Machine learning and image analysis in vascular surgery

Eco-Color Doppler, Intelligenza Artificiale

Authors: Roger T. Tomihama, Saharsh Dass, Sally Chen, Sharon C. Kiang

Abstract: Deep learning, a subset of machine learning within artificial intelligence, has been successful in medical image analysis in vascular surgery. Unlike traditional computer-based segmentation methods that manually extract features from input images, deep learning methods learn image features and classify data without making prior assumptions. Convolutional neural networks, the main type of deep learning for computer vision processing, are neural networks with multilevel architecture and weighted connections between nodes that can “auto-learn” through repeated exposure to training data without manual input or supervision. These networks have numerous applications in vascular surgery imaging analysis, particularly in disease classification, object identification, semantic segmentation, and instance segmentation. The purpose of this review article was to review the relevant concepts of machine learning image analysis and its application to the field of vascular surgery.

Fonte:
Seminars in Vascular Surgery, Volume 36, Issue 3, 2023. Pages 413-418.
DOI: https://doi.org/10.1053/j.semvascsurg.2023.07.001
© 2023 Elsevier Inc. All rights reserved.

Artificial intelligence in the prediction of venous thromboembolism: A systematic review and pooled analysis

Eco-Color Doppler, Intelligenza Artificiale

Authors: Thita Chiasakul, Barbara D. Lam, Megan McNichol, William Robertson, Rachel P. Rosovsky, Leslie Lake, Ioannis S. Vlachos, Alys Adamski, Nimia Reyes, Karon Abe, Jeffrey I. Zwicker, Rushad Patell

Abstract: Accurate diagnostic and prognostic predictions of venous thromboembolism (VTE) are crucial for VTE management. Artificial intelligence (AI) enables autonomous identification of the most predictive patterns from large complex data. Although evidence regarding its performance in VTE prediction is emerging, a comprehensive analysis of performance is lacking. To systematically review the performance of AI in the diagnosis and prediction of VTE and compare it to clinical risk assessment models (RAMs) or logistic regression models…

Fonte:
Eur J Haematol. 2023 Dec;111(6):951-962.
Epub 2023 Oct 4.
DOI: 10.1111/ejh.14110.
© 2023 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

International Union of Angiology consensus document on vascular compression syndromes

Linee-Guida ECD, Eco-Color Doppler

Vascular compression syndromes (VCS) are rare diseases, but they may cause significant symptoms interfering with the quality of life (QoL) of patients who are often in their younger age. Given their infrequent occurrence, multiform clinical and anatomical presentation, and absence of dedicated guidelines from scientific societies, further knowledge of these conditions is required to investigate and treat them using modern imaging and surgical (open or endovascular) techniques…

Guidelines for Vascular Anomalies by the Italian Society for the study of Vascular Anomalies (SISAV)

Linee-Guida ECD, Eco-Color Doppler

The first Italian Guidelines GL on Vascular Malformations were created in 20141 by SISAV which, after 6 years, intends to update them according to the recently published studies and the most current scientific-technological innovations. To ensure that the recommendations on the subject are shared as much as possible and to facilitate their use on the territory, the main Scientific Societies in this field were also involved: SICVE, CIF, SIAPAV, SIDEMAST, SICMF, SIRM and SICP…