Carotid atherosclerotic plaque stability prediction from transversal ultrasound images using deep learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376868" target="_blank" >RIV/68407700:21230/24:00376868 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61988987:17110/24:A2503AD7

Výsledek na webu

<a href="https://doi.org/10.48095/cccsnn2024255" target="_blank" >https://doi.org/10.48095/cccsnn2024255</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48095/cccsnn2024255" target="_blank" >10.48095/cccsnn2024255</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Carotid atherosclerotic plaque stability prediction from transversal ultrasound images using deep learning

Popis výsledku v původním jazyce

Aims: To automatically predict the stability of carotid artery plaque from standard B-mode transversal ultrasound images using deep learning. A reliable predictor would reduce the need for follow-up examination and pharmacological and surgical treatment. Methods: A region of interest (ROI) containing the carotid artery is automatically localized. An adversarial segmentation method was trained on a combination of a small pixelwise annotated dataset and a larger weakly annotated dataset. A multicriterion regression with automatic weight adaptation was applied to predict a series of clinically relevant attributes, including the plaque width increase over 3 years. Results: The current plaque width could be estimated with a high correlation (ϱ = 0.32) and a very high statistical significance. The estimated future increase of the plaque width was correlated less (ϱ = 0.22) but significantly (p < 0.01). The correlation between automatic and expert assessments of echogenicity, smoothness and calcification was even smaller. Conclusions: We confirmed that there is a relationship between the plaque appearance in ultrasound and the probability of its future growth, but it is too weak to be used in clinical practice as the sole predictor of the plaque stability.

Název v anglickém jazyce

Carotid atherosclerotic plaque stability prediction from transversal ultrasound images using deep learning

Popis výsledku anglicky

Aims: To automatically predict the stability of carotid artery plaque from standard B-mode transversal ultrasound images using deep learning. A reliable predictor would reduce the need for follow-up examination and pharmacological and surgical treatment. Methods: A region of interest (ROI) containing the carotid artery is automatically localized. An adversarial segmentation method was trained on a combination of a small pixelwise annotated dataset and a larger weakly annotated dataset. A multicriterion regression with automatic weight adaptation was applied to predict a series of clinically relevant attributes, including the plaque width increase over 3 years. Results: The current plaque width could be estimated with a high correlation (ϱ = 0.32) and a very high statistical significance. The estimated future increase of the plaque width was correlated less (ϱ = 0.22) but significantly (p < 0.01). The correlation between automatic and expert assessments of echogenicity, smoothness and calcification was even smaller. Conclusions: We confirmed that there is a relationship between the plaque appearance in ultrasound and the probability of its future growth, but it is too weak to be used in clinical practice as the sole predictor of the plaque stability.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/NV19-08-00362" target="_blank" >NV19-08-00362: Hodnocení stability aterosklerotického plátu v karotidě pomocí digitální analýzy ultrazvukového obrazu u pacientů se stenózou vnitřní karotidy</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Česká a slovenská neurologie a neurochirurgie

ISSN

1210-7859

e-ISSN

1802-4041

Svazek periodika

87

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

9

Strana od-do

255-263

Kód UT WoS článku

001329062600001

EID výsledku v databázi Scopus

2-s2.0-85206925810