Artificial intelligence and machine learning in aortic disease

Unsupervised classification of multi-contrast magnetic resonance histology of peripheral arterial disease lesions using a convolutional variational autoencoder with a Gaussian mixture model in latent space: A technical feasibility study

PURPOSE

To investigate the feasibility of a deep learning algorithm combining variational autoencoder (VAE) and two-dimensional (2D) convolutional neural networks (CNN) for automatically quantifying hard tissue presence and morphology in multi-contrast magnetic resonance (MR) images of peripheral arterial disease (PAD) occlusive lesions.

METHODS

Multi-contrast MR images (T2-weighted and ultrashort echo time) were acquired from lesions harvested from six amputated legs with high isotropic spatial resolution (0.078 mm and 0.156 mm, respectively) at 9.4 T. A total of 4014 pseudo-color combined images were generated, with 75% used to train a VAE employing custom 2D CNN layers. A Gaussian mixture model (GMM) was employed to classify the latent space data into four tissue classes: I) concentric calcified (c), II) eccentric calcified (e), III) occluded with hard tissue (h) and IV) occluded with soft tissue (s). Test image probabilities, encoded by the trained VAE were used to evaluate model performance.

RESULTS

GMM component classification probabilities ranged from 0.92 to 0.97 for class (c), 1.00 for class (e), 0.82-0.95 for class (h) and 0.56-0.93 for the remaining class (s). Due to the complexity of soft-tissue lesions reflected in the heterogeneity of the pseudo-color images, more GMM components (n=17) were attributed to class (s), compared to the other three (c, e and h) (n=6).

CONCLUSION

Combination of 2D CNN VAE and GMM achieves high classification probabilities for hard tissue-containing lesions. Automatic recognition of these classes may aid therapeutic decision-making and identifying uncrossable lesions prior to endovascular intervention.

Rapid segmentation of computed tomography angiography images of the aortic valve: the efficacy and clinical value of a deep learning algorithm

Objectives

The goal of this study was to explore the reliability and clinical value of fast, accurate automatic segmentation of the aortic root based on a deep learning tool compared with computed tomography angiography.

Methods

A deep learning tool for automatic 3-dimensional aortic root reconstruction, the CVPILOT system (TAVIMercy Data Technology Ltd., Nanjing, China), was trained and tested using computed tomography angiography scans collected from 183 patients undergoing transcatheter aortic valve replacement from January 2021 to December 2022. The quality of the reconstructed models was assessed using validation data sets and evaluated clinically by experts.

Results

The segmentation of the ascending aorta and the left ventricle attained Dice similarity coefficients (DSC) of 0.9806/0.9711 and 0.9603/0.9643 for the training and validation sets, respectively. The leaflets had a DSC of 0.8049/0.7931, and the calcification had a DSC of 0.8814/0.8630. After 6 months of application, the system modeling time was reduced to 19.83 s.

Conclusion

For patients undergoing transcatheter aortic valve replacement, the CVPILOT system facilitates clinical workflow. The reliable evaluation quality of the platform indicates broad clinical application prospects in the future.

Deep learning algorithm applied to plain CT images to identify superior mesenteric artery abnormalities

OBJECTIVES

Atypical presentations, lack of biomarkers, and low sensitivity of plain CT can delay the diagnosis of superior mesenteric artery (SMA) abnormalities, resulting in poor clinical outcomes. Our study aims to develop a deep learning (DL) model for detecting SMA abnormalities in plain CT and evaluate its performance in comparison with a clinical model and radiologist assessment.

MATERIALS AND METHODS

A total of 1048 patients comprised the internal (474 patients with SMA abnormalities, 474 controls) and external testing (50 patients with SMA abnormalities, 50 controls) cohorts. The internal cohort was divided into the training cohort (n = 776), validation cohort (n = 86), and internal testing cohort (n = 86). A total of 5 You Only Look Once version 8 (YOLOv8)-based DL submodels were developed, and the performance of the optimal submodel was compared with that of a clinical model and of experienced radiologists.

RESULTS

Of the submodels, YOLOv8x had the best performance. The area under the curve (AUC) of the YOLOv8x submodel was higher than that of the clinical model (internal test set: 0.990 vs 0.878, P =.002; external test set: 0.967 vs 0.912, P =.140) and that of all radiologists (P <.001). The YOLOv8x submodel, when compared with radiologist assessment, demonstrated higher sensitivity (internal test set: 100.0 % vs 70.7 %, P =.002; external test set: 96.0 % vs 68.8 %, P <.001) and specificity (internal test set: 90.7 % vs 66.0 %, P =.025; external test set: = 88.0 % vs 66.0 %, P <.001).

CONCLUSION

Using plain CT images, YOLOv8x was able to efficiently identify cases of SMA abnormalities. This could potentially improve early diagnosis accuracy and thus improve clinical outcomes.

Using machine learning to predict outcomes following open abdominal aortic aneurysm repair

OBJECTIVE

Prediction of outcomes following open abdominal aortic aneurysm (AAA) repair remains challenging with a lack of widely used tools to guide perioperative management. We developed machine learning (ML) algorithms that predict outcomes following open AAA repair.

METHODS

The Vascular Quality Initiative (VQI) database was used to identify patients who underwent elective open AAA repair between 2003 and 2023. Input features included 52 preoperative demographic/clinical variables. All available preoperative variables from VQI were used to maximize predictive performance. The primary outcome was in-hospital major adverse cardiovascular event (MACE; composite of myocardial infarction, stroke, or death). Secondary outcomes were individual components of the primary outcome, other in-hospital complications, and 1-year mortality and any reintervention. We split our data into training (70%) and test (30%) sets. Using 10-fold cross-validation, six ML models were trained using preoperative features (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score. The top 10 predictive features in our final model were determined based on variable importance scores. Performance was assessed on subgroups based on age, sex, race, ethnicity, rurality, median area deprivation index, proximal clamp site, prior aortic surgery, and concomitant procedures.

RESULTS

Overall, 12,027 patients were included. The primary outcome of in-hospital MACE occurred in 630 patients (5.2%). Compared with patients without a primary outcome, those who developed in-hospital MACE were older with more comorbidities, demonstrated poorer functional status, had more complex aneurysms, and were more likely to require concomitant procedures. Our best performing prediction model for in-hospital MACE was XGBoost, achieving an AUROC of 0.93 (95% confidence interval, 0.92-0.94). Comparatively, logistic regression had an AUROC of 0.71 (95% confidence interval, 0.70-0.73). For secondary outcomes, XGBoost achieved AUROCs between 0.84 and 0.94. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.05. These findings highlight the excellent predictive performance of the XGBoost model. The top three predictive features in our algorithm for in-hospital MACE following open AAA repair were: (1) coronary artery disease; (2) American Society of Anesthesiologists classification; and (3) proximal clamp site. Model performance remained robust on all subgroup analyses.

CONCLUSIONS

Open AAA repair outcomes can be accurately predicted using preoperative data with our ML models, which perform better than logistic regression. Our automated algorithms can help guide risk-mitigation strategies for patients being considered for open AAA repair to improve outcomes.

Machine learning to predict outcomes following endovascular abdominal aortic aneurysm repair

BACKGROUND

Endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA) carries important perioperative risks; however, there are no widely used outcome prediction tools. The aim of this study was to apply machine learning (ML) to develop automated algorithms that predict 1-year mortality following EVAR.

METHODS

The Vascular Quality Initiative database was used to identify patients who underwent elective EVAR for infrarenal AAA between 2003 and 2023. Input features included 47 preoperative demographic/clinical variables. The primary outcome was 1-year all-cause mortality. Data were split into training (70 per cent) and test (30 per cent) sets. Using 10-fold cross-validation, 6 ML models were trained using preoperative features with logistic regression as the baseline comparator. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score.

RESULTS

Some 63 655 patients were included. One-year mortality occurred in 3122 (4.9 per cent) patients. The best performing prediction model for 1-year mortality was XGBoost, achieving an AUROC (95 per cent c.i.) of 0.96 (0.95-0.97). Comparatively, logistic regression had an AUROC (95 per cent c.i.) of 0.69 (0.68-0.71). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.04. The top 3 predictive features in the algorithm were 1) unfit for open AAA repair, 2) functional status, and 3) preoperative dialysis.

CONCLUSIONS

In this data set, machine learning was able to predict 1-year mortality following EVAR using preoperative data and outperformed standard logistic regression models.

Utilizing convolutional neural networks to classify monkeypox skin lesions

Monkeypox is a rare viral disease that can cause severe illness in humans, presenting with skin lesions and rashes. However, accurately diagnosing monkeypox based on visual inspection of the lesions can be challenging and time-consuming, especially in resource-limited settings where laboratory tests may not be available. In recent years, deep learning methods, particularly Convolutional Neural Networks (CNNs), have shown great potential in image recognition and classification tasks. To this end, this study proposes an approach using CNNs to classify monkeypox skin lesions. Additionally, the study optimized the CNN model using the Grey Wolf Optimizer (GWO) algorithm, resulting in a significant improvement in accuracy, precision, recall, F1-score, and AUC compared to the non-optimized model. The GWO optimization strategy can enhance the performance of CNN models on similar tasks. The optimized model achieved an impressive accuracy of 95.3%, indicating that the GWO optimizer has improved the model's ability to discriminate between positive and negative classes. The proposed approach has several potential benefits for improving the accuracy and efficiency of monkeypox diagnosis and surveillance. It could enable faster and more accurate diagnosis of monkeypox skin lesions, leading to earlier detection and better patient outcomes. Furthermore, the approach could have crucial public health implications for controlling and preventing monkeypox outbreaks. Overall, this study offers a novel and highly effective approach for diagnosing monkeypox, which could have significant real-world applications.

Mechanism Analysis of Vascular Calcification Based on Fluid Dynamics

Vascular calcification is the abnormal deposition of calcium phosphate complexes in blood vessels, which is regarded as the pathological basis of multiple cardiovascular diseases. The flowing blood exerts a frictional force called shear stress on the vascular wall. Blood vessels have different hydrodynamic properties due to discrepancies in geometric and mechanical properties. The disturbance of the blood flow in the bending area and the branch point of the arterial tree produces a shear stress lower than the physiological magnitude of the laminar shear stress, which can induce the occurrence of vascular calcification. Endothelial cells sense the fluid dynamics of blood and transmit electrical and chemical signals to the full-thickness of blood vessels. Through crosstalk with endothelial cells, smooth muscle cells trigger osteogenic transformation, involved in mediating vascular intima and media calcification. In addition, based on the detection of fluid dynamics parameters, emerging imaging technologies such as 4D Flow MRI and computational fluid dynamics have greatly improved the early diagnosis ability of cardiovascular diseases, showing extremely high clinical application prospects.

Clinical Characteristics and Outcomes of Aortic Arch Emergencies: Takayasu Disease, Fibromuscular Dysplasia, and Aortic Arch Pathologies: A Retrospective Study and Review of the Literature

Non-atherosclerotic aortic arch pathologies (NA-AAPs) and anatomical variants are characterized as rare cardiovascular diseases with a low incidence rate, below 1 case per 2000 population, but enormous heterogeneity in terms of anatomical variants, i.e., Takayasu disease (TAK) and fibromuscular dysplasia (FMD). In specific clinical scenarios, NA-AAPs constitute life-threatening disorders.

METHODS

In this study, 82 (1.07%) consecutive patients with NA-AAPs (including 38 TAKs, 26 FMDs, and 18 other AAPs) out of 7645 patients who underwent endovascular treatment (EVT) for the aortic arch and its side-branch diseases at a single institution between 2002 and 2022 were retrospectively reviewed. The recorded demographic, biochemical, diagnostic, operative, and postoperative factors were reviewed, and the functional outcomes were determined during follow-up. A systematic review of the literature was also performed.

RESULTS

The study group comprised 65 (79.3%) female and 17 (21.7%) male subjects with a mean age of 46.1 ± 14.9 years. Overall, 62 (75.6%) patients were diagnosed with either cerebral ischemia symptoms or aortic arch dissection on admission. The EVT was feasible in 59 (72%) patients, whereas 23 (28%) patients were referred for medical treatment. In EVT patients, severe periprocedural complications occurred in two (3.39%) patients, including one periprocedural death and one cerebral hyperperfusion syndrome. During a median follow-up period of 64 months, cardiovascular events occurred in 24 (29.6%) patients (5 deaths, 13 ISs, and 6 myocardial infarctions). Repeated EVT for the index lesion was performed in 21/59 (35.6%) patients, including 19/33 (57.6%) in TAK and 2/13 (15.4%) in FMD. In the AAP group, one patient required additional stent-graft implantation for progressing dissection to the iliac arteries at 12 months. A baseline white blood count (odds ratio [HR]: 1.25, 95% confidence interval [CI]: 1.11-1.39; p < 0.001) was the only independent prognostic factor for recurrent stenosis, while a baseline hemoglobin level (HR: 0.73, 95%CI: 0.59-0.89; p = 0.002) and coronary involvement (HR: 4.11, 95%CI: 1.74-9.71; p = 0.001) were independently associated with a risk of major cardiac and cerebral events according to the multivariate Cox proportional hazards regression analysis.

CONCLUSIONS

This study showed that AAPs should not be neglected in clinical settings, as it can be a life-threatening condition requiring a multidisciplinary approach. The knowledge of prognostic risk factors for adverse outcomes may improve surveillance in this group of patients.

Deep Learning Prediction for Distal Aortic Remodeling After Thoracic Endovascular Aortic Repair in Stanford Type B Aortic Dissection

PURPOSE

This study aimed to develop a deep learning model for predicting distal aortic remodeling after proximal thoracic endovascular aortic repair (TEVAR) in patients with Stanford type B aortic dissection (TBAD) using computed tomography angiography (CTA).

METHODS

A total of 147 patients with acute or subacute TBAD who underwent proximal TEVAR at a single center were retrospectively reviewed. The boundary of aorta was manually segmented, and the point clouds of each aorta were obtained. Prediction of negative aortic remodeling or reintervention was accomplished by a convolutional neural network (CNN) and a point cloud neural network (PC-NN), respectively. The discriminatory value of the established models was mainly evaluated by the area under the receiver operating characteristic curve (AUC) in the test set.

RESULTS

The mean follow-up time was 34.0 months (range: 12-108 months). During follow-up, a total of 25 (17.0%) patients were identified as having negative aortic remodeling, and 16 (10.9%) patients received reintervention. The AUC (0.876) by PC-NN for predicting negative aortic remodeling was superior to that obtained by CNN (0.612, p=0.034) and similar to the AUC by PC-NN combined with clinical features (0.884, p=0.92). As to reintervention, the AUC by PC-NN was significantly higher than that by CNN (0.805 vs 0.579; p=0.042), and AUCs by PC-NN combined with clinical features and PC-NN alone were comparable (0.836 vs 0.805; p=0.81).

CONCLUSION

The CTA-based deep learning algorithms may assist clinicians in automated prediction of distal aortic remodeling after TEVAR for acute or subacute TBAD.

CLINICAL IMPACT

Negative aortic remodeling is the leading cause of late reintervention after proximal thoracic endovascular aortic repair (TEVAR) for Stanford type B aortic dissection (TBAD), and possesses great challenge to endovascular repair. Early recognizing high-risk patients is of supreme importance for optimizing the follow-up interval and therapy strategy. Currently, clinicians predict the prognosis of these patients based on several imaging signs, which is subjective. The computed tomography angiography-based deep learning algorithms may incorporate abundant morphological information of aorta, provide with a definite and objective output value, and finally assist clinicians in automated prediction of distal aortic remodeling after TEVAR for acute or subacute TBAD.

Acute aortic dissection

Although substantial progress has been made in the prevention, diagnosis, and treatment of acute aortic dissection, it remains a complex cardiovascular event, with a high immediate mortality and substantial morbidity in individuals surviving the acute period. The past decade has allowed a leap forward in understanding the pathophysiology of this disease; the existing classifications have been challenged, and the scientific community moves towards a nomenclature that is likely to unify the current definitions according to morphology and function. The most important pathophysiological pathway, namely the location and extension of the initial intimal tear, which causes a disruption of the media layer of the aortic wall, together with the size of the affected aortic segments, determines whether the patient should undergo emergency surgery, an endovascular intervention, or receive optimal medical treatment. The scientific evidence for the management and follow-up of acute aortic dissection continues to evolve. This Seminar provides a clinically relevant overview of potential prevention, diagnosis, and management of acute aortic dissection, which is the most severe acute aortic syndrome.

Assessment of shape-based features ability to predict the ascending aortic aneurysm growth

The current guidelines for the ascending aortic aneurysm (AsAA) treatment recommend surgery mainly according to the maximum diameter assessment. This criterion has already proven to be often inefficient in identifying patients at high risk of aneurysm growth and rupture. In this study, we propose a method to compute a set of local shape features that, in addition to the maximum diameter D, are intended to improve the classification performances for the ascending aortic aneurysm growth risk assessment. Apart from D, these are the ratio DCR between D and the length of the ascending aorta centerline, the ratio EILR between the length of the external and the internal lines and the tortuosity T. 50 patients with two 3D acquisitions at least 6 months apart were segmented and the growth rate (GR) with the shape features related to the first exam computed. The correlation between them has been investigated. After, the dataset was divided into two classes according to the growth rate value. We used six different classifiers with input data exclusively from the first exam to predict the class to which each patient belonged. A first classification was performed using only D and a second with all the shape features together. The performances have been evaluated by computing accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC) and positive (negative) likelihood ratio LHR+ (LHR-). A positive correlation was observed between growth rate and DCR (r = 0.511, p = 1.3e-4) and between GR and EILR (r = 0.472, p = 2.7e-4). Overall, the classifiers based on the four metrics outperformed the same ones based only on D. Among the diameter-based classifiers, k-nearest neighbours (KNN) reported the best accuracy (86%), sensitivity (55.6%), AUROC (0.74), LHR+ (7.62) and LHR- (0.48). Concerning the classifiers based on the four shape features, we obtained the best accuracy (94%), sensitivity (66.7%), specificity (100%), AUROC (0.94), LHR+ (+∞) and LHR- (0.33) with support vector machine (SVM). This demonstrates how automatic shape features detection combined with risk classification criteria could be crucial in planning the follow-up of patients with ascending aortic aneurysm and in predicting the possible dangerous progression of the disease.

Artificial intelligence: Advances and new frontiers in medical imaging

Artificial intelligence (AI) has been entwined with the field of radiology ever since digital imaging began replacing films over half a century ago. These algorithms, ranging from simplistic speech-to-text dictation programs to automated interpretation neural networks, have continuously sought to revolutionize medical imaging. With the number of imaging studies outpacing the amount of trained of readers, AI has been implemented to streamline workflow efficiency and provide quantitative, standardized interpretation. AI relies on massive amounts of data for its algorithms to function, and with the wide-spread adoption of Picture Archiving and Communication Systems (PACS), imaging data is accumulating rapidly. Current AI algorithms using machine-learning technology, or computer aided-detection, have been able to successfully pool this data for clinical use, although the scope of these algorithms remains narrow. Many systems have been developed to assist the workflow of the radiologist through PACS optimization and imaging study triage, however interpretation has generally remained a human responsibility for now. In this review article, we will summarize the current successes and limitations of AI in radiology, and explore the exciting prospects that deep-learning technology offers for the future.

Why 4D Flow MRI? Real Advantages

This special issue of Magnetic Resonance in Medical Sciences features the most recent reviews on 4D Flow MRI. These reviews deal with the current status of the emerging technique of 4D Flow MRI facilitated in various areas that are difficult to obtain with conventional flowmetry. MR signals inherently contain flow velocity information. In previous decades, in vivo blood flow measurement was traditionally performed by 2D methods, such as Doppler ultrasonography and 2D phase-contrast MRI, which have long been regarded as mature techniques in hemodynamic flowmetry. Although 2D velocimetries have many advantages over 4D Flow MRI in terms of cost and accessibility, and provide excellent temporal and in-plane spatial resolutions, they also have some disadvantages. The emerging technology of 4D Flow MRI can overcome the shortcomings of conventional 2D imaging. In recent years, hemodynamic analysis has witnessed significant progress that is primarily attributable to advances in 4D Flow MRI.

A Combined Deep Learning System for Automatic Detection of “Bovine” Aortic Arch on Computed Tomography Scans

The “bovine” aortic arch is an anatomic variant consisting in a common origin of the innominate and left carotid artery (CILCA), associated with a greater risk of thoracic aortic diseases (aneurysms and dissections), stroke, and complications after endovascular procedures. CILCA can be detected by visual assessment of computed tomography (CT) chest scans, but it is rarely reported. We developed a deep learning (DL) segmentation-plus-classification system to automatically detect CILCA based on 302 CT studies acquired at 2 centers. One model (3D U-Net) was trained from scratch (supervised by manual segmentation), validated, and tested for the automatic segmentation of the aortic arch and supra-aortic vessels. Three DL architectures (ResNet50, DenseNet-201, and SqueezeNet), pre-trained over millions of common images, were trained, validated, and tested for the automatic classification of CILCA versus non-CILCA, supervised by radiologist’s classification. The 3D U-Net-plus-DenseNet-201 was found to be the best system (Dice index 0.912); its classification performance obtained from internal, independent testing on 126 patients gave a receiver operating characteristic area under the curve of 87.0%, sensitivity 66.7%, specificity 90.5%, positive predictive value 87.5%, negative predictive value 73.1%, positive likelihood ratio 7.0, and negative likelihood ratio 0.4. In conclusion, a combined DL system applied to chest CT scans was developed and proven to be an effective tool to detect individuals with “bovine” aortic arch with a low rate of false-positive findings.

Artificial intelligence's role in vascular surgery decision-making

Artificial intelligence (AI) is the next great advance informing medical science. Several disciplines, including vascular surgery, use AI-based decision-making tools to improve clinical performance. Although applied widely, AI functions best when confronted with voluminous, accurate data. Consistent, predictable analytic technique selection also challenges researchers. This article contextualizes AI analyses within evidence-based medicine, focusing on "big data" and health services research, as well as discussing opportunities to improve data collection and realize AI's promise.

Artificial Intelligence in Vascular-PET:: Translational and Clinical Applications

Positron emission tomography (PET) offers an incredible wealth of diverse research applications in vascular disease, providing a depth of molecular, functional, structural, and spatial information. Despite this, vascular PET imaging has not yet assumed the same clinical use as vascular ultrasound, CT, and MR imaging which provides information about late-onset, structural tissue changes. The current clinical utility of PET relies heavily on visual inspection and suboptimal parameters such as SUVmax; emerging applications have begun to harness the tool of whole-body PET to better understand the disease. Even still, without automation, this is a time-consuming and variable process. This review summarizes PET applications in vascular disorders, highlights emerging AI methods, and discusses the unlocked potential of AI in the clinical space.