Coronary CT angiography: a guide to examination, interpretation, and clinical indications

Deep learning techniques for automated coronary artery segmentation and coronary artery disease detection: A systematic review of the last decade (2013-2024)

BACKGROUND

Coronary artery disease (CAD) is the most common cardiovascular disease, exacting high morbidity and mortality worldwide. CAD is detected on coronary artery imaging; coronary artery segmentation (CAS) of the images is essential for coronary lesion characterization. Both CAD detection and CAS require expert input, are labor-intensive, and error-prone.

OBJECTIVES

Deep learning (DL) techniques have achieved significant success in CAS and CAD detection, with many studies published recently. This study is an up-to-date systematic review of research on automated DL models for CAS and CAD detection in the past decade (2013-2024).

METHOD

Using PRISMA methodology, an initial literature search of 1,589 publications was conducted, from which 97 high-impact Q1 studies were selected based on pre-defined eligibility criteria. These studies were analyzed in terms of DL techniques employed, datasets, modalities, and performance metrics.

RESULTS

Of the 97 studies, most of which were published after 2016, 47 focused on CAS, 49 on CAD detection, and one on both tasks. CNN-based models were dominant in both domains. For CAS, CCTA was the most frequently used input modality, and U-Net was employed in 38 out of 48 studies, with recent works incorporating attention mechanisms and graph neural networks. ASOCA was the most widely used benchmark dataset. For CAD detection, ECG was the most common modality, with 45 out of 50 studies utilizing CNNs, and 20 of those relying purely on CNN architectures. Hybrid and multimodal models have become more prominent in recent years.

CONCLUSION

This review identified several challenges, including limited public datasets, variability in performance metrics, and model complexity. Future studies should focus on larger, diverse datasets and lightweight models integrating explainable artificial intelligence and uncertainty quantification to improve clinical applicability.

Minimally invasive coronary artery bypass grafting via left anterior minithoracotomy: Setup, results, and evolution of a new surgical procedure

Objective

Minimally invasive total arterial coronary artery bypass grafting offers the advantages of total arterial revascularization through an anterolateral minithoracotomy. However, the procedure is technically challenging and associated with a learning curve. The purpose of our study was to evaluate the progress and development of our program over an 8-year period.

Methods

We collected prospective data on all patients who underwent procedure at our institution from January 2015 to December 2023. Our program underwent several modifications during this study period, including optimization of surgical exposure using various available instruments, efficient intraoperative time management, utilization of a standard technique for all off-pump coronary artery bypass procedures, and close team member mentoring. Changes in quality control consisted of transitioning from routine postoperative coronary imaging to clinically indicated imaging. The influence of these interventions was assessed by focusing on in-hospital mortality as the primary end point, and operative time and perioperative myocardial infarction as secondary end points, over 2 time periods consisting of patients operated on during the first and second 4-year study period (Group 1, n = 137 and Group 2, n = 142).

Results

A total of 279 consecutive patients underwent elective, total arterial minimally invasive total arterial coronary artery bypass grafting at our institution over the study period. The mean age of patients was 66 ± 7 years, with 86% being men (n = 241) and 33.1% having diabetes (n = 77). Triple vessel disease was present in 53% of the cohort (n = 123) and left main disease was prevalent in 43% of patients (n = 101). The overall 30-day mortality was 0.4% (n = 1). Compared with the initial 4-year period, the rate of perioperative myocardial infarction decreased 3-fold (4.3% vs 1.4%; P = .1) and there was a statistically significant reduction in operating time (275 ± 59.5 and 246 ± 72.6 minutes; P < .001) in the most recent group of patients.

Conclusions

Total arterial minimally invasive total arterial coronary artery bypass grafting is a feasible surgical approach that can be performed with very good results, even during the initial learning curve phase. An evolving educational program can provide a smooth transition from off-pump coronary artery bypass grafting to minimally invasive total arterial coronary artery bypass grafting, when performed in selected patients in high-volume cardiac centers.

Computed tomography coronary angiography as an alternative to invasive coronary angiography in preoperative evaluation for mitral surgery

OBJECTIVE

To assess the effectiveness of noninvasive coronary computed tomography angiography (CTA) as an alternative to traditional invasive coronary angiography (ICA) for preoperative evaluation of low-risk patients with an indication for nonemergent mitral surgery and to assess any difference in adverse outcomes from this strategy.

METHODS

This was a retrospective cohort study from a single center with data collected from July 2014 to June 2020 for 1576 patients undergoing mitral valve surgery of all etiologies, excluding patients requiring coronary artery bypass surgery. We performed a 1:2 propensity score matching for patients evaluated with CTA (n = 345) to those evaluated with ICA (n = 602). The primary outcome was a composite of major adverse events in the immediate postoperative period, including death, stroke, new-onset renal failure, postoperative cardiac arrest, need for unplanned coronary artery bypass grafting or percutaneous coronary re-vascularization. The odds ratio was calculated for occurrence of major adverse events in the CTA group compared with the catheterization group.

RESULTS

The mean age (standard deviation) was 55.62 years (11.54) for the CTA group and 58.22 years (10.11) for the ICA group. In the CTA group 334 (96.8%) and from the ICA group 582 (96.7%) patients underwent mitral valve repair. Thirteen (3.8%) patients in the CTA group experienced a major adverse event compared with 25 (4.2%) patients in the ICA group. Of these, there were no mortalities in the CTA group but 1 (0.2%) operative mortality in the ICA group. Four (1.2%) patients in the CTA group had a postoperative stroke compared with 3 (0.5%) patients in the ICA group. One (0.3%) patient in the CTA group required renal-replacement therapy postoperatively compared with 11 (1.8%) in the ICA group. Percutaneous coronary intervention was required in 1 (0.3%) patient in CTA group and 2 (0.3%) patients in ICA group for a coronary complication of valve surgery despite nonobstructive coronary anatomy being confirmed in both groups preoperatively. The odds ratio for having a major adverse event when worked up by CTA compared with ICA was 0.904 (0.443, 1.761).

CONCLUSIONS

There were no increased odds of experiencing a major adverse event for low-risk patients undergoing elective mitral valve surgery and preoperative coronary evaluation with CTA compared with ICA. These data have modified our practice pattern, where we now offer coronary CTA to all elective patients who are low risk for coronary artery disease.

The Non-invasive Assessment of the Pulmonary Circulation-Right Ventricular Functional Unit: Diagnostic and Prognostic Implications

The pulmonary circulation and the right ventricle play a pivotal role in the global hemodynamics of human beings, so much so that their close interaction is encapsulated in the concept of a "morpho-functional unit". In this review we aim to pinpoint the strengths and weaknesses of various noninvasive established techniques. The goal is to detect early morphologic and/or functional changes in the pulmonary circulation and right ventricular unit, which is crucial for tailoring treatments and prognostic assessments. The scope of this review includes resting and stress echocardiography, cardiopulmonary exercise testing, computed tomography, and cardiac magnetic resonance in characterizing the pulmonary circulation-right ventricular unit both morphologically and functionally.

The value of CCTA combined with machine learning for predicting angina pectoris in the anomalous origin of the right coronary artery

BACKGROUND

Anomalous origin of coronary artery is a common coronary artery anatomy anomaly. The anomalous origin of the coronary artery may lead to problems such as narrowing of the coronary arteries at the beginning of the coronary arteries and abnormal alignment, which may lead to myocardial ischemia due to the compression of the coronary arteries. Clinical symptoms include chest tightness and dyspnea, with angina pectoris as a common symptom that can be life-threatening. Timely and accurate diagnosis of anomalous coronary artery origin is of great importance. Coronary computed tomography angiography (CCTA) can provide detailed information on the characteristics of coronary arteries. Therefore, we combined CCTA and artificial intelligence (AI) technology to analyze the CCTA image features and clinical features of patients with anomalous origin of the right coronary artery to predict angina pectoris and the relevance of different features to angina pectoris.

METHODS

In this retrospective analysis, we compiled data on 15 characteristics from 126 patients diagnosed with anomalous right coronary artery origins. The dataset encompassed both CCTA imaging attributes, such as the positioning of the right coronary artery orifices and the alignment of coronary arteries, and clinical parameters including gender and age. To identify the most salient features, we employed the Chi-square feature selection method, which filters features based on their statistical significance. We then focused on features yielding a Chi-square score exceeding a threshold of 1, thereby narrowing down the selection to seven key variables, including cardiac function and gender. Subsequently, we evaluated seven classifiers known for their efficacy in classification tasks. Through rigorous training and testing, we conducted a comparative analysis to identify the top three classifiers with the highest accuracy rates.

RESULTS

The top three classifiers in this study are Support Vector Machine (SVM), Ensemble Learning (EL), and Kernel Approximation Classifier. Among the SVM, EL and Kernel Approximation Classifier-based classifiers, the best performance is achieved for linear SVM, optimizable Ensembles Learning and SVM kernel, respectively. And the corresponding accuracy is 75.7%, 75.7%, and 73.0%, respectively. The AUC values are 0.77, 0.80, and 0.75, respectively.

CONCLUSIONS

Machine learning (ML) models can predict angina pectoris caused by the origin anomalous of the right coronary artery, providing valuable auxiliary diagnostic information for clinicians and serving as a warning to clinicians. It is hoped that timely intervention and treatment can be realized to avoid serious consequences such as myocardial infarction.

Coronary Artery Anomalies: A Computed Tomography Angiography Pictorial Review

Coronary arteries have a wide range of anatomical variability, and their spectrum ranges from asymptomatic cases to those predisposed to hemodynamic compromise or even sudden cardiac death. This paper aims to review the classification of coronary artery anomalies (CAAs) and illustrate their imaging characteristics by highlighting the important role of CT coronary angiography. Some of the coronary anomalies usually met in current practice are the high origin coronary artery, multiple ostia, aberrant origin from the opposite/non-coronary Valsalva sinus, single coronary artery, ALCAPA syndrome, duplications of the left anterior descending artery, coronary fistulas, and extracardiac terminations. CT coronary angiography is a non-invasive diagnostic modality for CAAs. The complex anatomy of these anomalies can be accurately described by employing 3D reconstructions and post-processing techniques. Knowledge of the imaging characteristics and potential functional impact of these anomalies is essential for accurate diagnosis and therapeutic planning of patients.

Multislice computerized tomography coronary angiography can be a comparable tool to intravascular ultrasound in evaluating "true" coronary artery bifurcations

Aim

Coronary bifurcation atherosclerosis depends on its angles, flow, and extensive branching. We investigate the ability of CT coronary angiography (CTCA) to determine atherosclerotic plaque characteristics of "true" bifurcation compared with intravascular ultrasound (IVUS) and the influence on side branch (SB) fate after percutaneous coronary intervention (PCI).

Methods and results

The study included 70 patients with 72 "true" bifurcations. Most of the bifurcations were in the left anterior descending-diagonal (Dg) territory [50 out of 72 (69.4%)]. Longitudinal plaque evaluation at the polygon of confluence [carina and 5 mm proximal and distal in the main branch (MB)] showed that carina side MB and SB plaque had occurred with the lowest incidence with fibro-lipid structure (115 ± 63 HU and 89 ± 73 HU, p < 0.001 for all). Bland-Altman analysis showed a discrepancy in measuring mainly the lumen area between CTCA and IVUS in proximal MB [lumen 5.10, 95% CI (95% confidence interval, 4.53-5.68) mm2, p < 0.001; vessel -1.42, 95% CI (-2.63 to -0.21) mm2, p = 0.023], carina MB [lumen 3.74, 95% CI (3.37-4.10) mm2, p < 0.001; vessel -0.48, 95% CI (-1.45 to 0.48) mm2, p = 0.322], and distal MB [lumen 4.72, 95% CI (4.27-5.18) mm2, p < 0.001; vessel 0.62, 95% CI (-0.53 to 1.77) mm2, p = 0.283]. A significant correlation existed between average plaque density on CTCA with a percentage of calcified plaque on IVUS tissue characterization (proximal r = 0.307/p = 0.024, carina 0.469/0.008, distal 0.339/0.024, minimal lumen diameter 0.318/0.020). Circumferential plaque in the proximal MB segment remained an independent predictor of SB compromise [OR 3.962 (95% CI 1.170-13.418)].

Conclusion

Detection and characterization of atherosclerotic plaque by CTCA in non-left main "true" coronary bifurcations can provide useful information about bifurcation anatomy and plaque distribution that can predict outcomes after provisional stenting, thus guiding the interventional strategy to bifurcation PCI.

[Benefits and drawbacks of CT scan as a triple rule-out exam in acute chest pain to exclude acute coronary syndrome, pulmonary embolism and aortic dissection]

Chest pain is one of the major causes for admission in the Emergency Room in most countries and one of the principal reasons for urgent consultation with a cardiologist or a general practitioner. After clinical examination and initial biological measurements, substantial patients require further explorations. CT scan allows the search for pulmonary embolism in the early stage of pulmonary arteries iodine contrast exploration. During the same exam at the systemic arterial phase, the search for aortic dissection or coronary artery disease is possible while exploring the later contrast in the aortic artery. This triple rule-out exam allows correct diagnosis in case of acute chest pain with suspected pulmonary embolism, aortic dissection and other acute aortic syndromes or acute coronary syndrome. But X-rays are substantially increased as well as iodine contrast agent quantity while exam quality is globally decreased. Artificial intelligence may play an important role in the development of this protocol.

Blood Coagulation and Thrombotic Disorders following SARS-CoV-2 Infection and COVID-19 Vaccination

Although abundant data confirm the efficacy and safety profile of the developed vaccines against COVID-19, there are still some concerns regarding vaccination in high-risk populations. This is especially valid for patients susceptible to thrombotic or bleeding events and hesitant people due to the fear of thrombotic incidents following vaccination. This narrative review focuses on various inherited and acquired thrombotic and coagulation disorders and the possible pathophysiologic mechanisms interacting with the coagulation system during immunization in view of the currently available safety data regarding COVID-19 vaccines. Inherited blood coagulation disorders and inherited thrombotic disorders in the light of COVID-19, as well as blood coagulation and thrombotic disorders and bleeding complications following COVID-19 vaccines, along with the possible pathogenesis hypotheses, therapeutic interventions, and imaging for diagnosing are discussed in detail. Lastly, the lack of causality between the bleeding and thrombotic events and COVID-19 vaccines is debated, but still emphasizes the importance of vaccination against COVID-19, outweighing the minimal risk of potential rare adverse events associated with coagulation.

A highly-detailed anatomical study of left atrial auricle as revealed by in-vivo computed tomography

The left atrial auricle (LAA) is the main source of intracardiac thrombi, which contribute significantly to the total number of stroke cases. It is also considered a major site of origin for atrial fibrillation in patients undergoing ablation procedures. The LAA is known to have a high degree of morphological variability, with shape and structure identified as important contributors to thrombus formation. A detailed understanding of LAA form, dimension, and function is crucial for radiologists, cardiologists, and cardiac surgeons. This review describes the normal anatomy of the LAA as visualized through multiple imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI), and echocardiography. Special emphasis is devoted to a discussion on how the morphological characteristics of the LAA are closely related to the likelihood of developing LAA thrombi, including insights into LAA embryology.

Role of integrated imaging in the diagnosis of an atypical and unresectable cardiac paraganglioma: a case report

BACKGROUND

Paragangliomas (PGLs) are rare neuroendocrine tumours that originate from extra-adrenal location. Cardiac PGLs can cause severe hypertension, palpitations, and lethal tachyarrhythmias. Diagnosis is based on measurement of plasma or urine metanephrines combined with conventional and nuclear imaging. Effective treatment is represented by surgical resection. We report a case of a 19-year-old patient with recurrent acute pericarditis; integrated imaging detected a large cardiac mass suggestive for PGL.

CASE SUMMARY

A 19-year-old male suffered pleuritic chest pain and fever for 4 days; electrocardiogram showed inferior ST elevation and transthoracic echocardiography a 2.2 cm pericardial effusion; these findings led to diagnose acute pericarditis. After a relapse of pericarditis, cardiac magnetic resonance and cardiac computed tomography (CCT) were performed, revealing a cardiac mass with radiological features of PGL. Blood and urine tests detected elevated levels of 3-methoxytyramine and chromogranin A. Gallium-68 positron emission tomography confirmed high metabolic activity of the mass. A negative 123-I-MIBG scintigraphy ruled out the possibility of radiometabolic treatment. A second CCT excluded the chance of surgical resection, due to intra-lesional course of the left anterior descending coronary artery. The young patient was referred to a different centre to achieve reduction of the mass, in order to potentially resect it afterwards.

DISCUSSION

Cardiac PGLs are rare tumours with significant morbidity related to norepinephrine secretion. In this case, without typical clinical manifestations and with no chance of surgical resection, integrated imaging played a central role in the differential diagnosis between PGL and other cardiac masses, providing both static and dynamic characterization.

Medical Radiology: Current Progress

Recently, medical radiology has undergone significant improvements in patient management due to advancements in image acquisition by the last generation of machines, data processing, and the integration of artificial intelligence. In this way, cardiovascular imaging is one of the fastest-growing radiological subspecialties. In this study, a compressive review was focused on addressing how and why CT and MR have gained a I class indication in most cardiovascular diseases, and the potential impact of tissue and functional characterization by CT photon counting, quantitative MR mapping, and 4-D flow. Regarding rectal imaging, advances in cancer imaging using diffusion-weighted MRI sequences for identifying residual disease after neoadjuvant chemoradiotherapy and [18F] FDG PET/MRI were provided for high-resolution anatomical and functional data in oncological patients. The results present a large overview of the approach to the imaging of diffuse and focal liver diseases by US elastography, contrast-enhanced US, quantitative MRI, and CT for patient risk stratification. Italy is currently riding the wave of these improvements. The development of large networks will be crucial to create high-quality databases for patient-centered precision medicine using artificial intelligence. Dedicated radiologists with specific training and a close relationship with the referring clinicians will be essential human factors.

Gender Medicine in Clinical Radiology Practice

Gender Medicine is rapidly emerging as a branch of medicine that studies how many diseases common to men and women differ in terms of prevention, clinical manifestations, diagnostic-therapeutic approach, prognosis, and psychological and social impact. Nowadays, the presentation and identification of many pathological conditions pose unique diagnostic challenges. However, women have always been paradoxically underestimated in epidemiological studies, drug trials, as well as clinical trials, so many clinical conditions affecting the female population are often underestimated and/or delayed and may result in inadequate clinical management. Knowing and valuing these differences in healthcare, thus taking into account individual variability, will make it possible to ensure that each individual receives the best care through the personalization of therapies, the guarantee of diagnostic-therapeutic pathways declined according to gender, as well as through the promotion of gender-specific prevention initiatives. This article aims to assess potential gender differences in clinical-radiological practice extracted from the literature and their impact on health and healthcare. Indeed, in this context, radiomics and radiogenomics are rapidly emerging as new frontiers of imaging in precision medicine. The development of clinical practice support tools supported by artificial intelligence allows through quantitative analysis to characterize tissues noninvasively with the ultimate goal of extracting directly from images indications of disease aggressiveness, prognosis, and therapeutic response. The integration of quantitative data with gene expression and patient clinical data, with the help of structured reporting as well, will in the near future give rise to decision support models for clinical practice that will hopefully improve diagnostic accuracy and prognostic power as well as ensure a more advanced level of precision medicine.

Coronary artery calcification-does it predict the CAD-RADS category?

PURPOSE

Coronary calcium scores (CCSs) in cardiac-gated computed tomography (CCT) are diagnostic for coronary artery disease (CAD). This study aims to investigate if CCSs can foretell CAD-reporting and data system (CAD-RADS) without performing computed tomography angiography (CTA).

METHODS

Profiles of 544 patients were studied who had gone through CCT and CTA; the number of calcified regions of interest (ROIs), the Agatston, area, volume, and mass CCSs were calculated. Among the CAD-RADS categories (1 to 5), the mean values were compared for each CCS separately. A cut-offfor each CCS was declared using ROC curve analysis, more than which could predict significant CAD (CAD-RADS 3 to 5). Also, logistic regression models indicated the most probable CAD-RADS category based on the CCSs. P < 0.05 was considered significant.

RESULTS

Among 53% male and 47% female participants with a mean (SD) age of 62.57 (0.84) years, numbers of calcified ROIs were significantly different between each pair of CAD-RADS categories. While other CCSs did not show a significant difference between CAD-RADS 1 and 2 or 2 and 3. All CCSs were significantly different between the non-significant and significant CAD groups; cut-offs for the number of calcified ROIs, the Agatston, area, volume, and mass scores were 9, 128, 44mm2, 111mm3, and 22 mg, respectively. Formulae A and B predicted the most probable CAD-RADS category (accuracy: 79%) and the probability of significant/non-significant CAD (accuracy: 81%), respectively.

CONCLUSION

CCSs could predict CAD-RADS with an accuracy of 80%. Further studies are needed to introduce more predictive calcium indices.

Study on the Relationship between Different Body Mass Indexes and Puncture Pain and Image Quality in Patients Undergoing Coronary Angiography with Intravenous Indwelling Needle

Objective

To investigate the effect of different body mass indexes (BMIs) on patients' puncture pain, puncture success rate, and image quality in coronary angiography (CAG) performed with an intravenous indwelling needle, and to provide a basis for selecting the appropriate intravenous indwelling needle for CAG in patients with different BMIs in an outpatient clinic.

Method

In this study, 300 patients undergoing CTA at the department of radiology in the First Affiliated Hospital of Wenzhou Medical University from January to May 2021 were divided into group 1 (BMI 1 ≤ 18.5), group 2 (18.5 < BMI ≤ 24), and group 3 (BMI > 24) according to their BMI, with 100 cases in each group, and a 20 G intravenous indwelling needle was used in each group. The age, sex, height, and weight of each patient were recorded, and the primary puncture success rate, contrast leakage rate, injection success rate, pain perception, and subjective ratings of image quality and objective indicators were compared in patients with different BMI values.

Results

There was no statistically significant difference between the age, gender, and heart rate of the patients in the three groups (P > 0.05). There was no statistically significant difference between the primary puncture success rate, injection success rate, and contrast leakage rate of the three groups of patients (P > 0.05). The pain scores of group 3 during contrast injection were significantly higher than those of the remaining two groups (P < 0.05), while the differences between the pain scores of group 2 and group 1 during contrast injection were not statistically significant (P > 0.05); the comparison of the pain scores of the three groups during puncture and during retention was not statistically significant (P > 0.05). The differences between the subjective ratings of image quality and the objective indicators of the three groups were not statistically significant (P > 0.05).

Conclusion

The 20 G indwelling needle can basically meet the coronary angiography examination of patients with different body mass indexes, but patients with a BMI greater than 24 are recommended to use a larger diameter indwelling needle to reduce contrast leakage as well as to reduce patient pain and improve patient comfort.