segmented area, and ComBat was used to harmonize them. The intraclass correlation coefficient (ICC) and overall concordance correlation coefficient (OCCC) tests were performed before and after ComBat to examine the impact of each parameter on feature robustness and to assess harmonization efficiency. The ANOVA and the Kruskal-Wallis tests were performed to evaluate the effectiveness of ComBat in correcting feature distributions. In addition, the Student's t-test, Wilcoxon rank-sum, and signed-rank tests were implemented to assess the significance level of the impacts made by each parameter of different batches and patient groups (normal vs. abnormal) on radiomic features.

RESULTS

Before applying ComBat, the majority of features (ICC: 82, OCCC: 61) achieved high reproducibility (ICC/OCCC ≥ 0.900) under every batch except Reconstruction. The largest and smallest number of poor features (ICC/OCCC < 0.500) were obtained by IterationSubset and Order batches, respectively. The most reliable features were from the first-order (FO) and gray-level co-occurrence matrix (GLCM) families. Following harmonization, the minimum number of robust features increased (ICC: 84, OCCC: 78). Applying ComBat showed that Order and Reconstruction were the least and the most responsive batches, respectively. The most robust families, in a descending order, were found to be FO, neighborhood gray-tone difference matrix (NGTDM), GLCM, gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), and gray-level dependence matrix (GLDM) under Cut-off, Filter, and Order batches. The Wilcoxon rank-sum test showed that the number of robust features significantly differed under most batches in the Normal and Abnormal groups.

CONCLUSION

The majority of radiomic features show high levels of robustness across different OSEM reconstruction parameters in uncorrected MPI-SPECT. ComBat is effective in realigning feature distributions and enhancing radiomic features reproducibility.

Normal values of myocardial blood flow measured with dynamic myocardial computed tomography perfusion

AIMS

Dynamic myocardial computed tomography (CT) perfusion (DM-CTP) can, in combination with coronary CT angiography (CCTA), provide anatomical and functional evaluation of coronary artery disease (CAD). However, normal values of myocardial blood flow (MBF) are needed to identify impaired myocardial blood supply in patients with suspected CAD. We aimed to establish normal values for MBF measured using DM-CTP, to assess the effects of age and sex, and to assess regional distribution of MBF.

METHODS AND RESULTS

A total of 82 healthy individuals (46 women) aged 45-78 years with normal coronary arteries by CCTA underwent either rest and adenosine stress DM-CTP (n = 30) or adenosine-induced stress DM-CTP only (n = 52). Global and segmental MBF were assessed. Global MBF at rest and during stress were 0.93 ± 0.42 and 3.58 ± 1.14 mL/min/g, respectively. MBF was not different between the sexes (P = 0.88 at rest and P = 0.61 during stress), and no correlation was observed between MBF and age (P = 0.08 at rest and P = 0.82 during stress). Among the 16 myocardial segments, significant intersegmental differences were found (P < 0.01), which was not related to age, sex, or coronary dominance.

CONCLUSION

MBF assessed by DM-CTP in healthy individuals with normal coronary arteries displays significant intersegmental heterogeneity which does not seem to be affected by age, sex, or coronary dominance. Normal values of MBF may be helpful in the clinical evaluation of suspected myocardial ischaemia using DM-CTP.

Classification of coronary artery disease severity based on SPECT MPI polarmap images and deep learning: A study on multi-vessel disease prediction

Background

Coronary artery disease (CAD) is a global health concern. Conventional single photon emission computed tomography myocardial perfusion imaging (SPECT MPI) is a noninvasive method for assessing the severity of CAD. However, it relies on manual classification by clinicians, which can lead to visual fatigue and potential errors. Deep learning techniques have displayed promising results in CAD diagnosis and prediction, providing efficient and accurate analysis of medical images.

Methods

In this study, we explore the application of deep learning methods for assessing the severity of CAD and identifying cases of multivessel disease (MVD). We utilized the EfficientNet-V2 model in combination with DeepSMOTE to evaluate CAD severity using SPECT MPI images.

Results

Utilizing a dataset consisting of 254 patients (176 with MVD and 78 with single-vessel disease [SVD]), our model achieved an accuracy rate of 84.31% and area under the receiver operating characteristic curve (AUC) value of 0.8714 in predicting cases of MVD. These results underline the promising potential of our approach in MVD prediction, offering valuable diagnostic insights and the prospect of reducing medical costs.

Conclusion

This study emphasizes the feasibility of employing deep learning techniques for predicting MVD based on SPECT MPI images. The integration of Efficient-Net-V2 and DeepSMOTE methods effectively evaluates CAD severity and distinguishes MVD from SVD. Our research presents a practical approach to the early prediction and diagnosis of MVD, ultimately leading to enhanced patient outcomes and reduced healthcare costs.

Optimizing stress-only myocardial perfusion imaging: a clinical prediction model to improve patient selection

BACKGROUND

Stress-only single photon emission computed tomography myocardial perfusion imaging (MPI) offers numerous advantages in terms of improved workflow, cost and radiation reduction but is currently not widely utilized due to challenges in selecting appropriate patients for this technique.

METHODS

Data from 5959 individuals were used to derive (N = 4018) and validate (N = 1941) a binomial logistic regression model to predict normal stress MPI studies (stress total perfusion deficit  < 4%, ejection fraction ≥ 50%). Model performance was analyzed using receiver operator characteristic curves. A simplified point-scoring system was developed and its impact on imaging workflow was assessed.

RESULTS

Significant predictors of abnormal vs. normal stress MPI included male sex, age > 65 years, cardiomyopathy, congestive heart failure, myocardial infarction, angina, and pharmacological stress. The final model and simplified scoring system were associated with areas under the curve of 0.81 (95% CI 0.79-0.83) and 0.80 (95% CI 0.79-0.82) in the validation group, respectively. Use of the scoring system was estimated to result in a decrease of 56.5% in the number of non-contributory imaging studies acquired with minimal patient rescheduling.

CONCLUSION

A prediction tool derived from simple clinical information can identify candidates for stress-only MPI studies with a beneficial impact on departmental workflow.

Myocardial Perfusion SPECT Imaging Radiomic Features and Machine Learning Algorithms for Cardiac Contractile Pattern Recognition

A U-shaped contraction pattern was shown to be associated with a better Cardiac resynchronization therapy (CRT) response. The main goal of this study is to automatically recognize left ventricular contractile patterns using machine learning algorithms trained on conventional quantitative features (ConQuaFea) and radiomic features extracted from Gated single-photon emission computed tomography myocardial perfusion imaging (GSPECT MPI). Among 98 patients with standard resting GSPECT MPI included in this study, 29 received CRT therapy and 69 did not (also had CRT inclusion criteria but did not receive treatment yet at the time of data collection, or refused treatment). A total of 69 non-CRT patients were employed for training, and the 29 were employed for testing. The models were built utilizing features from three distinct feature sets (ConQuaFea, radiomics, and ConQuaFea + radiomics (combined)), which were chosen using Recursive feature elimination (RFE) feature selection (FS), and then trained using seven different machine learning (ML) classifiers. In addition, CRT outcome prediction was assessed by different treatment inclusion criteria as the study's final phase. The MLP classifier had the highest performance among ConQuaFea models (AUC, SEN, SPE = 0.80, 0.85, 0.76). RF achieved the best performance in terms of AUC, SEN, and SPE with values of 0.65, 0.62, and 0.68, respectively, among radiomic models. GB and RF approaches achieved the best AUC, SEN, and SPE values of 0.78, 0.92, and 0.63 and 0.74, 0.93, and 0.56, respectively, among the combined models. A promising outcome was obtained when using radiomic and ConQuaFea from GSPECT MPI to detect left ventricular contractile patterns by machine learning.

Anthropomorphic cardiac phantom for dynamic SPECT

BACKGROUND

As myocardial blood flow measurement (MBF) in SPECT systems became recently available, significant effort has been devoted to its validation. For that purpose, we have developed a cardiac phantom that is able to mimic physiological radiotracer variation in the left ventricle cavity and in the myocardium, while performing beating-like motion. The new phantom is integrated inside a standard anthropomorphic torso allowing a realistic tissue attenuation and gamma-ray scattering METHODS AND RESULTS: A mechanical cardiac phantom was integrated in a commercially available anthropomorphic torso. Using a GE Discovery 530c SPECT, measurements were performed. It was found that gamma-ray attenuation effects are significant and limit the MBF measurements to global/three-vessel resolution. Dynamic SPECT experiments were performed to validate MBF accuracy and showed mean relative error of 14%. Finally, the effect of varying radiotracer dose on the accuracy of dynamic SPECT was studied CONCLUSIONS: A dynamic cardiac phantom has been developed and successfully integrated in a standard SPECT torso. A good agreement was found between SPECT-reported MBF values and the expected results. Despite increased noise-to-signal ratio when radiotracer doses were reduced, MBF uncertainty did not increase significantly down to very low doses, thanks to the temporal integration of the activity during the measurement.

Deep learning for myocardial ischemia auxiliary diagnosis using CZT SPECT myocardial perfusion imaging

BACKGROUND

The World Health Organization reported that cardiovascular disease is the most common cause of death worldwide. On average, one person dies of heart disease every 26 min worldwide. Deep learning approaches are characterized by the appropriate combination of abnormal features based on numerous annotated images. The constructed convolutional neural network (CNN) model can identify normal states of reversible and irreversible myocardial defects and alert physicians for further diagnosis.

METHODS

Cadmium zinc telluride single-photon emission computed tomography myocardial perfusion resting-state images were collected at Chang Gung Memorial Hospital, Kaohsiung Medical Center, Kaohsiung, Taiwan, and were analyzed with a deep learning convolutional neural network to classify myocardial perfusion images for coronary heart diseases.

RESULTS

In these grey-scale images, the heart blood flow distribution was the most crucial feature. The deep learning technique of You Only Look Once was used to determine the myocardial defect area and crop the images. After surrounding noise had been eliminated, a three-dimensional CNN model was used to identify patients with coronary heart diseases. The prediction area under the curve, accuracy, sensitivity, and specificity was 90.97, 87.08, 86.49, and 87.41%, respectively.

CONCLUSION

Our prototype system can considerably reduce the time required for image interpretation and improve the quality of medical care. It can assist clinical experts by offering accurate coronary heart disease diagnosis in practice.

Diagnostic accuracy of stress-only myocardial perfusion SPECT improved by deep learning

PURPOSE

Deep convolutional neural networks (CNN) for single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) has been used to improve the diagnostic accuracy of coronary artery disease (CAD). This study was to design and evaluate a deep learning (DL) approach to automatic diagnosis of myocardial perfusion abnormalities from stress-only MPI.

METHODS

The new DL approach developed for this study was compared to a conventional quantitative perfusion defect size (DS) method. A total of 37,243 patients (51.5% males) undergone stress ^99mTc-Tetrofosmin or ^99mTc-Sestamibi MPI were selected retrospectively from Yale New Haven Hospital. Patients were dichotomized as studies with normal (75.4%) or abnormal (24.6%) myocardial perfusion based on final diagnoses of clinical nuclear cardiologists. Stress myocardial perfusion defect size was calculated using Yale quantitative analytic software. A deep CNN was trained using the circumferential count profile maps derived from SPECT MPI and was evaluated for the diagnosis of perfusion abnormality with a 5-fold cross-validation approach. In each fold, 27,933, 1862 and 7448 patients were used as training, validation and testing datasets, respectively. The area under the receiver-operating characteristic curve (AUC) was calculated and analyzed for all patients as well as for the eight sub-groups classified based on patient genders, quantitative algorithms, radioactive tracers and SPECT cameras.

RESULTS

The AUC value resulted from the DL method was significantly higher than that from the DS method (0.872 ± 0.002 vs. 0.838 ± 0.003, p < 0.01). Across the eight sub-groups, the DL method provided more consistent AUC values in terms of smaller standard deviation and higher diagnostic accuracy and specificity, but slightly lower sensitivity than the DS method (AUC: 0.865 ± 0.010 vs. 0.838 ± 0.019, Accuracy: 82.7% ± 2.5% vs. 78.5% ± 3.6%, Specificity: 84.9% ± 3.7% vs. 77.5% ± 6.5%, Sensitivity: 74.4% ± 4.2% vs. 79.8% ± 5.8%).

CONCLUSIONS

The incorporation of deep learning for stress-only MPI has a considerable potential to improve the diagnostic accuracy and consistency in the detection of myocardial perfusion abnormalities.

Effect of reduced photon count levels and choice of normal data on semi-automated image assessment in cardiac SPECT

BACKGROUND

The SMARTZOOM multifocal collimator from Siemens Healthcare was developed to improve the γ-photon sensitivity in myocardial perfusion imaging without truncating the field of view. As part of the IQ-SPECT package, it may be used to reduce radiopharmaceutical dose to patients, as well as acquisition time. The aim of this study was twofold: (1) to evaluate the influence of dose reduction in semi-automated MPI scoring, with focus on different strategies for the choice of normal data (count-matched, full-count), and (2) to evaluate the effect of dose reduction afforded by Siemens' IQ-SPECT package.

METHODS

50 patients underwent Tc-99m-sestamibi one-day stress/rest SPECT/CT. Multiple levels of count reduction were generated using binomial thinning. Using Corridor 4DM, summed stress score (SSS) was calculated using either count-matched or full-count normal data. Studies were classified as low-risk (SSS < 4) or intermediate/high-risk (SSS ≥ 4).

RESULTS

Count reduction using count-matched normal data increases false-normal rate and decreases sensitivity. With full-count normal data, count reduction increases false-hypoperfusion rate, leading to decreased specificity. Altogether, rate of reclassification was significant at roughly 67% dose and below.

CONCLUSION

Significant bias results from count level of normal data relative to actual patient data. Compared to standard LEHR, IQ-SPECT should allow for significant dose reduction.

V/Q SPECT for the Assessment of Regional Lung Function: Generation of Normal Mean and Standard Deviation 3-D Maps

Background: V/Q SPECT/CT is attractive for regional lung function assessment, but accurate delineation and quantification of functional lung volumes remains a challenge. Physiological intra and inter patient non-uniformity of V/Q SPECT images make conventional delineation methods of functional lung volumes inaccurate. In that context it would be of interest to build statistical maps of normal V/Q SPECT to assess the physiological variability of radiotracers. The aim of this study was to generate normal mean and standard deviation maps of regional lung function as assessed with V/Q SPECT/CT, with (AC) and without (NoAC) attenuation correction. Methods: During a 13 month period, 73 consecutive patients referred for suspected acute pulmonary embolism, that had normal V/Q SPECT/CT based on the interpretation of 2 independent nuclear medicine physicians, were selected. Four set of images were reconstructed: perfusion and ventilation images, AC, and NoAC, respectively. Statistical maps were created as follows: all cases were registered to a reference scan using the CT data, first with a rigid then with a non-rigid method. SPECTs reconstructions were then co-registered and normalized, and mean and standard deviation voxel-wise maps were calculated. To assess the consistency of generated maps to lung physiology and the potential impact of non-rigid registration, visual analysis and quantitative comparison with non-registered data were performed in the whole series. Quantitative comparison was also conducted in two randomly sampled independent subsets. Results: Perfusion mean maps showed a continuous negative posterior to anterior gradient, majored on the AC mean map. Perfusion standard deviation maps showed higher variability in the periphery of the lungs, but especially in the posterior areas. The ventilation mean map showed a slightly positive posterior to anterior gradient on NoAC mean ventilation map, while the AC mean map showed no gradient. The NoAC ventilation SD map showed a higher variability in the periphery of the lungs as compared with AC SD map. No statistical difference in the posterior to anterior gradient measurements was found between the generated mean statistical maps and the non-registered data, either in the whole series or across the two independent datasets. Conclusion: We proposed a methodology to create statistical normal maps for V/Q SPECTs. Maps were consistent with the known physiological non-uniformity and showed the impact of attenuation correction on the posterior to anterior gradient. These maps could be used for a Z-score analysis, and a better segmentation of healthy uptake areas.

Impact of non-specific normal databases on perfusion quantification of low-dose myocardial SPECT studies

AIM

To evaluate the impact of non-specific normal databases on the percent summed rest score (SR%) and stress score (SS%) from simulated low-dose SPECT studies by shortening the acquisition time/projection.

METHODS

Forty normal-weight and 40 overweight/obese patients underwent myocardial studies with a conventional gamma-camera (BrightView, Philips) using three different acquisition times/projection: 30, 15, and 8 s (100%-counts, 50%-counts, and 25%-counts scan, respectively) and reconstructed using the iterative algorithm with resolution recovery (IRR) AstonishTM (Philips). Three sets of normal databases were used: (1) full-counts IRR; (2) half-counts IRR; and (3) full-counts traditional reconstruction algorithm database (TRAD). The impact of these databases and the acquired count statistics on the SR% and SS% was assessed by ANOVA analysis and Tukey test (P < 0.05).

RESULTS

Significantly higher SR% and SS% values (> 40%) were found for the full-counts TRAD databases respect to the IRR databases. For overweight/obese patients, significantly higher SS% values for 25%-counts scans (+19%) are confirmed compared to those of 50%-counts scan, independently of using the half-counts or the full-counts IRR databases.

CONCLUSIONS

AstonishTM requires the adoption of the own specific normal databases in order to prevent very high overestimation of both stress and rest perfusion scores. Conversely, the count statistics of the normal databases seems not to influence the quantification scores.

Classification of Polar Maps from Cardiac Perfusion Imaging with Graph-Convolutional Neural Networks

Myocardial perfusion imaging is a non-invasive imaging technique commonly used for the diagnosis of Coronary Artery Disease and is based on the injection of radiopharmaceutical tracers into the blood stream. The patient's heart is imaged while at rest and under stress in order to determine its capacity to react to the imposed challenge. Assessment of imaging data is commonly performed by visual inspection of polar maps showing the tracer uptake in a compact, two-dimensional representation of the left ventricle. This article presents a method for automatic classification of polar maps based on graph convolutional neural networks. Furthermore, it evaluates how well localization techniques developed for standard convolutional neural networks can be used for the localization of pathological segments with respect to clinically relevant areas. The method is evaluated using 946 labeled datasets and compared quantitatively to three other neural-network-based methods. The proposed model achieves an agreement with the human observer on 89.3% of rest test polar maps and on 91.1% of stress test polar maps. Localization performed on a fine 17-segment division of the polar maps achieves an agreement of 83.1% with the human observer, while localization on a coarse 3-segment division based on the vessel beds of the left ventricle has an agreement of 78.8% with the human observer. Our method could thus assist the decision-making process of physicians when analyzing polar map data obtained from myocardial perfusion images.

Effect of nicorandil administration on myocardial microcirculation during primary percutaneous coronary intervention in patients with acute myocardial infarction

Introduction

Prevention of the no-reflow phenomenon has a crucial role in primary percutaneous coronary intervention (P-PCI) procedures.

Aim

To assess the effects of early intracoronary administration of nicorandil (NIC) during P-PCI on myocardial microcirculation in patients with acute myocardial infarction (AMI).

Material and methods

A total of 120 patients with first acute anterior wall ST segment elevation myocardial infarction who underwent P-PCI were randomly divided into two groups: the NIC group (A, n = 60) and the placebo group (B, n = 60). Before stent placement, NIC or normal saline was injected using a guiding catheter. The thrombolysis in myocardial infarction (TIMI) grade, TIMI myocardial perfusion grade (TMPG), resolution of ST segment elevation (defined as > 50% decrease in ST elevation) 1 h after surgery, and ⁹⁹Tc^m-methoxyisobutyl isocyanide (MIBI) rest myocardial perfusion imaging (MPI) via single-photon emission computed tomography (⁹⁹Tc^m-MIBI SPECT) findings 10 days after surgery were compared between the two groups.

Results

The number of patients who achieved TIMI grade 3 (96.67% vs. 86.67%; p = 0.047) and TMPG 3 (95% vs. 83.33%; p = 0.040) was higher in the NIC group than in the placebo group. Resolution of ST segment elevation occurred in 95% and 81.67% of the patients in the NIC and placebo groups, respectively (p = 0.023); the MPI score of the two groups was 4.1 ±1.89 and 7.3 ±2.65, respectively (p = 0.014).

Conclusions

Early coronary administration of NIC can significantly reduce the damage in the myocardial microcirculation caused by P-PCI and the myocardial infarct size in patients with AMI.

Non-invasive imaging in cardiology for the generalist

In contrast to invasive techniques, the goal of non-invasive cardiac imaging is to identify or exclude heart disease in response to a patient's clinical history of cardiac localizing symptoms. Imaging also aims to establish the risk of an individual developing future heart disease with a view to preventing major cardiovascular events such as myocardial infarction. As well as a role in risk stratification, non-invasive cardiac imaging also helps with decision making for future medical and procedural interventions. This review outlines the non-invasive imaging modalities available to physicians to identify and risk stratify cardiovascular disease. It discusses the strengths of each imaging technique, in which circumstances it is most useful and its diagnostic accuracy.