Thoracic Aorta Calcium Detection and Quantification Using Convolutional Neural Networks in a Large Cohort of Intermediate-Risk Patients

Deep learning for automatic calcium detection in echocardiography

Cardiovascular diseases are the main cause of death in the world and cardiovascular imaging techniques are the mainstay of noninvasive diagnosis. Aortic stenosis is a lethal cardiac disease preceded by aortic valve calcification for several years. Data-driven tools developed with Deep Learning (DL) algorithms can process and categorize medical images data, providing fast diagnoses with considered reliability, to improve healthcare effectiveness. A systematic review of DL applications on medical images for pathologic calcium detection concluded that there are established techniques in this field, using primarily CT scans, at the expense of radiation exposure. Echocardiography is an unexplored alternative to detect calcium, but still needs technological developments. In this article, a fully automated method based on Convolutional Neural Networks (CNNs) was developed to detect Aortic Calcification in Echocardiography images, consisting of two essential processes: (1) an object detector to locate aortic valve - achieving 95% of precision and 100% of recall; and (2) a classifier to identify calcium structures in the valve - which achieved 92% of precision and 100% of recall. The outcome of this work is the possibility of automation of the detection with Echocardiography of Aortic Valve Calcification, a lethal and prevalent disease.

Abdominal aortic calcium and geometry in patients with essential hypertension

PURPOSE

Abdominal aorta calcium (AAC) burden and dilatation are associated with an increased risk of mortality. The purpose of this study was to investigate determinants of AAC and abdominal aorta size in patients with essential hypertension.

MATERIALS AND METHODS

Patients with uncomplicated essential hypertension who had undergone non-enhanced abdominal CT to rule out secondary hypertension in addition to biological test were recruited between 2010 and 2018. A semi-automatic system was designed to estimate the aortic size (diameter, length, volume) and quantify the AAC from mesenteric artery to bifurcation using the Agatston score. Determinants of aortic size and those related to AAC were searched for using uni- and multivariables analyses.

RESULTS

Among 293 randomly selected patients with hypertension (age 52 ± 11 [SD] years) included, 23% had resistant hypertension. Mean abdominal aorta diameter was 20.1 ± 2.1 (SD) mm. Eight (3%) patients had abdominal aorta aneurysm ≥ 30 mm and 58 (20%) had dilated abdominal aorta ≥ 27 mm. Median AAC score was 38 and calcifications were detected in the infra- and supra-renal abdominal aortic portions in 59% and 26% of the patients, respectively. After adjustment for age, male sex and body surface area, abdominal aorta diameter was positively associated with diastolic blood pressure (P = 0.0019). Smoking was the single variable associated with calcified abdominal aorta (P < 0.001) after adjustment for cofactors. In patients with calcifications of abdominal aorta, the score increased with smoking history (P < 0.001), statins treatment (P < 0.01), greater number of anti-hypertensive drugs (P < 0.01), larger abdominal aorta (P < 0.05) and greater systolic blood pressure (P < 0.05). Patients with resistant hypertension had more AAC in the supra-renal abdominal aorta portion than those without resistant hypertension (P < 0.01).

CONCLUSION

In patients with essential hypertension, abdominal aorta dilation is related with diastolic blood pressure while AAC is associated with smoking history and resistant hypertension when located to the supra-renal abdominal aorta portion.

Automatic 3D Segmentation and Identification of Anomalous Aortic Origin of the Coronary Arteries Combining Multi-view 2D Convolutional Neural Networks

This work aimed to automatically segment and classify the coronary arteries with either normal or anomalous origin from the aorta (AAOCA) using convolutional neural networks (CNNs), seeking to enhance and fasten clinician diagnosis. We implemented three single-view 2D Attention U-Nets with 3D view integration and trained them to automatically segment the aortic root and coronary arteries of 124 computed tomography angiographies (CTAs), with normal coronaries or AAOCA. Furthermore, we automatically classified the segmented geometries as normal or AAOCA using a decision tree model. For CTAs in the test set (n = 13), we obtained median Dice score coefficients of 0.95 and 0.84 for the aortic root and the coronary arteries, respectively. Moreover, the classification between normal and AAOCA showed excellent performance with accuracy, precision, and recall all equal to 1 in the test set. We developed a deep learning-based method to automatically segment and classify normal coronary and AAOCA. Our results represent a step towards an automatic screening and risk profiling of patients with AAOCA, based on CTA.

Predictive factors of thoracic aortic calcification in patients candidate for cardiac surgery

BACKGROUND

The presence of the severe thoracic aortic calcification (TAC) in cardiac surgery patients is associated with adverse post-operative outcome. However, the relationship between cardiovascular risk factors and aortic plaque burden remains unknown. The objective of this study was to determine the predictive factors of TAC in patients candidate for cardiac surgery.

METHODS

Patients who underwent thoracic CT scan prior to cardiac surgery between August 2020 to April 2021 were included. Of 556 patients, 209 (36.7%) had a thoracic aortic calcium score (TACS) ≥ 400 mm [3] and were compare with the remaining patients. Predictors of severe TAC were assessed through stepwise multivariable logistic regression analysis.

RESULTS

The patients with TACS ≥ 400 had a higher mean age (67.3 ± 7.1 vs. 55.7 ± 10.6; p < 0.001) with a higher frequency of diabetes mellitus (40.7% vs. 30.8%; p = 0.018), dyslipidemia (49.8% vs. 38.6%; p = 0.010), hypertension (60.8% vs. 44.7%; p < 0.001), opium addiction (18.2% vs. 11.2%; p = 0.023), peripheral vascular disease (PVD) (7.7% vs. 2.3%; p = 0.005) as compared with TACS < 400. The multiple determinants of TAC were PVD (OR = 2.86) followed by opium addiction, diabetes and age.

CONCLUSIONS

Thoracic CT scan prior to cardiac surgery for patients with older age, diabetes, opium addiction and PVD is recommended. Our study could serve as a foundation for future research endeavors aimed at establishing a risk score for TAC.

Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images

Thoracic aorta calcium (TAC) can be assessed from cardiac computed tomography (CT) studies to improve cardiovascular risk prediction. The aim of this study was to develop a fully automatic system to detect TAC and to evaluate its performance for classifying the patients into four TAC risk categories. The method started by segmenting the thoracic aorta, combining three UNets trained with axial, sagittal and coronal CT images. Afterwards, the surrounding lesion candidates were classified using three combined convolutional neural networks (CNNs) trained with orthogonal patches. Image datasets included 1190 non-enhanced ECG-gated cardiac CT studies from a cohort of cardiovascular patients (age 57 ± 9 years, 80% men, 65% TAC > 0). In the test set (N = 119), the combination of UNets was able to successfully segment the thoracic aorta with a mean volume difference of 0.3 ± 11.7 ml (<6%) and a median Dice coefficient of 0.947. The combined CNNs accurately classified the lesion candidates and 87% of the patients (N = 104) were accurately placed in their corresponding risk categories (Kappa = 0.826, ICC = 0.9915). TAC measurement can be estimated automatically from cardiac CT images using UNets to isolate the thoracic aorta and CNNs to classify calcified lesions.

Role and progress of artificial intelligence in radiodiagnosing vascular calcification: a narrative review

Background and Objective

Vascular calcification has important clinical significance due to its vital prognostic value for cardiovascular diseases, chronic kidney disease (CKD), diabetes, fracture, and other multisystem diseases. Radiology is the main diagnostic method of it, but facing great pressure such as the increasing workload and decreasing working accuracy rate. Therefore, radiology needs to find a way out to better realize the clinical value of vascular calcification. Artificial intelligence (AI) encompasses any algorithm imitating human intelligence. AI has shown great potential in image analysis, such as its high speed and accuracy, becoming the savior of the current situation. In order to promote more rational utilization, the role and progress of AI in this field were reviewed.

Methods

A search was conducted in PubMed and Web of Science. The key words included "artificial intelligence", "machine learning", "deep learning", and "vascular calcification". The qualitative analysis of literature was achieved through repeated deliberation after refining valuable content. The theme is the role and progress of AI in the diagnostic radiology of vascular calcification.

Key Content and Findings

Sixty-two articles were included. AI has been applied to the diagnostic radiology of 5 types of vascular calcification, including coronary artery calcification (CAC), thoracic aortic calcification (TAC), abdominal aortic calcification (AAC), carotid artery calcification, and breast artery calcification (BAC). Deep learning (DL), the latest technology in this field has been well applied and satisfactorily performed. Radiologists have been able to achieve efficient diagnosis of 5 types of vascular calcification through AI, with reliable accuracy.

Conclusions

Increasingly, advanced AI has achieved an accuracy comparable to that of human experts, with a faster speed. Moreover, the ability to reduce noise and artifacts enables more imaging equipment to obtain reliable quantification. AI has acquired the ability to cooperate with radiology departments in future work. However, the research in AAC and carotid artery calcification can be more in-depth, and more types of vascular calcification and more fields of radiology should be expanded to. The interpretation of results made by AI and the promotion of existing achievements to the development of other disciplines are also the focus in future.

Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review

Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.