Semi-automatic vessel detection for challenging cases of peripheral arterial 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.

The impact of multiple stenosis and aneurysms on arterial diseases: A cardiovascular study

The comparative effect of serial stenosis and aneurysms arteries on blood flow is examined to identify atherosclerotic diseases. The finite element approach has been used to solve the continuity, momentum, and Oldroyd-B partial differential equations to analyze the blood flow. Newtonian and non-Newtonian both cases are taken for the viscoelastic response of blood. In this study, the impact of multiple stenotic and aneurysmal arteries on blood flow have been studied to determine the severity of atherosclerosis diseases through the analysis of blood behavior. The novel aspect of the study is its assessment of the severity of atherosclerotic disorders for the occurrence of serial stenosis and aneurysm simultaneously in the blood vessel wall in each of the four cases. The maximum abnormal arterial blood flow effect is found for the presence of serial stenoses compared to aneurysms which refers to the severity of atherosclerosis. At the hub of stenosis, the blood velocity magnitude and wall shear stress (WSS) are higher, whereas the arterial wall normal gradient values are lower. For all cases, the contrary results are observed at the hub of the aneurysmal model. The blood flow has been affected significantly by the increases in Reynolds number for both models. The influence of stenotic and aneurysmal arteries on blood flow is graphically illustrated in terms of the velocity profile, pressure distribution, and WSS. Medical experts may use this study's findings to assess the severity of cardiovascular diseases.

Multi-Modality Imaging of Atheromatous Plaques in Peripheral Arterial Disease: Integrating Molecular and Imaging Markers

Peripheral artery disease (PAD) is a common and debilitating condition characterized by the narrowing of the limb arteries, primarily due to atherosclerosis. Non-invasive multi-modality imaging approaches using computed tomography (CT), magnetic resonance imaging (MRI), and nuclear imaging have emerged as valuable tools for assessing PAD atheromatous plaques and vessel walls. This review provides an overview of these different imaging techniques, their advantages, limitations, and recent advancements. In addition, this review highlights the importance of molecular markers, including those related to inflammation, endothelial dysfunction, and oxidative stress, in PAD pathophysiology. The potential of integrating molecular and imaging markers for an improved understanding of PAD is also discussed. Despite the promise of this integrative approach, there remain several challenges, including technical limitations in imaging modalities and the need for novel molecular marker discovery and validation. Addressing these challenges and embracing future directions in the field will be essential for maximizing the potential of molecular and imaging markers for improving PAD patient outcomes.

Applications of artificial intelligence for patients with peripheral artery disease

OBJECTIVE

Applications of artificial intelligence (AI) have been reported in several cardiovascular diseases but its interest in patients with peripheral artery disease (PAD) has been so far less reported. The aim of this review was to summarize current knowledge on applications of AI in patients with PAD, to discuss current limits, and highlight perspectives in the field.

METHODS

We performed a narrative review based on studies reporting applications of AI in patients with PAD. The MEDLINE database was independently searched by two authors using a combination of keywords to identify studies published between January 1995 and December 2021. Three main fields of AI were investigated including natural language processing (NLP), computer vision and machine learning (ML).

RESULTS

NLP and ML brought new tools to improve the screening, the diagnosis and classification of the severity of PAD. ML was also used to develop predictive models to better assess the prognosis of patients and develop real-time prediction models to support clinical decision-making. Studies related to computer vision mainly aimed at creating automatic detection and characterization of arterial lesions based on Doppler ultrasound examination or computed tomography angiography. Such tools could help to improve screening programs, enhance diagnosis, facilitate presurgical planning, and improve clinical workflow.

CONCLUSIONS

AI offers various applications to support and likely improve the management of patients with PAD. Further research efforts are needed to validate such applications and investigate their accuracy and safety in large multinational cohorts before their implementation in daily clinical practice.