MitraClip Device Automated Localization in 3D Transesophageal Echocardiography via Deep Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Munafò, Riccardo, Saitta, Simone, Vicentini, Luca, Tondi, Davide, Ruozzi, Veronica, Sturla, Francesco, Ingallina, Giacomo, Guidotti, Andrea, Agricola, Eustachio, Votta, Emiliano
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910809768067072
author Munafò, Riccardo
Saitta, Simone
Vicentini, Luca
Tondi, Davide
Ruozzi, Veronica
Sturla, Francesco
Ingallina, Giacomo
Guidotti, Andrea
Agricola, Eustachio
Votta, Emiliano
author_facet Munafò, Riccardo
Saitta, Simone
Vicentini, Luca
Tondi, Davide
Ruozzi, Veronica
Sturla, Francesco
Ingallina, Giacomo
Guidotti, Andrea
Agricola, Eustachio
Votta, Emiliano
contents The MitraClip is the most widely percutaneous treatment for mitral regurgitation, typically performed under the real-time guidance of 3D transesophagel echocardiography (TEE). However, artifacts and low image contrast in echocardiography hinder accurate clip visualization. This study presents an automated pipeline for clip detection from 3D TEE images. An Attention UNet was employed to segment the device, while a DenseNet classifier predicted its configuration among ten possible states, ranging from fully closed to fully open. Based on the predicted configuration, a template model derived from computer-aided design (CAD) was automatically registered to refine the segmentation and enable quantitative characterization of the device. The pipeline was trained and validated on 196 3D TEE images acquired using a heart simulator, with ground-truth annotations refined through CAD-based templates. The Attention UNet achieved an average surface distance of 0.76 mm and 95% Hausdorff distance of 2.44 mm for segmentation, while the DenseNet achieved an average weighted F1-score of 0.75 for classification. Post-refinement, segmentation accuracy improved, with average surface distance and 95% Hausdorff distance reduced to 0.75 mm and 2.05 mm, respectively. This pipeline enhanced clip visualization, providing fast and accurate detection with quantitative feedback, potentially improving procedural efficiency and reducing adverse outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15013
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MitraClip Device Automated Localization in 3D Transesophageal Echocardiography via Deep Learning
Munafò, Riccardo
Saitta, Simone
Vicentini, Luca
Tondi, Davide
Ruozzi, Veronica
Sturla, Francesco
Ingallina, Giacomo
Guidotti, Andrea
Agricola, Eustachio
Votta, Emiliano
Quantitative Methods
The MitraClip is the most widely percutaneous treatment for mitral regurgitation, typically performed under the real-time guidance of 3D transesophagel echocardiography (TEE). However, artifacts and low image contrast in echocardiography hinder accurate clip visualization. This study presents an automated pipeline for clip detection from 3D TEE images. An Attention UNet was employed to segment the device, while a DenseNet classifier predicted its configuration among ten possible states, ranging from fully closed to fully open. Based on the predicted configuration, a template model derived from computer-aided design (CAD) was automatically registered to refine the segmentation and enable quantitative characterization of the device. The pipeline was trained and validated on 196 3D TEE images acquired using a heart simulator, with ground-truth annotations refined through CAD-based templates. The Attention UNet achieved an average surface distance of 0.76 mm and 95% Hausdorff distance of 2.44 mm for segmentation, while the DenseNet achieved an average weighted F1-score of 0.75 for classification. Post-refinement, segmentation accuracy improved, with average surface distance and 95% Hausdorff distance reduced to 0.75 mm and 2.05 mm, respectively. This pipeline enhanced clip visualization, providing fast and accurate detection with quantitative feedback, potentially improving procedural efficiency and reducing adverse outcomes.
title MitraClip Device Automated Localization in 3D Transesophageal Echocardiography via Deep Learning
topic Quantitative Methods
url https://arxiv.org/abs/2412.15013