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

2021 ◽  
Vol 22 (Supplement_3) ◽  
Author(s):  
K Okuda ◽  
K Nakajima ◽  
H Saito ◽  
S Yamashita ◽  
M Hashimoto ◽  
...  
Keyword(s):  
Heart Failure ◽  
Myocardial Perfusion ◽  
Single Photon ◽  
Photon Emission ◽  
Myocardial Perfusion Spect ◽  
Feature Reduction ◽  
Support Vector ◽  
Emission Computed Tomography ◽  
Operating Characteristics ◽  
Perfusion Spect

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.

scholarly journals Quantitative analysis of gated myocardial perfusion SPECT

2018 ◽  
pp. 220-227
Author(s):  
Victor Ploskikh ◽  
Elena Kotina
Keyword(s):  
Quantitative Analysis ◽  
Myocardial Perfusion ◽  
Data Processing ◽  
Single Photon ◽  
Photon Emission ◽  
Myocardial Perfusion Spect ◽  
Mathematical Representation ◽  
Emission Computed Tomography ◽  
Gated Myocardial Perfusion Spect ◽  
Perfusion Spect

The paper considers the problem of gated myocardial perfusion single photon emission computed tomography (SPECT) data processing. An approach to the quantitative analysis of gated myocardial perfusion SPECT data used in software developed in the SPbSU is presented. The article presents and formalizes the complete data processing workflow. All the main tasks of the data processing are considered. Mathematical representation of problem domain objects is presented. A detailed algorithm of the data processing is given. The algorithmis implemented as component of the data processing software suite.

scholarly journals Challenges of gated myocardial perfusion SPECT processing

2021 ◽  
pp. 171-177
Author(s):  
Victor Ploskikh ◽  
Elena Kotina
Keyword(s):  
Myocardial Perfusion ◽  
Single Photon ◽  
Photon Emission ◽  
Myocardial Perfusion Spect ◽  
Mathematical Representation ◽  
Emission Computed Tomography ◽  
Gated Myocardial Perfusion Spect ◽  
Myocardial Perfusion Single Photon ◽  
Perfusion Spect ◽  
Photon Emission Computed Tomography

The paper provides an in-depth look at gated myocardial perfusion single photon emission computed tomography (SPECT) data processing. Attention paid to several unmentioned subjects of the quantitative analysis of gated myocardial perfusion SPECT data. The article considers several options in the construction process of the ellipsoid coordinate system of the left ventricle (LV). Mathematical representation of polar maps is given. Formulas of the regional parameters calculation are proposed. Issues of phase analysis are explored.

scholarly journals Сравнительный анализ данных перфузионной сцинтиграфии миокарда у пациентов с поражением коронарных артерий различной степени выраженности

2019 ◽  
Author(s):  
E DENISENKO-KANKIYA ◽  
F.N. CHANAKHCHIAN ◽  
E.I. VASILENKO ◽  
M.N. VAKHROMEEVA
Keyword(s):  
Myocardial Perfusion ◽  
Single Photon ◽  
Photon Emission ◽  
Emission Computed Tomography ◽  
Vulnerable Atherosclerotic Plaque ◽  
Gated Perfusion Spect ◽  
Perfusion Spect ◽  
Perfusion Defects ◽  
Reversible Ischemia ◽  
Myocardial Perfusion Defects

Известно, что дестабилизация атеросклеротической бляшки коронарных артерий (КА) играет ключевую роль в развитии осложнений хронической ишемической болезни сердца (ИБС). Ранняя диагностика ишемии миокарда и определение субклинического стеноза КА с помощью неинвазивного метода визуализации сердца может стать важным методом в предотвращении развития сердечно-сосудистых осложнений у данной популяции больных. Цель исследования. Определить выраженность преходящих нарушений перфузии миокарда, выявленных при однофотонной эмиссионной компьютерной томографии (ОЭКТ) миокарда у пациентов со стенозами КА различной степени тяжести. Материал и методы. В исследование включен 231 пациент (средний возраст 6210лет). Проанализированы факторы кардиального риска. Всем пациентам проводили ОЭКТ миокарда по стандартному протоколу. Региональную перфузию миокарда оценивали с использованием стандартизированной 20-сегментной модели, на которой оценивали: SSS общий счет снижения перфузии миокарда при нагрузке SDS общую разницу счета, соответствующую степени выраженности преходящей ишемии левого желудочка (ЛЖ). На основании полученных данных обследуемых пациентов классифицировали на группы: с нормальной перфузией (SSS4), незначительной (SSS4-6), умеренной и выраженной степенью снижения (SSS712 и SSS13 соответственно) перфузии миокарда ЛЖ. Результаты SDS классифицировали как: отсутствие ишемии (SDS2), умеренная преходящая ишемия (SDS2-6) и выраженная преходящая ишемия (SDS7). Количественные показатели перфузии миокарда сравнивали с результатами инвазивной коронароангиографии (КАГ). Результаты. Из 231 пациента у 69 (29,9) по данным КАГ были выявлены стенозы до 20, у 126 (54,5) стенозы 2049, у 36 (15,6) стенозы 50 и более. Сравнительный анализ количественных показателей перфузии миокарда (SSS и SDS) и результатов КАГ показал, что достоверные дефекты перфузии после нагрузки и преходящая ишемия ЛЖ определены в основном у пациентов со стенозами КА50 (47,2 и 63,9 соответственно, р0,01). В группе пациентов с стенозами КА 2049 у 42,1 показатели SSS соответствовали незначительной (25,4) и умеренной (16,7) степени снижения перфузии после нагрузки (р0,01). При сопоставлении данных перфузионной сцинтиграфии миокарда выявлена связь между показателем SSS, наличием факторов риска и наличием сопутствующих заболеваний у пациентов с ИБС (р0,05). Заключение. Перфузионная ОЭКТ миокарда может использоваться в качестве метода выявления преходящей ишемии миокарда у пациентов со стенозами КА различной тяжести. Ключевые слова: ишемическая болезнь сердца, однофотонная эмиссионная компьютерная томография, перфузия миокарда, сцинтиграфия миокарда, необструктивное поражение, обструктивное поражение, коронароангиография.Vulnerable atherosclerotic plaque in coronary arteries (CA) is the primary mechanism responsible for complications of CAD even in the terms of non-obstructive CAD. Early determination of myocardial ischemia and CA stenosis with non-invasive imaging technique could predict the development of major cardiac events in patients with CAD. Aim: evaluation the severity of myocardial perfusion defects with single photon emission computed tomography (SPECT) in patients with obstructive or non-obstructive CAD. Material and methods: Overall 231patients (average age of 6210) were analyzed. All patients underwent 1-day gated perfusion SPECT protocol before coronary angiography (CAG). SPECT images were quantified by SSS and SDS using Cedars-Sinai QPS. Normal myocardial perfusion was considered if SSS4 mildly abnormal: SSS4-7 moderate and significantly abnormal: SSS8-12 and SSS13, respectively. Reversible ischemia was defined as SDS2. Degree of ischemia was assessed to moderate (SDS2-7) and severe (SDS7). Obstructive CAD was defined as 50 stenosis in 1 vessel on CAG. Results: From 231 patients 69 (29,9) have non-significant CA stenosis (20), 126 (54,5) have non-obstructive CAD (20-49) and 36 (15,6) - obstructive CAD (50). There were significant differences between CA stenosis severity via CAG and SSS via SPECT. In obstructive CAD significant myocardial perfusion defect at stress (SSS) and reversible ischemia (SDS) were observed in 47,2 and 63,9 patients, respectively (p0,01). In patients with non-obstructive CAD although the majority has normal myocardial perfusion in stress (SSS4 55,6), 42,1 has both mild (25,4) and moderate (16,7) myocardial perfusion defects in stress (p0,001). In this subgroup 45,2 of patients have moderate and 18,3 - severe reversible ischemia according to SDS (p0,001). Abnormal perfusion in stress was associated with hazards of cardiac risk factors or associated diseases (p0,05). Conclusion: Perfusion SPECT has a prognostic value over invasive CAG. The addition SPECT quantitative analysis to CAG allows improved risk stratification of patients with non-obstructive CAD.

Nuclear cardiology: state of the art

Heart ◽  
2021 ◽  
pp. heartjnl-2019-315628
Author(s):  
Rebecca Schofield ◽  
Leon Menezes ◽  
Stephen Richard Underwood
Keyword(s):  
Heart Failure ◽  
Myocardial Perfusion ◽  
Radionuclide Imaging ◽  
Single Photon ◽  
Imaging Techniques ◽  
Sympathetic Innervation ◽  
Photon Emission ◽  
Myocardial Inflammation ◽  
Emission Computed Tomography ◽  
Device Infection

Radionuclide imaging remains an essential component of modern cardiology. There is overlap with the information from other imaging techniques, but no technique is static and new developments have expanded its role. This review focuses on ischaemic heart disease, heart failure, infection and inflammation. Radiopharmaceutical development includes the wider availability of positron emission tomography (PET) tracers such as rubidium-82, which allows myocardial perfusion to be quantified in absolute terms. Compared with alternative techniques, myocardial perfusion scintigraphy PET and single photon emission computed tomography (SPECT) have the advantages of being widely applicable using exercise or pharmacological stress, full coverage of the myocardium and a measure of ischaemic burden, which helps to triage patients between medical therapy and revascularisation. Disadvantages include the availability of expertise in some cardiac centres and the lack of simple SPECT quantification, meaning that global abnormalities can be underestimated. In patients with heart failure, despite the findings of the STICH (Surgical Treatment for Ischemic Heart Failure) trial, there are still data to support the assessment of myocardial hibernation in predicting when abolition of ischaemia might lead to improvement in ventricular function. Imaging of sympathetic innervation is well validated, but simpler markers of prognosis mean that it has not been widely adopted. There are insufficient data to support its use in predicting the need for implanted devices, but non-randomised studies are promising. Other areas where radionuclide imaging is uniquely valuable are detection and monitoring of endocarditis, device infection, myocardial inflammation in sarcoidosis, myocarditis and so on, and reliable detection of deposition in suspected transthyretin-related amyloidosis.

scholarly journals Machine learning predicts per-vessel early coronary revascularization after fast myocardial perfusion SPECT: results from multicentre REFINE SPECT registry

2019 ◽  
Vol 21 (5) ◽  
pp. 549-559 ◽  
Author(s):  
Lien-Hsin Hu ◽  
Julian Betancur ◽  
Tali Sharir ◽  
Andrew J Einstein ◽  
Sabahat Bokhari ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Perfusion ◽  
Single Photon ◽  
Coronary Revascularization ◽  
Stress Test ◽  
Invasive Coronary Angiography ◽  
Photon Emission ◽  
Myocardial Perfusion Spect ◽  
Patient Specific ◽  
Emission Computed Tomography

Abstract Aims To optimize per-vessel prediction of early coronary revascularization (ECR) within 90 days after fast single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) using machine learning (ML) and introduce a method for a patient-specific explanation of ML results in a clinical setting. Methods and results A total of 1980 patients with suspected coronary artery disease (CAD) underwent stress/rest 99mTc-sestamibi/tetrofosmin MPI with new-generation SPECT scanners were included. All patients had invasive coronary angiography within 6 months after SPECT MPI. ML utilized 18 clinical, 9 stress test, and 28 imaging variables to predict per-vessel and per-patient ECR with 10-fold cross-validation. Area under the receiver operator characteristics curve (AUC) of ML was compared with standard quantitative analysis [total perfusion deficit (TPD)] and expert interpretation. ECR was performed in 958 patients (48%). Per-vessel, the AUC of ECR prediction by ML (AUC 0.79, 95% confidence interval (CI) [0.77, 0.80]) was higher than by regional stress TPD (0.71, [0.70, 0.73]), combined-view stress TPD (AUC 0.71, 95% CI [0.69, 0.72]), or ischaemic TPD (AUC 0.72, 95% CI [0.71, 0.74]), all P < 0.001. Per-patient, the AUC of ECR prediction by ML (AUC 0.81, 95% CI [0.79, 0.83]) was higher than that of stress TPD, combined-view TPD, and ischaemic TPD, all P < 0.001. ML also outperformed nuclear cardiologists’ expert interpretation of MPI for the prediction of early revascularization performance. A method to explain ML prediction for an individual patient was also developed. Conclusion In patients with suspected CAD, the prediction of ECR by ML outperformed automatic MPI quantitation by TPDs (per-vessel and per-patient) or nuclear cardiologists’ expert interpretation (per-patient).

scholarly journals Machine Learning Algorithms to Distinguish Myocardial Perfusion SPECT Polar Maps

2021 ◽  
Vol 8 ◽  
Author(s):  
Erito Marques de Souza Filho ◽  
Fernando de Amorim Fernandes ◽  
Christiane Wiefels ◽  
Lucas Nunes Dalbonio de Carvalho ◽  
Tadeu Francisco dos Santos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Perfusion ◽  
Single Photon ◽  
Photon Emission ◽  
Image Features ◽  
Machine Learning Algorithms ◽  
University Hospital ◽  
Emission Computed Tomography ◽  
Operating Characteristics ◽  
Adaptive Boosting

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.

scholarly journals Impact of iterative reconstruction with resolution recovery in myocardial perfusion SPECT: phantom and clinical studies

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Koichi Okuda ◽  
Kenichi Nakajima ◽  
Hiroto Yoneyama ◽  
Takayuki Shibutani ◽  
Masahisa Onoguchi ◽  
...  
Keyword(s):  
Myocardial Perfusion ◽  
Iterative Reconstruction ◽  
Clinical Studies ◽  
Photon Emission ◽  
Myocardial Perfusion Spect ◽  
Correction Method ◽  
Emission Computed Tomography ◽  
Variable Depth ◽  
Clinical Patient ◽  
Perfusion Spect

AbstractThe corrections of photon attenuation, scatter, and depth-dependent blurring improve image quality in myocardial perfusion single-photon emission computed tomography (SPECT) imaging; however, the combined corrections induce artifacts. Here, we present the single correction method of depth-dependent blurring and its impact for myocardial perfusion distribution in phantom and clinical studies. The phantom and clinical patient images were acquired with two conditions: circular and noncircular orbits of gamma cameras yielded constant and variable depth-dependent blurring, respectively. An iterative reconstruction with the correction method of depth-dependent was used to reconstruct the phantom and clinical patient images. We found that the single correction method improved the robustness of phantom images whether the images contained constant or variable depth-dependent blurring. The myocardial perfusion databases generated from 72 normal patients exhibited uniform perfusion distribution of whole myocardium. In summary, the single correction method of depth-dependent blurring with iterative reconstruction is helpful for myocardial perfusion SPECT.

Heart failure

ESC CardioMed ◽  
2018 ◽  
pp. 600-603
Author(s):  
Danilo Neglia ◽  
Oliver Gaemperli
Keyword(s):  
Heart Failure ◽  
Myocardial Perfusion ◽  
Radionuclide Imaging ◽  
Single Photon ◽  
Photon Emission ◽  
Treatment Strategies ◽  
Radionuclide Ventriculography ◽  
Myocardial Perfusion Spect ◽  
Emission Tomography ◽  
Positron Emission

Heart failure (HF) has turned into an increasing global socioeconomic issue associated with a high morbidity and mortality. Cardiac radionuclide imaging offers important clinical information for risk stratification and tailored treatment strategies in patients with HF. Ischaemic cardiomyopathy is the most common cause of HF. Left and right ventricular function can be assessed and quantified with radionuclide ventriculography (RNV) or gated scintigraphic studies. Additionally, radionuclide imaging may help to assess functional and metabolic integrity of dysfunctional myocardium. Chronic myocardial ischaemia can lead to variable reversible states of contractile impairment termed myocardial stunning or hibernation. Radionuclide techniques including positron emission tomography with 18F-fluorodeoxyglucose or myocardial perfusion scintigraphy can identify viable myocardium with the potential for functional recovery, and thereby guide revascularization procedures. Increased sympathetic myocardial innervation assessed by 131I-metaiodobenzylguanidine (MIBG) single-photon emission tomography (SPECT) is associated with poorer HF outcomes and higher rates of sudden cardiac death or arrhythmia. Finally, left ventricular mechanical dyssynchrony can be evaluated using Fourier-transformed phase analysis of RNV or gated myocardial perfusion SPECT. This approach could potentially be useful to guide targeted resynchronization therapy in the future.

Sign in / Sign up

Export Citation Format

Share Document