Cargando…

Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling

Deep learning is a recent technology that has shown excellent capabilities for recognition and identification tasks. This study applies these techniques in open cranial vault remodeling surgeries performed to correct craniosynostosis. The objective was to automatically recognize surgical tools in re...

Descripción completa

Detalles Bibliográficos
Autores principales: Pose Díez de la Lastra, Alicia, García-Duarte Sáenz, Lucía, García-Mato, David, Hernández-Álvarez, Luis, Ochandiano, Santiago, Pascau, Javier
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8303376/
https://www.ncbi.nlm.nih.gov/pubmed/34206962
http://dx.doi.org/10.3390/e23070817
_version_ 1783727071969673216
author Pose Díez de la Lastra, Alicia
García-Duarte Sáenz, Lucía
García-Mato, David
Hernández-Álvarez, Luis
Ochandiano, Santiago
Pascau, Javier
author_facet Pose Díez de la Lastra, Alicia
García-Duarte Sáenz, Lucía
García-Mato, David
Hernández-Álvarez, Luis
Ochandiano, Santiago
Pascau, Javier
author_sort Pose Díez de la Lastra, Alicia
collection PubMed
description Deep learning is a recent technology that has shown excellent capabilities for recognition and identification tasks. This study applies these techniques in open cranial vault remodeling surgeries performed to correct craniosynostosis. The objective was to automatically recognize surgical tools in real-time and estimate the surgical phase based on those predictions. For this purpose, we implemented, trained, and tested three algorithms based on previously proposed Convolutional Neural Network architectures (VGG16, MobileNetV2, and InceptionV3) and one new architecture with fewer parameters (CranioNet). A novel 3D Slicer module was specifically developed to implement these networks and recognize surgical tools in real time via video streaming. The training and test data were acquired during a surgical simulation using a 3D printed patient-based realistic phantom of an infant’s head. The results showed that CranioNet presents the lowest accuracy for tool recognition (93.4%), while the highest accuracy is achieved by the MobileNetV2 model (99.6%), followed by VGG16 and InceptionV3 (98.8% and 97.2%, respectively). Regarding phase detection, InceptionV3 and VGG16 obtained the best results (94.5% and 94.4%), whereas MobileNetV2 and CranioNet presented worse values (91.1% and 89.8%). Our results prove the feasibility of applying deep learning architectures for real-time tool detection and phase estimation in craniosynostosis surgeries.
format Online
Article
Text
id pubmed-8303376
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83033762021-07-25 Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling Pose Díez de la Lastra, Alicia García-Duarte Sáenz, Lucía García-Mato, David Hernández-Álvarez, Luis Ochandiano, Santiago Pascau, Javier Entropy (Basel) Article Deep learning is a recent technology that has shown excellent capabilities for recognition and identification tasks. This study applies these techniques in open cranial vault remodeling surgeries performed to correct craniosynostosis. The objective was to automatically recognize surgical tools in real-time and estimate the surgical phase based on those predictions. For this purpose, we implemented, trained, and tested three algorithms based on previously proposed Convolutional Neural Network architectures (VGG16, MobileNetV2, and InceptionV3) and one new architecture with fewer parameters (CranioNet). A novel 3D Slicer module was specifically developed to implement these networks and recognize surgical tools in real time via video streaming. The training and test data were acquired during a surgical simulation using a 3D printed patient-based realistic phantom of an infant’s head. The results showed that CranioNet presents the lowest accuracy for tool recognition (93.4%), while the highest accuracy is achieved by the MobileNetV2 model (99.6%), followed by VGG16 and InceptionV3 (98.8% and 97.2%, respectively). Regarding phase detection, InceptionV3 and VGG16 obtained the best results (94.5% and 94.4%), whereas MobileNetV2 and CranioNet presented worse values (91.1% and 89.8%). Our results prove the feasibility of applying deep learning architectures for real-time tool detection and phase estimation in craniosynostosis surgeries. MDPI 2021-06-26 /pmc/articles/PMC8303376/ /pubmed/34206962 http://dx.doi.org/10.3390/e23070817 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Pose Díez de la Lastra, Alicia
García-Duarte Sáenz, Lucía
García-Mato, David
Hernández-Álvarez, Luis
Ochandiano, Santiago
Pascau, Javier
Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling
title Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling
title_full Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling
title_fullStr Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling
title_full_unstemmed Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling
title_short Real-Time Tool Detection for Workflow Identification in Open Cranial Vault Remodeling
title_sort real-time tool detection for workflow identification in open cranial vault remodeling
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8303376/
https://www.ncbi.nlm.nih.gov/pubmed/34206962
http://dx.doi.org/10.3390/e23070817
work_keys_str_mv AT posediezdelalastraalicia realtimetooldetectionforworkflowidentificationinopencranialvaultremodeling
AT garciaduartesaenzlucia realtimetooldetectionforworkflowidentificationinopencranialvaultremodeling
AT garciamatodavid realtimetooldetectionforworkflowidentificationinopencranialvaultremodeling
AT hernandezalvarezluis realtimetooldetectionforworkflowidentificationinopencranialvaultremodeling
AT ochandianosantiago realtimetooldetectionforworkflowidentificationinopencranialvaultremodeling
AT pascaujavier realtimetooldetectionforworkflowidentificationinopencranialvaultremodeling