CT evaluation of 2D and 3D holistic deep learning methods for the volumetric segmentation of airway lesions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bouzid, Amel Imene Hadj, de Senneville, Baudouin Denis, Baldacci, Fabien, Desbarats, Pascal, Berger, Patrick, Benlala, Ilyes, Dournes, Gaël
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916353811677184
author Bouzid, Amel Imene Hadj
de Senneville, Baudouin Denis
Baldacci, Fabien
Desbarats, Pascal
Berger, Patrick
Benlala, Ilyes
Dournes, Gaël
author_facet Bouzid, Amel Imene Hadj
de Senneville, Baudouin Denis
Baldacci, Fabien
Desbarats, Pascal
Berger, Patrick
Benlala, Ilyes
Dournes, Gaël
contents This research embarked on a comparative exploration of the holistic segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized data from two CF reference centers, covering five major CF structural changes. Initially, it compared the 2D and 3D models, highlighting the 3D model's superior capability in capturing complex features like mucus plugs and consolidations. To improve the 2D model's performance, a loss adapted to fine structures segmentation was implemented and evaluated, significantly enhancing its accuracy, though not surpassing the 3D model's performance. The models underwent further validation through external evaluation against pulmonary function tests (PFTs), confirming the robustness of the findings. Moreover, this study went beyond comparing metrics; it also included comprehensive assessments of the models' interpretability and reliability, providing valuable insights for their clinical application.
format Preprint
id arxiv_https___arxiv_org_abs_2403_08042
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CT evaluation of 2D and 3D holistic deep learning methods for the volumetric segmentation of airway lesions
Bouzid, Amel Imene Hadj
de Senneville, Baudouin Denis
Baldacci, Fabien
Desbarats, Pascal
Berger, Patrick
Benlala, Ilyes
Dournes, Gaël
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
This research embarked on a comparative exploration of the holistic segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized data from two CF reference centers, covering five major CF structural changes. Initially, it compared the 2D and 3D models, highlighting the 3D model's superior capability in capturing complex features like mucus plugs and consolidations. To improve the 2D model's performance, a loss adapted to fine structures segmentation was implemented and evaluated, significantly enhancing its accuracy, though not surpassing the 3D model's performance. The models underwent further validation through external evaluation against pulmonary function tests (PFTs), confirming the robustness of the findings. Moreover, this study went beyond comparing metrics; it also included comprehensive assessments of the models' interpretability and reliability, providing valuable insights for their clinical application.
title CT evaluation of 2D and 3D holistic deep learning methods for the volumetric segmentation of airway lesions
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.08042