A machine learning-based approach to directly compare the diagnostic accuracy of myocardial perfusion imaging by conventional and cadmium-zinc telluride SPECT

Immediate recruitment of dormant coronary collaterals can provide more than half of normal resting perfusion during coronary occlusion in patients with coronary artery disease

BACKGROUND

Dormant coronary collaterals are highly prevalent and clinically beneficial in cases of coronary occlusion. However, the magnitude of myocardial perfusion provided by immediate coronary collateral recruitment during acute occlusion is unknown. We aimed to quantify collateral myocardial perfusion during balloon occlusion in patients with coronary artery disease (CAD).

METHODS

Patients without angiographically visible collaterals undergoing elective percutaneous transluminal coronary angioplasty (PTCA) to a single epicardial vessel underwent two scans with 99mTc-sestamibi myocardial perfusion single-photon emission computed tomography (SPECT). All subjects underwent at least three minutes of angiographically verified complete balloon occlusion, at which time an intravenous injection of the radiotracer was administered, followed by SPECT imaging. A second radiotracer injection followed by SPECT imaging was performed 24 h after PTCA.

RESULTS

The study included 22 patients (median [interquartile range] age 68 [54-72] years. The perfusion defect extent was 19 [11-38] % of the LV, and the collateral perfusion at rest was 64 [58-67]% of normal.

CONCLUSION

This is the first study to describe the magnitude of short-term changes in coronary microvascular collateral perfusion in patients with CAD. On average, despite coronary occlusion and an absence of angiographically visible collateral vessels, collaterals provided more than half of the normal perfusion.

Review of cardiovascular imaging in the Journal of Nuclear Cardiology 2022: single photon emission computed tomography

In this review, we will summarize a selection of articles on single-photon emission computed tomography published in the Journal of Nuclear Cardiology in 2022. The aim of this review is to concisely recap major advancements in the field to provide the reader a glimpse of the research published in the journal over the last year. This review will place emphasis on myocardial perfusion imaging using single-photon emission computed tomography summarizing advances in the field including in prognosis, non-perfusion variables, attenuation compensation, machine learning and camera design. It will also review nuclear imaging advances in amyloidosis, left ventricular mechanical dyssynchrony, cardiac innervation, and lung perfusion. We encourage interested readers to go back to the original articles, and editorials, for a comprehensive read as necessary but hope that this yearly review will be helpful in reminding readers of articles they have seen and attracting their attentions to ones they have missed.

Regional myocardial perfusion imaging in predicting vessel-related outcome: interplay between the perfusion results and angiographic findings

BACKGROUND

Despite myocardial perfusion imaging (MPI) by cadmium-zinc-telluride (CZT) single-photon emission computed tomography (SPECT) camera is largely used in the diagnosis and risk stratification of patients with suspected or known coronary artery disease (CAD), no data are available on the prognostic value of a regional MPI evaluation. We evaluated the prognostic value of regional MPI by the CZT camera in predicting clinical outcomes at the vessel level in patients with available angiographic data.

METHODS AND RESULTS

Five hundred and forty-one subjects with suspected or known CAD referred to 99mTc-sestamibi gated CZT-SPECT cardiac imaging and with available angiographic data were studied. Both regional total perfusion deficit (TPD) and ischemic TPD (ITPD) were calculated separately for each vascular territory (left anterior descending, left circumflex, and right coronary artery). The outcome end points were cardiac death, target vessel-related myocardial infarction, or late coronary revascularization. The prevalence of CAD ≥ 50%, regional stress TPD, and regional ITPD was significantly higher in vessels with events as compared to those without (both P < 0.001). The receiver operating characteristics area under the curve for regional ITPD for the identification of vessel-related events was 0.81 (95% confidence interval 0.75-0.86). An ITPD value of 2.0% provided the best trade-off for identifying the vessel-related event. At multivariable analysis, both CAD ≥ 50% and ITPD ≥ 2.0% resulted in independent predictors of events.

CONCLUSIONS

Regional myocardial perfusion assessed by the CZT camera demonstrated good reliability in predicting vessel-related events in patients with suspected or known CAD.

Radiopharmaceuticals for PET and SPECT Imaging: A Literature Review over the Last Decade

Positron emission tomography (PET) uses radioactive tracers and enables the functional imaging of several metabolic processes, blood flow measurements, regional chemical composition, and/or chemical absorption. Depending on the targeted processes within the living organism, different tracers are used for various medical conditions, such as cancer, particular brain pathologies, cardiac events, and bone lesions, where the most commonly used tracers are radiolabeled with 18F (e.g., [18F]-FDG and NA [18F]). Oxygen-15 isotope is mostly involved in blood flow measurements, whereas a wide array of 11C-based compounds have also been developed for neuronal disorders according to the affected neuroreceptors, prostate cancer, and lung carcinomas. In contrast, the single-photon emission computed tomography (SPECT) technique uses gamma-emitting radioisotopes and can be used to diagnose strokes, seizures, bone illnesses, and infections by gauging the blood flow and radio distribution within tissues and organs. The radioisotopes typically used in SPECT imaging are iodine-123, technetium-99m, xenon-133, thallium-201, and indium-111. This systematic review article aims to clarify and disseminate the available scientific literature focused on PET/SPECT radiotracers and to provide an overview of the conducted research within the past decade, with an additional focus on the novel radiopharmaceuticals developed for medical imaging.

Machine Learning Algorithms to Distinguish Myocardial Perfusion SPECT Polar Maps

Myocardial perfusion imaging (MPI) plays an important role in patients with suspected and documented coronary artery disease (CAD). Machine Learning (ML) algorithms have been developed for many medical applications with excellent performance. This study used ML algorithms to discern normal and abnormal gated Single Photon Emission Computed Tomography (SPECT) images. We analyzed one thousand and seven polar maps from a database of patients referred to a university hospital for clinically indicated MPI between January 2016 and December 2018. These studies were reported and evaluated by two different expert readers. The image features were extracted from a specific type of polar map segmentation based on horizontal and vertical slices. A senior expert reading was the comparator (gold standard). We used cross-validation to divide the dataset into training and testing subsets, using data augmentation in the training set, and evaluated 04 ML models. All models had accuracy >90% and area under the receiver operating characteristics curve (AUC) >0.80 except for Adaptive Boosting (AUC = 0.77), while all precision and sensitivity obtained were >96 and 92%, respectively. Random Forest had the best performance (AUC: 0.853; accuracy: 0,938; precision: 0.968; sensitivity: 0.963). ML algorithms performed very well in image classification. These models were capable of distinguishing polar maps remarkably into normal and abnormal.

Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure

Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical outcome in native liver survivor BA patients after KP. Twenty-four patients were evaluated according to clinical and laboratory data at initial evaluation (median follow-up = 9.7 years) after KP as having ideal (n = 15) or non-ideal (n = 9) medical outcomes. Patients were re-evaluated after an additional 4 years and classified in group 1 (n = 12) as stable and group 2 (n = 12) as non-stable in the disease course. Laboratory and quantitative imaging parameters were merged to test ML algorithms. Total and direct bilirubin (TB and DB), as laboratory parameters, and US stiffness, as an imaging parameter, were the only statistically significant parameters between the groups. The best algorithm in terms of accuracy, sensitivity, specificity, and AUCROC was naive Bayes algorithm, selecting only laboratory parameters (TB and DB). This preliminary ML analysis confirms the fundamental role of TB and DB values in predicting the long-term medical outcome for BA patients after KP, even though their values may be within the normal range. Physicians should be alert when TB and DB values change slightly.

Assessment of the routine reporting of very low-dose exercise-first myocardial perfusion SPECT from a large-scale real-world cohort and correlation with the subsequent reporting of coronary stenosis at angiography

PURPOSE

Our study assesses the routine reporting of exercise ischemia using very low-dose exercise-first myocardial perfusion SPECT in a large number of patients and under real-life conditions, by evaluating correlations with the subsequent routine reporting of coronary stenosis by angiography and with factors that predict ischemia.

METHODS

Data from 13,126 routine exercise MPI reports, from 11,952 patients (31% women), using very low doses of sestamibi and a high-sensitivity cardiac CZT camera, were extracted to assess the reporting of significant MPI-ischemia (> 1 left ventricular segment), to determine the MPI normalcy rate in a group with < 5% pretest probability of coronary artery disease (CAD) (n = 378), and to assess the ability of MPI to predict a > 50% coronary stenosis in patients with available coronary angiography reports in the 3 months after the MPI (n = 713).

RESULTS

The median effective patient dose was 2.51 [IQR: 1.00-4.71] mSv. The normalcy rate was 98%, and the MPI-ischemia rate was independently predicted by a known CAD, the male gender, obesity, and a < 50% LV ejection fraction, ranging from 29.5% with all these risk factors represented to 1.5% when there were no risk factors. A > 50% coronary stenosis was significantly predicted by MPI-ischemia, less significantly for mild (odds ratio [95% confidence interval]: 1.61 [1.26-1.96]) than for moderate-to-severe MPI-ischemia (4.05 [3.53-4.57]) and was also impacted by having a known CAD (2.17 [1.83-2.51]), by a submaximal exercise test (1.48 [1.15-1.81]) and being ≥ 65 years of age (1.43 [1.11-1.76]).

CONCLUSION

Ischemia detected using a very low-dose exercise-first MPI protocol in a large-scale clinical cohort and under real-life routine conditions is a highly significant predictor for the subsequent reporting of coronary stenosis, although this prediction is enhanced by other variables. This weakly irradiating approach is amenable to being repeated at shorter time intervals, in target patient groups with a high probability of MPI-ischemia.

Comparing the Prognostic Value of Stress Myocardial Perfusion Imaging by Conventional and Cadmium-Zinc Telluride Single-Photon Emission Computed Tomography through a Machine Learning Approach

We compared the prognostic value of myocardial perfusion imaging (MPI) by conventional- (C-) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride- (CZT-) SPECT in a cohort of patients with suspected or known coronary artery disease (CAD) using machine learning (ML) algorithms. A total of 453 consecutive patients underwent stress MPI by both C-SPECT and CZT-SPECT. The outcome was a composite end point of all-cause death, cardiac death, nonfatal myocardial infarction, or coronary revascularization procedures whichever occurred first. ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (KNN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for KNN) was greater than that of C-SPECT (88% for RF and 53% for KNN). A preliminary univariate analysis was performed through Mann-Whitney tests separately on the features of each camera in order to understand which ones could distinguish patients who will experience an adverse event from those who will not. Then, a machine learning analysis was performed by using Matlab (v. 2019b). Tree, KNN, support vector machine (SVM), Naïve Bayes, and RF were implemented twice: first, the analysis was performed on the as-is dataset; then, since the dataset was imbalanced (patients experiencing an adverse event were lower than the others), the analysis was performed again after balancing the classes through the Synthetic Minority Oversampling Technique. According to KNN and SVM with and without balancing the classes, the accuracy (p value = 0.02 and p value = 0.01) and recall (p value = 0.001 and p value = 0.03) of the CZT-SPECT were greater than those obtained by C-SPECT in a statistically significant way. ML approach showed that although the prognostic value of stress MPI by C-SPECT and CZT-SPECT is comparable, CZT-SPECT seems to have higher accuracy and recall.

Exploration of the efficacy of radiomics applied to left ventricular tomograms obtained from D-SPECT MPI for the auxiliary diagnosis of myocardial ischemia in CAD

To explore the feasibility and efficacy of radiomics with left ventricular tomograms obtained from D-SPECT myocardial perfusion imaging (MPI) for auxiliary diagnosis of myocardial ischemia in coronary artery disease (CAD). The images of 103 patients with CAD myocardial ischemia between September 2020 and April 2021 were retrospectively selected. After information desensitization processing, format conversion, annotation using the Labelme tool on an open-source platform, lesion classification, and establishment of a database, the images were cropped for analysis. The ResNet18 model was used to automate two steps (classification and segmentation) with five randomization, training and validation steps. The sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, positive predictive value, negative predictive value, Youden's index, agreement rate, and kappa value were calculated as evaluation indexes of the classification results for each training-validation step; then, receiver operating characteristics (ROC) curves were drawn, and the areas under the curve (AUCs) were calculated. The Dice coefficient, intersection over union, and Hausdorff distance were calculated as evaluation indexes of the segmentation results for each training-validation step; then, the predicted images were exported. Under the existing conditions, the radiomics model used in this study had an AUC above 0.95 in identifying the presence or absence of myocardial ischemia; in the prediction of the extent of myocardial ischemia, its evaluation index distribution is also close to that of the gold standard. Radiomics can be feasibly applied to left ventricular tomograms obtained from D-SPECT MPI for auxiliary diagnosis. With more in-depth research and the development of technology, adding this method to the existing auxiliary diagnosis will likely further improve the diagnostic accuracy and efficiency, and patients will therefore benefit.

Health technology assessment through the six sigma approach in abdominoplasty: Scalpel vs electrosurgery

Abdominoplasty is a surgical procedure conducted to reduce excess abdominal skin and fat and improve body contouring. Despite being commonly performed, it is associated with a risk of complications such as infection, seroma, haematoma and wound dehiscence. To reduce the incidence of complications, different methods are used to create the abdominal flap, i.e., incision with a scalpel or electrosurgery. In this study, health technology assessment (HTA) using the Six Sigma methodology was conducted to compare these incision techniques in patients undergoing abdominoplasty. Two consecutively enroled groups of patients (33 in the scalpel group and 35 in the electrosurgery group) who underwent surgery at a single institution, the University of Campania "Luigi Vanvitelli", were analysed using the drain output as the main outcome for comparison of the incision techniques. While no difference was found regarding haematoma or seroma formation (no cases in either group), the main results also indicate a greater drain output (p-value<0.001) and a greater incidence of dehiscence (p-value=0.056) in patients whose incisions were made through electrosurgery. The combination of HTA and the Six Sigma methodology was useful to prove the possible advantages of creating skin incisions with a scalpel in full abdominoplasty, particularly a significant reduction in the total drain output and a reduction in wound healing problems, namely, wound dehiscence, when compared with electrosurgery, despite considering two limited and heterogeneous groups.

Machine learning analysis: general features, requirements and cardiovascular applications

Artificial intelligence represents the science which will probably change the future of medicine by solving actually challenging issues. In this special article, the general features of machine learning are discussed. First, a background explanation regarding the division of artificial intelligence, machine learning and deep learning is given and a focus on the structure of machine learning subgroups is shown. The traditional process of a machine learning analysis is described, starting from the collection of data, across features engineering, modelling and till the validation and deployment phase. Due to the several applications of machine learning performed in literature in the last decades and the lack of some guidelines, the need of a standardization for reporting machine learning analysis results emerged. Some possible standards for reporting machine learning results are identified and discussed deeply; these are related to study population (number of subjects), repeatability of the analysis, validation, results, comparison with current practice. The way to the use of machine learning in clinical practice is open and the hope is that, with emerging technology and advanced digital and computational tools, available from hospitalization and subsequently after discharge, it will also be possible, with the help of increasingly powerful hardware, to build assistance strategies useful in clinical practice.

A Six Sigma DMAIC methodology as a support tool for Health Technology Assessment of two antibiotics

Health Technology Assessment (HTA) and Six Sigma (SS) have largely proved their reliability in the healthcare context. The former focuses on the assessment of health technologies to be introduced in a healthcare system. The latter deals with the improvement of the quality of services, reducing errors and variability in the healthcare processes. Both the approaches demand a detailed analysis, evidence-based decisions, and efficient control plans. In this paper, the SS is applied as a support tool for HTA of two antibiotics with the final aim of assessing their clinical and organizational impact in terms of postoperative Length Of Stay (LOS) for patients undergoing tongue cancer surgery. More specifically, the SS has been implemented through its main tool, namely the DMAIC (Define, Measure, Analyse, Improve, Control) cycle. Moreover, within the DMAIC cycle, a modelling approach based on a multiple linear regression analysis technique is introduced, in the Control phase, to add complementary information and confirm the results obtained by the statistical analysis performed within the other phases of the SS DMAIC. The obtained results show that the proposed methodology is effective to determine the clinical and organizational impact of each of the examined antibiotics, when LOS is taken as a measure of performance, and guide the decision-making process. Furthermore, our study provides a systematic procedure which, properly combining different and well-assessed tools available in the literature, demonstrated to be a useful guidance for choosing the right treatment based on the available data in the specific circumstance.

Machine learning to predict mortality after rehabilitation among patients with severe stroke

Stroke is among the leading causes of death and disability worldwide. Approximately 20–25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 1207 stroke patients with severe disability who completed rehabilitation and comparing the performance of ML algorithms to that of a standard logistic regression. The logistic regression model achieved an area under the Receiver Operating Characteristics curve (AUC) of 0.745 and was well calibrated. At the optimal risk threshold, the model had an accuracy of 75.7%, a positive predictive value (PPV) of 33.9%, and a negative predictive value (NPV) of 91.0%. The ML algorithm outperformed the logistic regression model through the implementation of synthetic minority oversampling technique and the Random Forests, achieving an AUC of 0.928 and an accuracy of 86.3%. The PPV was 84.6% and the NPV 87.5%. This study introduced a step forward in the creation of standardisable tools for predicting health outcomes in individuals affected by stroke.