ABSTRACT
Chest computed tomography is one of the most common diagnostic tests, with 15 million scans performed annually in the United States. Coronary calcium can be visualized on these scans, but other measures of cardiac risk such as atrial and ventricular volumes have classically required administration of contrast. Here we show that a fully automated pipeline, incorporating two artificial intelligence models, automatically quantifies coronary calcium, left atrial volume, left ventricular mass, and other cardiac chamber volumes in 29,687 patients from three cohorts. The model processes chamber volumes and coronary artery calcium with an end-to-end time of ~18 s, while failing to segment only 0.1% of cases. Coronary calcium, left atrial volume, and left ventricular mass index are independently associated with all-cause and cardiovascular mortality and significantly improve risk classification compared to identification of abnormalities by a radiologist. This automated approach can be integrated into clinical workflows to improve identification of abnormalities and risk stratification, allowing physicians to improve clinical decision-making.
Subject(s)
Calcium , Cardiac Volume , Humans , Heart Ventricles , Artificial Intelligence , Tomography, X-Ray Computed/methodsABSTRACT
BACKGROUND: Myocardial perfusion imaging (MPI) is one of the most common cardiac scans and is used for diagnosis of coronary artery disease and assessment of cardiovascular risk. However, the large majority of MPI patients have normal results. We evaluated whether unsupervised machine learning could identify unique phenotypes among patients with normal scans and whether those phenotypes were associated with risk of death or myocardial infarction. METHODS: Patients from a large international multicenter MPI registry (10 sites) with normal perfusion by expert visual interpretation were included in this cohort analysis. The training population included 9849 patients, and external testing population 12,528 patients. Unsupervised cluster analysis was performed, with separate training and external testing cohorts, to identify clusters, with four distinct phenotypes. We evaluated the clinical and imaging features of clusters and their associations with death or myocardial infarction. FINDINGS: Patients in Clusters 1 and 2 almost exclusively underwent exercise stress, while patients in Clusters 3 and 4 mostly required pharmacologic stress. In external testing, the risk for Cluster 4 patients (20.2% of population, unadjusted hazard ratio [HR] 6.17, 95% confidence interval [CI] 4.64-8.20) was higher than the risk associated with pharmacologic stress (HR 3.03, 95% CI 2.53-3.63), or previous myocardial infarction (HR 1.82, 95% CI 1.40-2.36). INTERPRETATION: Unsupervised learning identified four distinct phenotypes of patients with normal perfusion scans, with a significant proportion of patients at very high risk of myocardial infarction or death. Our results suggest a potential role for patient phenotyping to improve risk stratification of patients with normal imaging results. FUNDING: This work was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R35HL161195 to PS]. The REFINE SPECT database was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R01HL089765 to PS]. MCW was supported by the British Heart Foundation [FS/ICRF/20/26002].
Subject(s)
Coronary Artery Disease , Myocardial Infarction , Humans , Coronary Artery Disease/diagnostic imaging , Myocardial Infarction/diagnostic imaging , Myocardial Infarction/etiology , Perfusion , Prognosis , Risk Factors , Unsupervised Machine Learning , Retrospective StudiesABSTRACT
We investigated the prognostic utility of visually estimated coronary artery calcification (VECAC) from low dose computed tomography attenuation correction (CTAC) scans obtained during SPECT/CT myocardial perfusion imaging (MPI), and assessed how it compares to coronary artery calcifications (CAC) quantified by calcium score on CTACs (QCAC). From the REFINE SPECT Registry 4,236 patients without prior coronary stenting with SPECT/CT performed at a single center were included (age: 64 ± 12 years, 47% female). VECAC in each coronary artery (left main, left anterior descending, circumflex, and right) were scored separately as 0 (absent), 1 (mild), 2 (moderate), or 3 (severe), yielding a possible score of 0-12 for each patient (overall VECAC grade zero:0, mild:1-2, moderate: 3-5, severe: >5). CAC scoring of CTACs was performed at the REFINE SPECT core lab with dedicated software. VECAC was correlated with categorized QCAC (zero: 0, mild: 1-99, moderate: 100-399, severe: ≥400). A high degree of correlation was observed between VECAC and QCAC, with 73% of VECACs in the same category as QCAC and 98% within one category. There was substantial agreement between VECAC and QCAC (weighted kappa: 0.78 with 95% confidence interval: 0.76-0.79, p < 0.001). During a median follow-up of 25 months, 372 patients (9%) experienced major adverse cardiovascular events (MACE). In survival analysis, both VECAC and QCAC were associated with MACE. The area under the receiver operating characteristic curve for 2-year-MACE was similar for VECAC when compared to QCAC (0.694 versus 0.691, p = 0.70). In conclusion, visual assessment of CAC on low-dose CTAC scans provides good estimation of QCAC in patients undergoing SPECT/CT MPI. Visually assessed CAC has similar prognostic value for MACE in comparison to QCAC.
Subject(s)
Calcinosis , Coronary Artery Disease , Myocardial Perfusion Imaging , Humans , Female , Middle Aged , Aged , Male , Myocardial Perfusion Imaging/methods , Prognosis , Predictive Value of Tests , Tomography, Emission-Computed, Single-Photon/methods , Coronary Artery Disease/diagnostic imaging , Tomography, X-Ray Computed/methodsABSTRACT
PURPOSE: This study aimed to compare the predictive value of CT attenuation-corrected stress total perfusion deficit (AC-sTPD) and non-corrected stress TPD (NC-sTPD) for major adverse cardiac events (MACE) in obese patients undergoing cadmium zinc telluride (CZT) SPECT myocardial perfusion imaging (MPI). METHODS: The study included 4,585 patients who underwent CZT SPECT/CT MPI for clinical indications (chest pain: 56%, shortness of breath: 13%, other: 32%) at Yale New Haven Hospital (age: 64 ± 12 years, 45% female, body mass index [BMI]: 30.0 ± 6.3 kg/m2, prior coronary artery disease: 18%). The association between AC-sTPD or NC-sTPD and MACE defined as the composite end point of mortality, nonfatal myocardial infarction or late coronary revascularization (> 90 days after SPECT) was evaluated with survival analysis. RESULTS: During a median follow-up of 25 months, 453 patients (10%) experienced MACE. In patients with BMI ≥ 35 kg/m2 (n = 931), those with AC-sTPD ≥ 3% had worse MACE-free survival than those with AC-sTPD < 3% (HR: 2.23, 95% CI: 1.40 - 3.55, p = 0.002) with no difference in MACE-free survival between patients with NC-sTPD ≥ 3% and NC-sTPD < 3% (HR:1.06, 95% CI:0.67 - 1.68, p = 0.78). AC-sTPD had higher AUC than NC-sTPD for the detection of 2-year MACE in patients with BMI ≥ 35 kg/m2 (0.631 versus 0.541, p = 0.01). In the overall cohort AC-sTPD had a higher ROC area under the curve (AUC, 0.641) than NC-sTPD (0.608; P = 0.01) for detection of 2-year MACE. In patients with BMI ≥ 35 kg/m2 AC sTPD provided significant incremental prognostic value beyond NC sTPD (net reclassification index: 0.14 [95% CI: 0.20 - 0.28]). CONCLUSIONS: AC sTPD outperformed NC sTPD in predicting MACE in patients undergoing SPECT MPI with BMI ≥ 35 kg/m2. These findings highlight the superior prognostic value of AC-sTPD in this patient population and underscore the importance of CT attenuation correction.
Subject(s)
Coronary Artery Disease , Myocardial Infarction , Myocardial Perfusion Imaging , Humans , Female , Middle Aged , Aged , Male , Coronary Artery Disease/complications , Coronary Artery Disease/diagnostic imaging , Tomography, Emission-Computed, Single-Photon/methods , Myocardial Perfusion Imaging/methods , Tomography, X-Ray Computed , Prognosis , Obesity/complications , Obesity/diagnostic imagingABSTRACT
AIMS: Transoesophageal echocardiography (TOE) is often performed before catheter ablation or cardioversion to rule out the presence of left atrial appendage thrombus (LAT) in patients on chronic oral anticoagulation (OAC), despite associated discomfort. A machine learning model [LAT-artificial intelligence (AI)] was developed to predict the presence of LAT based on clinical and transthoracic echocardiography (TTE) features. METHODS AND RESULTS: Data from a 13-site prospective registry of patients who underwent TOE before cardioversion or catheter ablation were used. LAT-AI was trained to predict LAT using data from 12 sites (n = 2827) and tested externally in patients on chronic OAC from two sites (n = 1284). Areas under the receiver operating characteristic curve (AUC) of LAT-AI were compared with that of left ventricular ejection fraction (LVEF) and CHA2DS2-VASc score. A decision threshold allowing for a 99% negative predictive value was defined in the development cohort. A protocol where TOE in patients on chronic OAC is performed depending on the LAT-AI score was validated in the external cohort. In the external testing cohort, LAT was found in 5.5% of patients. LAT-AI achieved an AUC of 0.85 [95% confidence interval (CI): 0.82-0.89], outperforming LVEF (0.81, 95% CI 0.76-0.86, P < .0001) and CHA2DS2-VASc score (0.69, 95% CI: 0.63-0.7, P < .0001) in the entire external cohort. Based on the proposed protocol, 40% of patients on chronic OAC from the external cohort would safely avoid TOE. CONCLUSION: LAT-AI allows accurate prediction of LAT. A LAT-AI-based protocol could be used to guide the decision to perform TOE despite chronic OAC.
Subject(s)
Atrial Appendage , Atrial Fibrillation , Heart Diseases , Thrombosis , Humans , Echocardiography, Transesophageal/methods , Atrial Appendage/diagnostic imaging , Stroke Volume , Artificial Intelligence , Atrial Fibrillation/complications , Ventricular Function, Left , Echocardiography , Heart Diseases/diagnosis , Thrombosis/diagnosis , Risk FactorsABSTRACT
(1) Background: Assessment of cognitive function is not routine in cardiac patients, and knowledge on the subject remains limited. The aim of this study was to assess post-myocardial infarction (MI) cognitive functioning in order to determine the frequency of cognitive impairment (CI) and to identify factors that may influence it. (2) Methods: A prospective study included 468 patients hospitalized for MI. Participants were assessed twice: during the first hospitalization and 6 months later. The Mini-Mental State Examination was used to assess the occurrence of CI. (3) Results: Cognitive dysfunction based on the MMSE was found in 37% (N-174) of patients during the first hospitalization. After 6 months, the prevalence of deficits decreased significantly to 25% (N-91) (p < 0.001). Patients with CI significantly differed from those without peri-infarction deficits in the GFR, BNP, ejection fraction and SYNTAX score, while after 6 months, significant differences were observed in LDL and HCT levels. There was a high prevalence of non-cognitive mental disorders among post-MI patients. (4) Conclusions: There is a high prevalence of CI and other non-cognitive mental disorders, such as depression, sleep disorders and a tendency to aggression, among post-MI patients. The analysis of the collected material indicates a significant impact of worse cardiac function expressed as EF and BNP, greater severity of coronary atherosclerosis expressed by SYNTAX results, and red blood cell parameters and LDL levels on the occurrence of CI in the post-MI patient population.
ABSTRACT
In this review, we summarize state-of-the-art artificial intelligence applications for non-invasive cardiovascular imaging modalities including CT, MRI, echocardiography, and nuclear myocardial perfusion imaging.
ABSTRACT
Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.
ABSTRACT
PURPOSE: Patients with known coronary artery disease (CAD) comprise a heterogenous population with varied clinical and imaging characteristics. Unsupervised machine learning can identify new risk phenotypes in an unbiased fashion. We use cluster analysis to risk-stratify patients with known CAD undergoing single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). METHODS: From 37,298 patients in the REFINE SPECT registry, we identified 9221 patients with known coronary artery disease. Unsupervised machine learning was performed using clinical (23), acquisition (17), and image analysis (24) parameters from 4774 patients (internal cohort) and validated with 4447 patients (external cohort). Risk stratification for all-cause mortality was compared to stress total perfusion deficit (< 5%, 5-10%, ≥10%). RESULTS: Three clusters were identified, with patients in Cluster 3 having a higher body mass index, more diabetes mellitus and hypertension, and less likely to be male, have dyslipidemia, or undergo exercise stress imaging (p < 0.001 for all). In the external cohort, during median follow-up of 2.6 [0.14, 3.3] years, all-cause mortality occurred in 312 patients (7%). Cluster analysis provided better risk stratification for all-cause mortality (Cluster 3: hazard ratio (HR) 5.9, 95% confidence interval (CI) 4.0, 8.6, p < 0.001; Cluster 2: HR 3.3, 95% CI 2.5, 4.5, p < 0.001; Cluster 1, reference) compared to stress total perfusion deficit (≥10%: HR 1.9, 95% CI 1.5, 2.5 p < 0.001; < 5%: reference). CONCLUSIONS: Our unsupervised cluster analysis in patients with known CAD undergoing SPECT MPI identified three distinct phenotypic clusters and predicted all-cause mortality better than ischemia alone.
Subject(s)
Coronary Artery Disease , Myocardial Perfusion Imaging , Male , Female , Humans , Coronary Artery Disease/diagnostic imaging , Myocardial Perfusion Imaging/methods , Unsupervised Machine Learning , Tomography, Emission-Computed, Single-Photon/methods , Exercise Test/methods , PrognosisABSTRACT
PURPOSE: An important aspect in the prevention and treatment of coronary artery disease is the functional evaluation of narrowed blood vessels. Medical image-based Computational Fluid Dynamic methods are currently increasingly being used in the clinical setting for flow studies of cardio vascular system. The aim of our study was to confirm the feasibility and functionality of a non-invasive computational method providing information about hemodynamic significance of coronary stenosis. METHODS: A comparative method was used to simulate the flow energy losses in real (stenotic) and reconstructed models without (reference) stenosis of the coronary arteries under stress test conditions, i.e. for maximum blood flow and minimal, constant vascular resistance. In addition to the absolute pressure drop in the stenotic arteries (FFRsten) and in the reconstructed arteries (FFRrec), a new energy flow reference index (EFR) was also defined, which expresses the total pressure changes caused by stenosis in relation to the pressure changes in normal coronary arteries, which also allows a separate assessment of the haemodynamic significance of the atherosclerotic lesion itself. The article presents the results obtained from flow simulations in coronary arteries, reconstructed on the basis of 3D segmentation of cardiac CT images of 25 patients from retrospective data collection, with different degrees of stenoses and different areas of their occurrence. RESULTS: The greater the degree of narrowing of the vessel, the greater drop of flow energy. Each parameter introduces an additional diagnostic value. In contrast to FFRsten, the EFR indices that are calculated on the basis of a comparison of stenosed and reconstructed models, are associated directly with localization, shape and geometry of stenosis only. Both FFRsten and EFR showed very significant positive correlation (P < 0.0001) with coronary CT angiography-derived FFR, with a correlation coefficient of 0.8805 and 0.9011 respectively. CONCLUSION: The study presented promising results of non-invasive, comparative test to support of prevention of coronary disease and functional evaluation of stenosed vessels.
Subject(s)
Coronary Artery Disease , Coronary Stenosis , Fractional Flow Reserve, Myocardial , Humans , Computed Tomography Angiography , Constriction, Pathologic , Retrospective Studies , Coronary Artery Disease/diagnostic imaging , Tomography, X-Ray Computed , Coronary Angiography/methods , Hemodynamics , Coronary Vessels/diagnostic imagingABSTRACT
BACKGROUND: Breast cancer remains the most common nonskin cancer among women. Prophylactic methods for reducing surgical-site complications after immediate breast reconstruction (IBR) are crucial to prevent acellular dermal matrices or prosthesis exposure and loss. The authors assessed the impact of closed-incision negative-pressure wound therapy (ciNPWT) versus standard dressings (ST) after IBR on surgical-site complications, superficial skin temperature (SST), skin elasticity, and subjective scar quality, to determine the potential benefit of prophylactic ciNPWT application. METHODS: A multicenter randomized controlled study of 60 adult female patients was conducted between January of 2019 and July of 2021. All patients had oncologic indications for IBR using implants or expanders. RESULTS: Application of ciNPWT correlated with a significant decrease in surgical-site complications within 1 year of surgery (total, 40%; ST, 60%; ciNPWT, 20%; P = 0.003) and resulted in more elastic scar tissue as measured with a Cutometer (average coefficient of elasticity, 0.74; ST, 0.7; ciNPWT, 0.9; P < 0.001). The SST of each scar 1 week after surgery was significantly higher in the ciNPWT group (average SST, 31.5; ST SST, 31.2; ciNPWT SST, 32.3; P = 0.006). According to the Patient and Observer Scar Assessment Scale v2.0, subjective scar outcomes in both groups were comparable. CONCLUSIONS: This is the first randomized controlled study that demonstrated a significant decrease in surgical-site wound complications within 1 year of surgery in IBR patients receiving ciNPWT. A high probability of postoperative radiotherapy should be a relative indication for the use of ciNPWT. . CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, II.
Subject(s)
Breast Neoplasms , Mammaplasty , Negative-Pressure Wound Therapy , Surgical Wound , Adult , Humans , Female , Cicatrix/prevention & control , Cicatrix/complications , Negative-Pressure Wound Therapy/methods , Surgical Wound/therapy , Surgical Wound/complications , Surgical Wound Infection/prevention & control , Mammaplasty/adverse effects , Mammaplasty/methods , Breast Neoplasms/surgery , Breast Neoplasms/complicationsABSTRACT
AIMS: Prediction of adverse events in mid-term follow-up after transcatheter aortic valve implantation (TAVI) is challenging. We sought to develop and validate a machine learning model for prediction of 1-year all-cause mortality in patients who underwent TAVI and were discharged following the index procedure. METHODS AND RESULTS: The model was developed on data of patients who underwent TAVI at a high-volume centre between January 2013 and March 2019. Machine learning by extreme gradient boosting was trained and tested with repeated 10-fold hold-out testing using 34 pre- and 25 peri-procedural clinical variables. External validation was performed on unseen data from two other independent high-volume TAVI centres. Six hundred four patients (43% men, 81 ± 5 years old, EuroSCORE II 4.8 [3.0-6.3]%) in the derivation and 823 patients (46% men, 82 ± 5 years old, EuroSCORE II 4.7 [2.9-6.0]%) in the validation cohort underwent TAVI and were discharged home following the index procedure. Over the 12 months of follow-up, 68 (11%) and 95 (12%) subjects died in the derivation and validation cohorts, respectively. In external validation, the machine learning model had an area under the receiver-operator curve of 0.82 (0.78-0.87) for prediction of 1-year all-cause mortality following hospital discharge after TAVI, which was superior to pre- and peri-procedural clinical variables including age 0.52 (0.46-0.59) and the EuroSCORE II 0.57 (0.51-0.64), P < 0.001 for a difference. CONCLUSION: Machine learning based on readily available clinical data allows accurate prediction of 1-year all-cause mortality following a successful TAVI.
Subject(s)
Aortic Valve Stenosis , Transcatheter Aortic Valve Replacement , Male , Humans , Infant , Aged , Aged, 80 and over , Female , Transcatheter Aortic Valve Replacement/adverse effects , Aortic Valve/surgery , Aortic Valve Stenosis/surgeryABSTRACT
To improve diagnostic accuracy, myocardial perfusion imaging (MPI) SPECT studies can use CT-based attenuation correction (AC). However, CT-based AC is not available for most SPECT systems in clinical use, increases radiation exposure, and is impacted by misregistration. We developed and externally validated a deep-learning model to generate simulated AC images directly from non-AC (NC) SPECT, without the need for CT. Methods: SPECT myocardial perfusion imaging was performed using 99mTc-sestamibi or 99mTc-tetrofosmin on contemporary scanners with solid-state detectors. We developed a conditional generative adversarial neural network that applies a deep learning model (DeepAC) to generate simulated AC SPECT images. The model was trained with short-axis NC and AC images performed at 1 site (n = 4,886) and was tested on patients from 2 separate external sites (n = 604). We assessed the diagnostic accuracy of the stress total perfusion deficit (TPD) obtained from NC, AC, and DeepAC images for obstructive coronary artery disease (CAD) with area under the receiver-operating-characteristic curve. We also quantified the direct count change among AC, NC, and DeepAC images on a per-voxel basis. Results: DeepAC could be obtained in less than 1 s from NC images; area under the receiver-operating-characteristic curve for obstructive CAD was higher for DeepAC TPD (0.79; 95% CI, 0.72-0.85) than for NC TPD (0.70; 95% CI, 0.63-0.78; P < 0.001) and similar to AC TPD (0.81; 95% CI, 0.75-0.87; P = 0.196). The normalcy rate in the low-likelihood-of-coronary-disease population was higher for DeepAC TPD (70.4%) and AC TPD (75.0%) than for NC TPD (54.6%, P < 0.001 for both). The positive count change (increase in counts) was significantly higher for AC versus NC (median, 9.4; interquartile range, 6.0-14.2; P < 0.001) than for AC versus DeepAC (median, 2.4; interquartile range, 1.3-4.2). Conclusion: In an independent external dataset, DeepAC provided improved diagnostic accuracy for obstructive CAD, as compared with NC images, and this accuracy was similar to that of actual AC. DeepAC simplifies the task of artifact identification for physicians, avoids misregistration artifacts, and can be performed rapidly without the need for CT hardware and additional acquisitions.
Subject(s)
Coronary Artery Disease , Deep Learning , Myocardial Perfusion Imaging , Humans , Sensitivity and Specificity , Tomography, Emission-Computed, Single-Photon/methods , Coronary Artery Disease/diagnostic imaging , ROC Curve , Myocardial Perfusion Imaging/methodsABSTRACT
Low-dose ungated CT attenuation correction (CTAC) scans are commonly obtained with SPECT/CT myocardial perfusion imaging. Despite the characteristically low image quality of CTAC, deep learning (DL) can potentially quantify coronary artery calcium (CAC) from these scans in an automatic manner. We evaluated CAC quantification derived with a DL model, including correlation with expert annotations and associations with major adverse cardiovascular events (MACE). Methods: We trained a convolutional long short-term memory DL model to automatically quantify CAC on CTAC scans using 6,608 studies (2 centers) and evaluated the model in an external cohort of patients without known coronary artery disease (n = 2,271) obtained in a separate center. We assessed agreement between DL and expert annotated CAC scores. We also assessed associations between MACE (death, revascularization, myocardial infarction, or unstable angina) and CAC categories (0, 1-100, 101-400, or >400) for scores manually derived by experienced readers and scores obtained fully automatically by DL using multivariable Cox models (adjusted for age, sex, past medical history, perfusion, and ejection fraction) and net reclassification index. Results: In the external testing population, DL CAC was 0 in 908 patients (40.0%), 1-100 in 596 (26.2%), 100-400 in 354 (15.6%), and >400 in 413 (18.2%). Agreement in CAC category by DL CAC and expert annotation was excellent (linear weighted κ, 0.80), but DL CAC was obtained automatically in less than 2 s compared with about 2.5 min for expert CAC. DL CAC category was an independent risk factor for MACE with hazard ratios in comparison to a CAC of zero: CAC of 1-100 (2.20; 95% CI, 1.54-3.14; P < 0.001), CAC of 101-400 (4.58; 95% CI, 3.23-6.48; P < 0.001), and CAC of more than 400 (5.92; 95% CI, 4.27-8.22; P < 0.001). Overall, the net reclassification index was 0.494 for DL CAC, which was similar to expert annotated CAC (0.503). Conclusion: DL CAC from SPECT/CT attenuation maps agrees well with expert CAC annotations and provides a similar risk stratification but can be obtained automatically. DL CAC scores improved classification of a significant proportion of patients as compared with SPECT myocardial perfusion alone.
Subject(s)
Coronary Artery Disease , Deep Learning , Humans , Coronary Artery Disease/diagnostic imaging , Calcium , Single Photon Emission Computed Tomography Computed Tomography/adverse effects , Tomography, Emission-Computed, Single-Photon , Risk Factors , Coronary Angiography/adverse effectsABSTRACT
BACKGROUND: Assessment of coronary artery calcium (CAC) by computed tomographic (CT) imaging provides an accurate measure of atherosclerotic burden. CAC is also visible in computed tomographic attenuation correction (CTAC) scans, always acquired with cardiac positron emission tomographic (PET) imaging. OBJECTIVES: The aim of this study was to develop a deep-learning (DL) model capable of fully automated CAC definition from PET CTAC scans. METHODS: The novel DL model, originally developed for video applications, was adapted to rapidly quantify CAC. The model was trained using 9,543 expert-annotated CT scans and was tested in 4,331 patients from an external cohort undergoing PET/CT imaging with major adverse cardiac events (MACEs) (follow-up 4.3 years), including same-day paired electrocardiographically gated CAC scans available in 2,737 patients. MACE risk stratification in 4 CAC score categories (0, 1-100, 101-400, and >400) was analyzed and CAC scores derived from electrocardiographically gated CT scans (standard scores) by expert observers were compared with automatic DL scores from CTAC scans. RESULTS: Automatic DL scoring required <6 seconds per scan. DL CTAC scores provided stepwise increase in the risk for MACE across the CAC score categories (HR up to 3.2; P < 0.001). Net reclassification improvement of standard CAC scores over DL CTAC scores was nonsignificant (-0.02; 95% CI: -0.11 to 0.07). The negative predictive values for MACE of zero CAC with standard (85%) and DL CTAC (83%) CAC scores were similar (P = 0.19). CONCLUSIONS: DL CTAC scores predict cardiovascular risk similarly to standard CAC scores quantified manually by experienced operators from dedicated electrocardiographically gated CAC scans and can be obtained almost instantly, with no changes to PET/CT scanning protocol.
Subject(s)
Coronary Artery Disease , Deep Learning , Humans , Positron Emission Tomography Computed Tomography , Calcium , Coronary Artery Disease/diagnostic imaging , Predictive Value of TestsABSTRACT
BACKGROUND: Machine learning (ML) has been previously applied for prognostication in patients undergoing SPECT myocardial perfusion imaging (MPI). We evaluated whether including attenuation CT coronary artery calcification (CAC) scoring improves ML prediction of major adverse cardiovascular events (MACE) in patients undergoing SPECT/CT MPI. METHODS: From the REFINE SPECT Registry 4770 patients with SPECT/CT performed at a single center were included (age: 64 ± 12 years, 45% female). ML algorithm (XGBoost) inputs were clinical risk factors, stress variables, SPECT imaging parameters, and expert-observer CAC scoring using CT attenuation correction scans performed to obtain CT attenuation maps. The ML model was trained and validated using tenfold hold-out validation. Receiver Operator Characteristics (ROC) curves were analyzed for prediction of MACE. MACE-free survival was evaluated with standard survival analyses. RESULTS: During a median follow-up of 24.1 months, 475 patients (10%) experienced MACE. Higher area under the ROC curve for MACE was observed with ML when CAC scoring was included (CAC-ML score, 0.77, 95% confidence interval [CI] 0.75-0.79) compared to ML without CAC (ML score, 0.75, 95% CI 0.73-0.77, P = .005) and when compared to CAC score alone (0.71, 95% CI 0.68-0.73, P < .001). Among clinical, imaging, and stress parameters, CAC score had highest variable importance for ML. On survival analysis patients with high CAC-ML score (> 0.091) had higher event rate when compared to patients with low CAC-ML score (hazard ratio 5.3, 95% CI 4.3-6.5, P < .001). CONCLUSION: Integration of attenuation CT CAC scoring improves the predictive value of ML risk score for MACE prediction in patients undergoing SPECT MPI.
Subject(s)
Coronary Artery Disease , Myocardial Perfusion Imaging , Humans , Female , Middle Aged , Aged , Male , Calcium , Myocardial Perfusion Imaging/methods , Tomography, Emission-Computed, Single-Photon/methods , Tomography, X-Ray Computed , Machine Learning , PrognosisABSTRACT
BACKGROUND: We aim to develop an explainable deep learning (DL) network for the prediction of all-cause mortality directly from positron emission tomography myocardial perfusion imaging flow and perfusion polar map data and evaluate it using prospective testing. METHODS: A total of 4735 consecutive patients referred for stress and rest 82Rb positron emission tomography between 2010 and 2018 were followed up for all-cause mortality for 4.15 (2.24-6.3) years. DL network utilized polar maps of stress and rest perfusion, myocardial blood flow, myocardial flow reserve, and spill-over fraction combined with cardiac volumes, singular indices, and sex. Patients scanned from 2010 to 2016 were used for training and validation. The network was tested in a set of 1135 patients scanned from 2017 to 2018 to simulate prospective clinical implementation. RESULTS: In prospective testing, the area under the receiver operating characteristic curve for all-cause mortality prediction by DL (0.82 [95% CI, 0.77-0.86]) was higher than ischemia (0.60 [95% CI, 0.54-0.66]; P <0.001), myocardial flow reserve (0.70 [95% CI, 0.64-0.76], P <0.001) or a comprehensive logistic regression model (0.75 [95% CI, 0.69-0.80], P <0.05). The highest quartile of patients by DL had an annual all-cause mortality rate of 11.87% and had a 16.8 ([95% CI, 6.12%-46.3%]; P <0.001)-fold increase in the risk of death compared with the lowest quartile patients. DL showed a 21.6% overall reclassification improvement as compared with established measures of ischemia. CONCLUSIONS: The DL model trained directly on polar maps allows improved patient risk stratification in comparison with established methods for positron emission tomography flow or perfusion assessments.
Subject(s)
Coronary Artery Disease , Deep Learning , Myocardial Perfusion Imaging , Humans , Myocardial Perfusion Imaging/methods , Positron-Emission Tomography/methods , Prospective StudiesABSTRACT
PURPOSE: We sought to evaluate inter-scan and inter-reader agreement of coronary calcium (CAC) scores obtained from dedicated, ECG-gated CAC scans (standard CAC scan) and ultra-low-dose, ungated computed tomography attenuation correction (CTAC) scans obtained routinely during cardiac PET/CT imaging. METHODS: From 2928 consecutive patients who underwent same-day 82Rb cardiac PET/CT and gated CAC scan in the same hybrid PET/CT scanning session, we have randomly selected 200 cases with no history of revascularization. Standard CAC scans and ungated CTAC scans were scored by two readers using quantitative clinical software. We assessed the agreement between readers and between two scan protocols in 5 CAC categories (0, 1-10, 11-100, 101-400, and > 400) using Cohen's Kappa and concordance. RESULTS: Median age of patients was 70 (inter-quartile range: 63-77), and 46% were male. The inter-scan concordance index and Cohen's Kappa for readers 1 and 2 were 0.69; 0.75 (0.69, 0.81) and 0.72; 0.8 (0.75, 0.85) respectively. The inter-reader concordance index and Cohen's Kappa (95% confidence interval [CI]) was higher for standard CAC scans: 0.9 and 0.92 (0.89, 0.96), respectively, vs. for CTAC scans: 0.83 and 0.85 (0.79, 0.9) for CTAC scans (p = 0.02 for difference in Kappa). Most discordant readings between two protocols occurred for scans with low extent of calcification (CAC score < 100). CONCLUSION: CAC can be quantitatively assessed on PET CTAC maps with good agreement with standard scans, however with limited sensitivity for small lesions. CAC scoring of CTAC can be performed routinely without modification of PET protocol and added radiation dose.