Cargando…

Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies

Background: The aim of this work is to identify an automatic, accurate, and fast deep learning segmentation approach, applied to the parenchyma, using a very small dataset of high-resolution computed tomography images of patients with idiopathic pulmonary fibrosis. In this way, we aim to enhance the...

Descripción completa

Detalles Bibliográficos
Autores principales: Comelli, Albert, Coronnello, Claudia, Dahiya, Navdeep, Benfante, Viviana, Palmucci, Stefano, Basile, Antonio, Vancheri, Carlo, Russo, Giorgio, Yezzi, Anthony, Stefano, Alessandro
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321165/
https://www.ncbi.nlm.nih.gov/pubmed/34460569
http://dx.doi.org/10.3390/jimaging6110125
_version_ 1783730786124431360
author Comelli, Albert
Coronnello, Claudia
Dahiya, Navdeep
Benfante, Viviana
Palmucci, Stefano
Basile, Antonio
Vancheri, Carlo
Russo, Giorgio
Yezzi, Anthony
Stefano, Alessandro
author_facet Comelli, Albert
Coronnello, Claudia
Dahiya, Navdeep
Benfante, Viviana
Palmucci, Stefano
Basile, Antonio
Vancheri, Carlo
Russo, Giorgio
Yezzi, Anthony
Stefano, Alessandro
author_sort Comelli, Albert
collection PubMed
description Background: The aim of this work is to identify an automatic, accurate, and fast deep learning segmentation approach, applied to the parenchyma, using a very small dataset of high-resolution computed tomography images of patients with idiopathic pulmonary fibrosis. In this way, we aim to enhance the methodology performed by healthcare operators in radiomics studies where operator-independent segmentation methods must be used to correctly identify the target and, consequently, the texture-based prediction model. Methods: Two deep learning models were investigated: (i) U-Net, already used in many biomedical image segmentation tasks, and (ii) E-Net, used for image segmentation tasks in self-driving cars, where hardware availability is limited and accurate segmentation is critical for user safety. Our small image dataset is composed of 42 studies of patients with idiopathic pulmonary fibrosis, of which only 32 were used for the training phase. We compared the performance of the two models in terms of the similarity of their segmentation outcome with the gold standard and in terms of their resources’ requirements. Results: E-Net can be used to obtain accurate (dice similarity coefficient = 95.90%), fast (20.32 s), and clinically acceptable segmentation of the lung region. Conclusions: We demonstrated that deep learning models can be efficiently applied to rapidly segment and quantify the parenchyma of patients with pulmonary fibrosis, without any radiologist supervision, in order to produce user-independent results.
format Online
Article
Text
id pubmed-8321165
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83211652021-08-26 Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies Comelli, Albert Coronnello, Claudia Dahiya, Navdeep Benfante, Viviana Palmucci, Stefano Basile, Antonio Vancheri, Carlo Russo, Giorgio Yezzi, Anthony Stefano, Alessandro J Imaging Article Background: The aim of this work is to identify an automatic, accurate, and fast deep learning segmentation approach, applied to the parenchyma, using a very small dataset of high-resolution computed tomography images of patients with idiopathic pulmonary fibrosis. In this way, we aim to enhance the methodology performed by healthcare operators in radiomics studies where operator-independent segmentation methods must be used to correctly identify the target and, consequently, the texture-based prediction model. Methods: Two deep learning models were investigated: (i) U-Net, already used in many biomedical image segmentation tasks, and (ii) E-Net, used for image segmentation tasks in self-driving cars, where hardware availability is limited and accurate segmentation is critical for user safety. Our small image dataset is composed of 42 studies of patients with idiopathic pulmonary fibrosis, of which only 32 were used for the training phase. We compared the performance of the two models in terms of the similarity of their segmentation outcome with the gold standard and in terms of their resources’ requirements. Results: E-Net can be used to obtain accurate (dice similarity coefficient = 95.90%), fast (20.32 s), and clinically acceptable segmentation of the lung region. Conclusions: We demonstrated that deep learning models can be efficiently applied to rapidly segment and quantify the parenchyma of patients with pulmonary fibrosis, without any radiologist supervision, in order to produce user-independent results. MDPI 2020-11-19 /pmc/articles/PMC8321165/ /pubmed/34460569 http://dx.doi.org/10.3390/jimaging6110125 Text en © 2020 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 (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Comelli, Albert
Coronnello, Claudia
Dahiya, Navdeep
Benfante, Viviana
Palmucci, Stefano
Basile, Antonio
Vancheri, Carlo
Russo, Giorgio
Yezzi, Anthony
Stefano, Alessandro
Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies
title Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies
title_full Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies
title_fullStr Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies
title_full_unstemmed Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies
title_short Lung Segmentation on High-Resolution Computerized Tomography Images Using Deep Learning: A Preliminary Step for Radiomics Studies
title_sort lung segmentation on high-resolution computerized tomography images using deep learning: a preliminary step for radiomics studies
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321165/
https://www.ncbi.nlm.nih.gov/pubmed/34460569
http://dx.doi.org/10.3390/jimaging6110125
work_keys_str_mv AT comellialbert lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT coronnelloclaudia lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT dahiyanavdeep lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT benfanteviviana lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT palmuccistefano lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT basileantonio lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT vanchericarlo lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT russogiorgio lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT yezzianthony lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies
AT stefanoalessandro lungsegmentationonhighresolutioncomputerizedtomographyimagesusingdeeplearningapreliminarystepforradiomicsstudies