Cargando…
The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans
Lung cancer is a highly prevalent pathology and a leading cause of cancer-related deaths. Most patients are diagnosed when the disease has manifested itself, which usually is a sign of lung cancer in an advanced stage and, as a consequence, the 5-year survival rates are low. To increase the chances...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9100675/ https://www.ncbi.nlm.nih.gov/pubmed/35591132 http://dx.doi.org/10.3390/s22093443 |
_version_ | 1784706903653220352 |
---|---|
author | Sousa, Joana Pereira, Tania Neves, Inês Silva, Francisco Oliveira, Hélder P. |
author_facet | Sousa, Joana Pereira, Tania Neves, Inês Silva, Francisco Oliveira, Hélder P. |
author_sort | Sousa, Joana |
collection | PubMed |
description | Lung cancer is a highly prevalent pathology and a leading cause of cancer-related deaths. Most patients are diagnosed when the disease has manifested itself, which usually is a sign of lung cancer in an advanced stage and, as a consequence, the 5-year survival rates are low. To increase the chances of survival, improving the cancer early detection capacity is crucial, for which computed tomography (CT) scans represent a key role. The manual evaluation of the CTs is a time-consuming task and computer-aided diagnosis (CAD) systems can help relieve that burden. The segmentation of the lung is one of the first steps in these systems, yet it is very challenging given the heterogeneity of lung diseases usually present and associated with cancer development. In our previous work, a segmentation model based on a ResNet34 and U-Net combination was developed on a cross-cohort dataset that yielded good segmentation masks for multiple pathological conditions but misclassified some of the lung nodules. The multiple datasets used for the model development were originated from different annotation protocols, which generated inconsistencies for the learning process, and the annotations are usually not adequate for lung cancer studies since they did not comprise lung nodules. In addition, the initial datasets used for training presented a reduced number of nodules, which was showed not to be enough to allow the segmentation model to learn to include them as a lung part. In this work, an objective protocol for the lung mask’s segmentation was defined and the previous annotations were carefully reviewed and corrected to create consistent and adequate ground-truth masks for the development of the segmentation model. Data augmentation with domain knowledge was used to create lung nodules in the cases used to train the model. The model developed achieved a Dice similarity coefficient (DSC) above 0.9350 for all test datasets and it showed an ability to cope, not only with a variety of lung patterns, but also with the presence of lung nodules as well. This study shows the importance of using consistent annotations for the supervised learning process, which is a very time-consuming task, but that has great importance to healthcare applications. Due to the lack of massive datasets in the medical field, which consequently brings a lack of wide representativity, data augmentation with domain knowledge could represent a promising help to overcome this limitation for learning models development. |
format | Online Article Text |
id | pubmed-9100675 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-91006752022-05-14 The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans Sousa, Joana Pereira, Tania Neves, Inês Silva, Francisco Oliveira, Hélder P. Sensors (Basel) Article Lung cancer is a highly prevalent pathology and a leading cause of cancer-related deaths. Most patients are diagnosed when the disease has manifested itself, which usually is a sign of lung cancer in an advanced stage and, as a consequence, the 5-year survival rates are low. To increase the chances of survival, improving the cancer early detection capacity is crucial, for which computed tomography (CT) scans represent a key role. The manual evaluation of the CTs is a time-consuming task and computer-aided diagnosis (CAD) systems can help relieve that burden. The segmentation of the lung is one of the first steps in these systems, yet it is very challenging given the heterogeneity of lung diseases usually present and associated with cancer development. In our previous work, a segmentation model based on a ResNet34 and U-Net combination was developed on a cross-cohort dataset that yielded good segmentation masks for multiple pathological conditions but misclassified some of the lung nodules. The multiple datasets used for the model development were originated from different annotation protocols, which generated inconsistencies for the learning process, and the annotations are usually not adequate for lung cancer studies since they did not comprise lung nodules. In addition, the initial datasets used for training presented a reduced number of nodules, which was showed not to be enough to allow the segmentation model to learn to include them as a lung part. In this work, an objective protocol for the lung mask’s segmentation was defined and the previous annotations were carefully reviewed and corrected to create consistent and adequate ground-truth masks for the development of the segmentation model. Data augmentation with domain knowledge was used to create lung nodules in the cases used to train the model. The model developed achieved a Dice similarity coefficient (DSC) above 0.9350 for all test datasets and it showed an ability to cope, not only with a variety of lung patterns, but also with the presence of lung nodules as well. This study shows the importance of using consistent annotations for the supervised learning process, which is a very time-consuming task, but that has great importance to healthcare applications. Due to the lack of massive datasets in the medical field, which consequently brings a lack of wide representativity, data augmentation with domain knowledge could represent a promising help to overcome this limitation for learning models development. MDPI 2022-04-30 /pmc/articles/PMC9100675/ /pubmed/35591132 http://dx.doi.org/10.3390/s22093443 Text en © 2022 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 Sousa, Joana Pereira, Tania Neves, Inês Silva, Francisco Oliveira, Hélder P. The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans |
title | The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans |
title_full | The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans |
title_fullStr | The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans |
title_full_unstemmed | The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans |
title_short | The Influence of a Coherent Annotation and Synthetic Addition of Lung Nodules for Lung Segmentation in CT Scans |
title_sort | influence of a coherent annotation and synthetic addition of lung nodules for lung segmentation in ct scans |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9100675/ https://www.ncbi.nlm.nih.gov/pubmed/35591132 http://dx.doi.org/10.3390/s22093443 |
work_keys_str_mv | AT sousajoana theinfluenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT pereiratania theinfluenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT nevesines theinfluenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT silvafrancisco theinfluenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT oliveirahelderp theinfluenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT sousajoana influenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT pereiratania influenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT nevesines influenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT silvafrancisco influenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans AT oliveirahelderp influenceofacoherentannotationandsyntheticadditionoflungnodulesforlungsegmentationinctscans |