Manish Motwani

Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis

Aims Traditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics. Methods and results The analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P< 0.001). Conclusions Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

Motion Correction of 18F-NaF PET for Imaging Coronary Atherosclerotic Plaques

Ruptured coronary atherosclerotic plaques commonly cause acute myocardial infarction. It has recently been shown that active microcalcification in the coronary arteries, one of the features that characterizes vulnerable plaques at risk of rupture, can be imaged using 18F-NaF PET. We aimed to determine whether a motion correction technique applied to gated 18F-NaF PET images could enhance image quality and improve uptake estimates. Methods: Seventeen patients with myocardial infarction (n = 7) or stable angina (n = 10) underwent 18F-NaF PET and prospective coronary CT angiography. PET data were reconstructed in 4 different ways: the first was 1 gated bin (end-diastolic phase with 25% of the counts), the second was 4 gated bins (consecutive 25% segments), the third was 10 gated bins (consecutive 10% segments), and the fourth was ungated. Subsequently, with data from either 4 or 10 bins, gated PET images were registered using a local, nonlinear motion correction method guided by the extracted coronary arteries from CT angiography. Global noise levels and target-to-background ratios (TBR) defined on manually delineated coronary plaque lesions were compared to assess image quality and uptake estimates. Results: Compared with the reference standard of using only 1 bin of PET data, motion correction using 10 bins of PET data reduced image noise by 46% (P < 0.0001). TBR in positive lesions for 10-bin motion-corrected data was 11% higher than for 1-bin data (1.98 [interquartile range, 1.70–2.37] vs. 1.78 [1.58–2.16], P = 0.0027) and 33% higher than for ungated data (1.98 [1.70–2.37] vs. 1.49 [1.39–1.88], P < 0.0001). Conclusion: Motion correction of gated 18F-NaF PET/coronary CT angiography is feasible, reduces image noise, and increases TBR. This improvement may allow more reliable identification of vulnerable coronary artery plaques using 18F-NaF PET.

Quantitative global plaque characteristics from coronary computed tomography angiography for the prediction of future cardiac mortality during long-term follow-up

Aims Adverse plaque characteristics determined by coronary computed tomography angiography (CTA) have been associated with future cardiac events. Our aim was to investigate whether quantitative global per-patient plaque characteristics from coronary CTA can predict subsequent cardiac death during long-term follow-up. Methods and results Out of 2748 patients without prior history of coronary artery disease undergoing CTA with dual-source CT, 32 patients suffered cardiac death (mean follow-up of 5 ± 2 years). These patients were matched to 32 controls by age, gender, risk factors, and symptoms (total 64 patients, 59% male, age 69 ± 10 years). Coronary CTA data sets were analysed by semi-automated software to quantify plaque characteristics over the entire coronary tree, including total plaque volume, volumes of non-calcified plaque (NCP), low-density non-calcified plaque (LD-NCP, attenuation <30 Hounsfield units), calcified plaque (CP), and corresponding burden (plaque volume × 100%/vessel volume), as well as stenosis and contrast density difference (CDD, maximum percent difference in luminal attenuation/cross-sectional area compared to proximal cross-section). In patients who died from cardiac cause, NCP, LD-NCP, CP and total plaque volumes, quantitative stenosis, and CDD were significantly increased compared to controls (P < 0.025 for all). NCP > 146 mm³ [hazards ratio (HR) 2.24; 1.09-4.58; P = 0.027], LD-NCP > 10.6 mm³ (HR 2.26; 1.11-4.63; P = 0.025), total plaque volume > 179 mm³ (HR 2.30; 1.12-4.71; P = 0.022), and CDD > 35% in any vessel (HR 2.85;1.4-5.9; P = 0.005) were associated with increased risk of future cardiac death, when adjusted for segment involvement score. Conclusion Among quantitative global plaque characteristics, total, non-calcified, and low-density plaque volumes as well as CDD predict cardiac death in long-term follow-up.

Reasons and implications of agreements and disagreements between coronary flow reserve, fractional flow reserve, and myocardial perfusion imaging

Information on coronary physiology and myocardial blood flow (MBF) in patients with suspected angina is increasingly important to inform treatment decisions. A number of different techniques including myocardial perfusion imaging (MPI), noninvasive estimation of MBF, and coronary flow reserve (CFR), as well as invasive methods for CFR and fractional flow reserve (FFR) are now readily available. However, despite their incorporation into contemporary guidelines, these techniques are still poorly understood and their interpretation to guide revascularization decisions is often inconsistent. In particular, these inconsistencies arise when there are discrepancies between the various techniques. The purpose of this article is therefore to review the basic principles, techniques, and clinical value of MPI, FFR, and CFR—with particular focus on interpreting their agreements and disagreements.

Demons versus Level-Set motion registration for coronary 18F-sodium fluoride PET

Ruptured coronary atherosclerotic plaques commonly cause acute myocardial infarction. It has been recently shown that active microcalcification in the coronary arteries, one of the features that characterizes vulnerable plaques at risk of rupture, can be imaged using cardiac gated 18F-sodium fluoride (18F-NaF) PET. We have shown in previous work that a motion correction technique applied to cardiac-gated 18F-NaF PET images can enhance image quality and improve uptake estimates. In this study, we further investigated the applicability of different algorithms for registration of the coronary artery PET images. In particular, we aimed to compare demons vs. level-set nonlinear registration techniques applied for the correction of cardiac motion in coronary 18F-NaF PET. To this end, fifteen patients underwent 18F-NaF PET and prospective coronary CT angiography (CCTA). PET data were reconstructed in 10 ECG gated bins; subsequently these gated bins were registered using demons and level-set methods guided by the extracted coronary arteries from CCTA, to eliminate the effect of cardiac motion on PET images. Noise levels, target-to-background ratios (TBR) and global motion were compared to assess image quality. Compared to the reference standard of using only diastolic PET image (25% of the counts from PET acquisition), cardiac motion registration using either level-set or demons techniques almost halved image noise due to the use of counts from the full PET acquisition and increased TBR difference between 18F-NaF positive and negative lesions. The demons method produces smoother deformation fields, exhibiting no singularities (which reflects how physically plausible the registration deformation is), as compared to the level-set method, which presents between 4 and 8% of singularities, depending on the coronary artery considered. In conclusion, the demons method produces smoother motion fields as compared to the level-set method, with a motion that is physiologically plausible. Therefore, level-set technique will likely require additional post-processing steps. On the other hand, the observed TBR increases were the highest for the level-set technique. Further investigations of the optimal registration technique of this novel coronary PET imaging technique are warranted.

Automated Quantitative Nuclear Cardiology Methods.

Quantitative analysis of SPECT and PET has become a major part of nuclear cardiology practice. Current software tools can automatically segment the left ventricle, quantify function, establish myocardial perfusion maps, and estimate global and local measures of stress/rest perfusion, all with minimal user input. State-of-the-art automated techniques have been shown to offer high diagnostic accuracy for detecting coronary artery disease, as well as predict prognostic outcomes. This article briefly reviews these techniques, highlights several challenges, and discusses the latest developments.

Impact of incomplete ventricular coverage on diagnostic performance of myocardial perfusion imaging

In the context of myocardial perfusion imaging (MPI) with cardiac magnetic resonance (CMR), there is ongoing debate on the merits of using technically complex acquisition methods to achieve whole-heart spatial coverage, rather than conventional 3-slice acquisition. An adequately powered comparative study is difficult to achieve given the requirement for two separate stress CMR studies in each patient. The aim of this work is to draw relevant conclusions from SPECT MPI by comparing whole-heart versus simulated 3-slice coverage in a large existing dataset. SPECT data from 651 patients with suspected coronary artery disease who underwent invasive angiography were analyzed. A computational approach was designed to model 3-slice MPI by retrospective subsampling of whole- heart data. For both whole-heart and 3-slice approaches, the diagnostic performance and the stress total perfusion deficit (TPD) score—a measure of ischemia extent/severity—were quantified and compared. Diagnostic accuracy for the 3-slice and whole-heart approaches were similar (area under the curve: 0.843 vs. 0.855, respectively; P = 0.07). The majority (54%) of cases missed by 3-slice imaging had primarily apical ischemia. Whole-heart and 3-slice TPD scores were strongly correlated (R2 = 0.93, P < 0.001) but 3-slice TPD showed a small yet significant bias compared to whole-heart TPD (− 1.19%; P < 0.0001) and the 95% limits of agreement were relatively wide (− 6.65% to 4.27%). Incomplete ventricular coverage typically acquired in 3-slice CMR MPI does not significantly affect the diagnostic accuracy. However, 3-slice MPI may fail to detect severe apical ischemia and underestimate the extent/severity of perfusion defects. Our results suggest that caution is required when comparing the ischemic burden between 3-slice and whole-heart datasets, and corroborate the need to establish prognostic thresholds specific to each approach.

Role of Novel Imaging Techniques in Detection of Chemotoxicity: Cardiac Magnetic Resonance and Radionuclide Imaging

Chemotherapy-induced cardiotoxicity manifests as reduced left ventricular ejection fraction and is associated with significant morbidity. Often, patients do not present with clinical symptoms until irreversible myocardial damage has occurred. Cardiac magnetic resonance imaging (CMR) enables the detection of subclinical changes so that cardioprotective medications and alternative chemotherapeutic strategies may be initiated before the onset of clinical symptoms. In addition to quantification of chamber volumes and ventricular function, advances in CMR including T1 and T2 mapping are playing an increasingly prominent role for the detection of inflammation and fibrosis. In this chapter we also present the relative advantages of CMR over other imaging modalities for the detection of early changes associated with cardiotoxicity.

Subclinical systolic and diastolic dysfunction in women with signs and symptoms of ischemia but no obstructive coronary disease: novel insights using myocardial feature tracking in the NHLBI WISE study

Background Women with signs and symptoms of ischemia–but no obstructive coronary artery disease–often have coronary microvascular dysfunction (CMD), and are at increased risk of major cardiovascular events, including heart failure. Using cardiac magnetic resonance tissue tagging, we recently found subclinical diastolic dysfunction in these women, suggesting that ischemia-related diastolic dysfunction may be mechanistically linked to the development of heart failure. Tissue tagging involves specialized image acquisition and post processing, and thus is not typically suitable for large patient studies. We hypothesized that feature tracking of conventional (clinical) cardiac cine images would provide similar information. We therefore compared feature tracking with gold-standard tissue tagging, and then, used feature tracking to assess left ventricular function in women with suspected CMD.

Interscan reproducibility of cardiovascular magnetic resonance myocardial perfusion reserve index in women with suspected coronary microvascular dysfunction and no obstructive coronary artery disease

Background Cardiovascular magnetic resonance (CMR) myocardial perfusion reserve index (MPRI) has recently shown promise for detecting coronary microvascular dysfunction (CMD) in women with signs and symptoms of ischemia and no obstructive coronary artery disease (CAD). Prior CMR studies in CAD populations and in healthy volunteers have shown good intra and interobserver reproducibility for MPRI. However, interscan reproducibility is more variable. If MPRI is to be considered useful for the detection of CMD in women, the interscan reproducibility in this population must also be understood, such that proposed MPRI cut-off thresholds can be appropriately adjusted. Therefore, the aim of this study was to determine the interscan reproducibility of MPRI in women with suspected CMD.