Explainable artificial intelligence (AI) can be integrated within standard clinical software to facilitate the acceptance of the diagnostic findings during clinical interpretation.
This study sought ...to develop and evaluate a novel, general purpose, explainable deep learning model (coronary artery disease–deep learning CAD-DL) for the detection of obstructive CAD following single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI).
A total of 3,578 patients with suspected CAD undergoing SPECT MPI and invasive coronary angiography within a 6-month interval from 9 centers were studied. CAD-DL computes the probability of obstructive CAD from stress myocardial perfusion, wall motion, and wall thickening maps, as well as left ventricular volumes, age, and sex. Myocardial regions contributing to the CAD-DL prediction are highlighted to explain the findings to the physician. A clinical prototype was integrated using a standard clinical workstation. Diagnostic performance by CAD-DL was compared to automated quantitative total perfusion deficit (TPD) and reader diagnosis.
In total, 2,247 patients (63%) had obstructive CAD. In 10-fold repeated testing, the area under the receiver-operating characteristic curve (AUC) (95% CI) was higher according to CAD-DL (AUC: 0.83 95% CI: 0.82-0.85) than stress TPD (AUC: 0.78 95% CI: 0.77-0.80) or reader diagnosis (AUC: 0.71 95% CI: 0.69-0.72; P < 0.0001 for both). In external testing, the AUC in 555 patients was higher according to CAD-DL (AUC: 0.80 95% CI: 0.76-0.84) than stress TPD (AUC: 0.73 95% CI: 0.69-0.77) or reader diagnosis (AUC: 0.65 95% CI: 0.61-0.69; P < 0.001 for all). The present model can be integrated within standard clinical software and generates results rapidly (<12 seconds on a standard clinical workstation) and therefore could readily be incorporated into a typical clinical workflow.
The deep-learning model significantly surpasses the diagnostic accuracy of standard quantitative analysis and clinical visual reading for MPI. Explainable artificial intelligence can be integrated within standard clinical software to facilitate acceptance of artificial intelligence diagnosis of CAD following MPI.
Display omitted
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Stress-only myocardial perfusion imaging (MPI) markedly reduces radiation dose, scanning time, and cost. We developed an automated clinical algorithm to safely cancel unnecessary rest imaging with ...high sensitivity for obstructive coronary artery disease (CAD).
Patients without known CAD undergoing both MPI and invasive coronary angiography from REFINE SPECT were studied. A machine learning score (MLS) for prediction of obstructive CAD was generated using stress-only MPI and pre-test clinical variables. An MLS threshold with a pre-defined sensitivity of 95% was applied to the automated patient selection algorithm. Obstructive CAD was present in 1309/2079 (63%) patients. MLS had higher area under the receiver operator characteristic curve (AUC) for prediction of CAD than reader diagnosis and TPD (0.84 vs 0.70 vs 0.78, P < .01). An MLS threshold of 0.29 had superior sensitivity than reader diagnosis and TPD for obstructive CAD (95% vs 87% vs 87%, P < .01) and high-risk CAD, defined as stenosis of the left main, proximal left anterior descending, or triple-vessel CAD (sensitivity 96% vs 89% vs 90%, P < .01).
The MLS is highly sensitive for prediction of both obstructive and high-risk CAD from stress-only MPI and can be applied to a stress-first protocol for automatic cancellation of unnecessary rest imaging.
Full text
Available for:
EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OILJ, PNG, SAZU, SBCE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Optimal risk stratification with machine learning (ML) from myocardial perfusion imaging (MPI) includes both clinical and imaging data. While most imaging variables can be derived automatically, ...clinical variables require manual collection, which is time-consuming and prone to error. We determined the fewest manually input and imaging variables required to maintain the prognostic accuracy for major adverse cardiac events (MACE) in patients undergoing a single-photon emission computed tomography (SPECT) MPI.
This study included 20 414 patients from the multicentre REFINE SPECT registry and 2984 from the University of Calgary for training and external testing of the ML models, respectively. ML models were trained using all variables (ML-All) and all image-derived variables (including age and sex, ML-Image). Next, ML models were sequentially trained by incrementally adding manually input and imaging variables to baseline ML models based on their importance ranking. The fewest variables were determined as the ML models (ML-Reduced, ML-Minimum, and ML-Image-Reduced) that achieved comparable prognostic performance to ML-All and ML-Image. Prognostic accuracy of the ML models was compared with visual diagnosis, stress total perfusion deficit (TPD), and traditional multivariable models using area under the receiver-operating characteristic curve (AUC). ML-Minimum (AUC 0.798) obtained comparable prognostic accuracy to ML-All (AUC 0.799, P = 0.19) by including 12 of 40 manually input variables and 11 of 58 imaging variables. ML-Reduced achieved comparable accuracy (AUC 0.796) with a reduced set of manually input variables and all imaging variables. In external validation, the ML models also obtained comparable or higher prognostic accuracy than traditional multivariable models.
Reduced ML models, including a minimum set of manually collected or imaging variables, achieved slightly lower accuracy compared to a full ML model but outperformed standard interpretation methods and risk models. ML models with fewer collected variables may be more practical for clinical implementation.
Purpose
Artificial intelligence (AI) has high diagnostic accuracy for coronary artery disease (CAD) from myocardial perfusion imaging (MPI). However, when trained using high-risk populations (such as ...patients with correlating invasive testing), the disease probability can be overestimated due to selection bias. We evaluated different strategies for training AI models to improve the calibration (accurate estimate of disease probability), using external testing.
Methods
Deep learning was trained using 828 patients from 3 sites, with MPI and invasive angiography within 6 months. Perfusion was assessed using upright (U-TPD) and supine total perfusion deficit (S-TPD). AI training without data augmentation (model 1) was compared to training with augmentation (increased sampling) of patients without obstructive CAD (model 2), and patients without CAD and TPD < 2% (model 3). All models were tested in an external population of patients with invasive angiography within 6 months (
n
= 332) or low likelihood of CAD (
n
= 179).
Results
Model 3 achieved the best calibration (Brier score 0.104 vs 0.121,
p
< 0.01). Improvement in calibration was particularly evident in women (Brier score 0.084 vs 0.124,
p
< 0.01). In external testing (
n
= 511), the area under the receiver operating characteristic curve (AUC) was higher for model 3 (0.930), compared to U-TPD (AUC 0.897) and S-TPD (AUC 0.900,
p
< 0.01 for both).
Conclusion
Training AI models with augmentation of low-risk patients can improve calibration of AI models developed to identify patients with CAD, allowing more accurate assignment of disease probability. This is particularly important in lower-risk populations and in women, where overestimation of disease probability could significantly influence down-stream patient management.
Full text
Available for:
DOBA, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, IZUM, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, SIK, UILJ, UKNU, UL, UM, UPUK, VKSCE, VSZLJ, ZAGLJ
99mTc-pyrophosphate imaging has emerged as an important non-invasive method to diagnose transthyretin cardiac amyloidosis (ATTR-CM). Quantitation of 99mTc-pyrophosphate activity, on SPECT images, ...could be a marker of ATTR-CM disease burden. We assessed the diagnostic accuracy and clinical significance of 99mTc-pyrophosphate quantitation.
Patients who underwent 99mTc-pyrophosphate imaging for suspected ATTR-CM were included. Using SPECT images, radiotracer activity in the myocardium was calculated using cardiac pyrophosphate activity (CPA) and volume of involvement (VOI), with thresholds for abnormal activity derived from LVBP activity. Diagnostic accuracy was assessed using area under the receiver operating characteristic curve (AUC). In total, 124 patients were identified, mean age 73.9 ± 11.4, with ATTR-CM diagnosed in 43 (34.7%) patients. CPA had the highest diagnostic accuracy (AUC .996, 95% CI .987-1.00), and was significantly higher compared to the Perugini score (AUC .952, P = .016). In patients with ATTR-CM, CPA was associated with reduced left ventricular ejection fraction (adjusted odds ratio 1.28, P = .035) and heart failure hospitalizations (adjusted hazard ratio 1.29, P = .006).
Quantitative assessment of myocardial radiotracer activity with CPA or VOI have high diagnostic accuracy for ATTR-CM. Both measures are potential non-invasive markers to follow progression of disease or response to therapy.
Las imágenes de 99mTc-pirofosfato han surgido como un importante método no invasivo para diagnosticar la amiloidosis cardíaca por transtiretina (ATTR-CM). La cuantificación de la actividad del 99mTc-pirofosfato, en las imágenes de SPECT, podría ser un marcador de la carga de enfermedad de ATTR-CM. Evaluamos la precisión diagnóstica y la importancia clínica de la cuantificación del 99mTc-pirofosfato.
Se incluyeron pacientes que se sometieron 99mTc-pirofosfato por sospecha de ATTR-CM. Utilizando imágenes de SPECT, se calculó la actividad del radiotrazador en el miocardio utilizando la actividad cardiaca del pirofosfato (CPA) y el volumen del involucro (VOI), con umbrales para la actividad anormal derivados de la actividad del LVBP. La precisión diagnóstica se evaluó utilizando el área bajo la curva (AUC) de las características del funcionamiento del receptor. En total, se identificaron 124 pacientes, edad media 73,9 ± 11,4, con ATTR-CM diagnosticado en 43 (34,7%) pacientes. La CPA tuvo la mayor certeza diagnóstica (AUC 0.996, IC del 95% 0.987 – 1.00), y fue significativamente mayor en comparación con el score de Perugini (AUC 0.952, p = 0.016). En pacientes con ATTR-CM, la CPA se asoció con una fracción de eyección del ventrículo izquierdo disminuida (odds ratio ajustada 1.28, p = 0.035) y hospitalizaciones por falla cardíaca (hazard ratio ajustado 1.29, p =0,006).
La evaluación cuantitativa de la actividad del radiotrazador en miocárdico con CPA o VOI tiene una alta certeza diagnóstica para ATTR-CM. Ambas medidas son potenciales marcadores no invasivos para seguir la progresión de la enfermedad o la respuesta a terapia.
99m锝-焦磷酸盐成像已成为诊断运甲状腺素蛋白心脏淀粉样变性(ATTR-CM)的一种重要的非侵入性方法。 在SPECT图像上定量分析99m锝-焦磷酸盐的活性可能是ATTR-CM疾病严重程度的标志。 本文评估了99m锝-焦磷酸盐定量分析的诊断准确性和临床意义。
接受99m锝-焦磷酸盐成像的疑似ATTR-CM的患者纳入本研究。在SPECT图像中,使用心脏焦磷酸盐活性(CPA)和受累体积(VOI)计算心肌中的放射性示踪剂活性,并根据LVBP活性得出异常活性的阈值。 使用接受者操作特征曲线下的面积(AUC)评估诊断准确性。本实验共入组124例患者,平均年龄为73±11.4,其中43例(34.7%)患者被诊断为ATTR-CM。 CPA的诊断准确度最高(AUC 0.996,95%CI 0.987 – 1.00),与Perugini评分相比明显更高(AUC 0.952,p = 0.016)。 在ATTR-CM的患者中,CPA与左心室射血分数降低(调整后的优势比1.28,p = 0.035)和心衰住院(调整后的危险比1.29,p = 0.006)相关。
使用CPA或VOI定量评估心肌放射性示踪剂的活性对ATTR-CM具有很高的诊断准确性。 两种方法都是潜在的非侵入性指标,可跟踪疾病的进展或治疗效果。
L’imagerie au 99mTc-pyrophosphate est devenue une méthode non invasive importante pour le diagnostic de l’amyloidose cardiaque à transthyrétine (ATTR-CM). La quantification de l’activité du 99mTc-pyrophosphate sur les images SPECT, pourrait être un marqueur de l’intensité de la maladie. Dans cette étude, nous avons évalué la précision diagnostique et la signification clinique de la quantification au 99mTc-pyrophosphate.
Les patients ayant bénéficié d’une imagerie au 99mTc-pyrophosphate pour suspicion d’ATTR-CM ont été inclus. Nous avons calculé l’activité (CPA) et le volume (VOI) du 99mTc-pyrophosphate (CPA) au niveau du myocarde sur les images SPECT en rapport à l’activité sanguine au niveau de la cavité ventriculaire gauche. La précision du test a été évaluée en utilisant la surface (AUC) sous la courbe ROC. Au total, 124 patients ont été étudiés (âge moyen de 73,9 ± 11,4). Quarante trois de ces patients (34.7%) furent diagnostiqués positivement pour l’ ATTR-CM. La précision diagnostique de la CPA s’est révélée la plus élevée (AUC 0,996, IC à 95% 0,987 - 1,00), et s’est avérée significativement plus élevée que le score de Perugini (AUC 0,952, p = 0,016). Chez les patients avec ATTR-CM, la CPA est associée à une fraction d’éjection ventriculaire gauche réduite (odds ratio ajusté de 1,28, p = 0,035) et une augmentation d’ hospitalisation pour insuffisance cardiaque (hazard ratio ajusté de 1,29, p = 0,006).
L’évaluation quantitative de l’activité du 99mTc-pyrophosphate est d’une grande précision diagnostique pour l’ ATTR-CM. Les mesures CAP et VOI sont des marqueurs non invasifs potentiels pour le suivi de la progression de la maladie ou réponse au traitement.
Full text
Available for:
EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
This information statement from the Society of Nuclear Medicine and Molecular Imaging, American Society of Nuclear Cardiology, and European Association of Nuclear Medicine describes the performance, ...interpretation, and reporting of hot spot imaging in nuclear cardiology. The field of nuclear cardiology has historically focused on cold spot imaging for the interpretation of myocardial ischemia and infarction. Hot spot imaging has been an important part of nuclear medicine, particularly for oncology or infection indications, and the use of hot spot imaging in nuclear cardiology continues to expand. This document focuses on image acquisition and processing, methods of quantification, indications, protocols, and reporting of hot spot imaging. Indications discussed include myocardial viability, myocardial inflammation, device or valve infection, large vessel vasculitis, valve calcification and vulnerable plaques, and cardiac amyloidosis. This document contextualizes the foundations of image quantification and highlights reporting in each indication for the cardiac nuclear imager.
Full text
Available for:
EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Artificial intelligence may improve accuracy of myocardial perfusion imaging (MPI) but will likely be implemented as an aid to physician interpretation rather than an autonomous tool. Deep learning ...(DL) has high standalone diagnostic accuracy for obstructive coronary artery disease (CAD), but its influence on physician interpretation is unknown. We assessed whether access to explainable DL predictions improves physician interpretation of MPI.
We selected a representative cohort of patients who underwent MPI with reference invasive coronary angiography. Obstructive CAD, defined as stenosis ≥50% in the left main artery or ≥70% in other coronary segments, was present in half of the patients. We used an explainable DL model (CAD-DL), which was previously developed in a separate population from different sites. Three physicians interpreted studies first with clinical history, stress, and quantitative perfusion, then with all the data plus the DL results. Diagnostic accuracy was assessed using area under the receiver-operating-characteristic curve (AUC).
In total, 240 patients with a median age of 65 y (interquartile range 58-73) were included. The diagnostic accuracy of physician interpretation with CAD-DL (AUC 0.779) was significantly higher than that of physician interpretation without CAD-DL (AUC 0.747,
= 0.003) and stress total perfusion deficit (AUC 0.718,
< 0.001). With matched specificity, CAD-DL had higher sensitivity when operating autonomously compared with readers without DL results (
< 0.001), but not compared with readers interpreting with DL results (
= 0.122). All readers had numerically higher accuracy with CAD-DL, with AUC improvement 0.02-0.05, and interpretation with DL resulted in overall net reclassification improvement of 17.2% (95% CI 9.2%-24.4%,
< 0.001).
Explainable DL predictions lead to meaningful improvements in physician interpretation; however, the improvement varied across the readers, reflecting the acceptance of this new technology. This technique could be implemented as an aid to physician diagnosis, improving the diagnostic accuracy of MPI.
There has been an evolutionary leap in SPECT imaging with the advent of camera systems that use solid-state crystals and novel collimator designs configured specifically for cardiac imaging. ...Solid-state SPECT camera systems have facilitated dramatic reductions in both imaging time and radiation dose while maintaining high diagnostic accuracy. These advances are related to simultaneous improvement in photon sensitivity due to the collimator and imaging geometry, as well as image resolution due to the improved energy resolution of the new crystals. Improved photon sensitivity has facilitated fast or low-dose myocardial perfusion imaging (MPI), and early dynamic imaging has emerged as a technique for assessing myocardial blood flow with SPECT. Lastly, general-purpose solid-state camera systems and hybrid SPECT/CT systems have also been developed that may have important clinical roles in cardiac imaging. This review summarizes state-of-the-art solid-state SPECT MPI technology and clinical applications, including emerging techniques for SPECT MPI flow estimation. We also discuss imaging protocols used with the new cameras, potential imaging pitfalls, and the latest data providing large-scale validation of the diagnostic and prognostic value of this new technology.
Abstract
Aims
Our aim was to evaluate the performance of machine learning (ML), integrating clinical parameters with coronary artery calcium (CAC), and automated epicardial adipose tissue (EAT) ...quantification, for the prediction of long-term risk of myocardial infarction (MI) and cardiac death in asymptomatic subjects.
Methods and results
Our study included 1912 asymptomatic subjects 1117 (58.4%) male, age: 55.8 ± 9.1 years from the prospective EISNER trial with long-term follow-up after CAC scoring. EAT volume and density were quantified using a fully automated deep learning method. ML extreme gradient boosting was trained using clinical co-variates, plasma lipid panel measurements, risk factors, CAC, aortic calcium, and automated EAT measures, and validated using repeated 10-fold cross validation. During mean follow-up of 14.5 ± 2 years, 76 events of MI and/or cardiac death occurred. ML obtained a significantly higher AUC than atherosclerotic cardiovascular disease (ASCVD) risk and CAC score for predicting events (ML: 0.82; ASCVD: 0.77; CAC: 0.77, P < 0.05 for all). Subjects with a higher ML score (by Youden’s index) had high hazard of suffering events (HR: 10.38, P < 0.001); the relationships persisted in multivariable analysis including ASCVD-risk and CAC measures (HR: 2.94, P = 0.005). Age, ASCVD-risk, and CAC were prognostically important for both genders. Systolic blood pressure was more important than cholesterol in women, and the opposite in men.
Conclusions
In this prospective study, machine learning used to integrate clinical and quantitative imaging-based variables significantly improves prediction of MI and cardiac death compared with standard clinical risk assessment. Following further validation, such a personalized paradigm could potentially be used to improve cardiovascular risk assessment.
Obese patients constitute a substantial proportion of patients referred for SPECT myocardial perfusion imaging (MPI), presenting a challenge of increased soft tissue attenuation. We investigated ...whether automated quantitative perfusion analysis can stratify risk among different obesity categories and whether two-view acquisition adds to prognostic assessment.
Participants were categorized according to body mass index (BMI). SPECT MPI was assessed visually and quantified automatically; combined total perfusion deficit (TPD) was evaluated. Kaplan–Meier and Cox proportional hazard analyses were used to assess major adverse cardiac event (MACE) risk. Prognostic accuracy for MACE was also compared.
Patients were classified according to BMI: BMI < 30, 30 ≤ BMI < 35, BMI ≥ 35. In adjusted analysis, each category of increasing stress TPD was associated with increased MACE risk, except for 1% ≤ TPD < 5% and 5% ≤ TPD < 10% in patients with BMI ≥ 35. Compared to visual analysis, single-position stress TPD had higher prognostic accuracy in patients with BMI < 30 (AUC .652 vs .631, P < .001) and 30 ≤ BMI < 35 (AUC .660 vs .636, P = .027). Combined TPD had better discrimination than visual analysis in patients with BMI ≥ 35 (AUC .662 vs .615, P = .003).
Automated quantitative methods for SPECT MPI interpretation provide robust risk stratification in the obese population. Combined stress TPD provides additional prognostic accuracy in patients with more significant obesity.
Full text
Available for:
EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OILJ, PNG, SAZU, SBCE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
PDF
