Method to estimate in real time the final positioning of a stent-graft and/or a percutaneous valve in a minimally invasive intervention for vascular and/or valvular pathologies, comprising the following steps: creating a database of data generated by models of minimally invasive procedures and training a predictive algorithm (P) with these data; acquiring clinical images (1) relating to vessels of a patient affected by vascular and/or valvular pathology and extracting from these clinical images geometric parameters (2) of the vessels affected by the pathology and morphological parameters (3) of the pathology; generating a three-dimensional model (4) of the affected vessels and the pathology by processing the geometric parameters (2) and the morphological parameters (3); selecting indicator parameters relating to minimally invasive intervention by processing the three-dimensional model (4) of the affected vessels and the pathology; calculating an estimate of the final positioning (5) of a stent-graft and/or a percutaneous valve following the intervention by processing the indicator parameters using the predictive algorithm (P), wherein the predictive algorithm (P) is expected to be trained by processing the data through machine learning techniques on a predefined number of numerical simulations of the finite elements of minimally invasive procedures of stent-graft implantation for vascular pathologies and/or percutaneous valve implantation for valvular pathologies.

Method to estimate in real time the final positioning of a device in a minimally invasive intervention for vascular and/or valvular pathologies

MIGLIAVACCA, Francesco;RODRIGUEZ MATAS, Jose Felix;LURAGHI, Giulia;RAMELLA, Anna;BARATI, Sara;BRIDIO, Sara
2024-01-01

Abstract

Method to estimate in real time the final positioning of a stent-graft and/or a percutaneous valve in a minimally invasive intervention for vascular and/or valvular pathologies, comprising the following steps: creating a database of data generated by models of minimally invasive procedures and training a predictive algorithm (P) with these data; acquiring clinical images (1) relating to vessels of a patient affected by vascular and/or valvular pathology and extracting from these clinical images geometric parameters (2) of the vessels affected by the pathology and morphological parameters (3) of the pathology; generating a three-dimensional model (4) of the affected vessels and the pathology by processing the geometric parameters (2) and the morphological parameters (3); selecting indicator parameters relating to minimally invasive intervention by processing the three-dimensional model (4) of the affected vessels and the pathology; calculating an estimate of the final positioning (5) of a stent-graft and/or a percutaneous valve following the intervention by processing the indicator parameters using the predictive algorithm (P), wherein the predictive algorithm (P) is expected to be trained by processing the data through machine learning techniques on a predefined number of numerical simulations of the finite elements of minimally invasive procedures of stent-graft implantation for vascular pathologies and/or percutaneous valve implantation for valvular pathologies.
2024
File in questo prodotto:
File Dimensione Formato  
WO_2025083523_A1.pdf

accesso aperto

Descrizione: pct
: Publisher’s version
Dimensione 1.76 MB
Formato Adobe PDF
1.76 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1290133
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact