Cargando…

Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning

We are developing imaging methods for a co-clinical trial investigating synergy between immunotherapy and radiotherapy. We perform longitudinal micro-computed tomography (micro-CT) of mice to detect lung metastasis after treatment. This work explores deep learning (DL) as a fast approach for automat...

Descripción completa

Detalles Bibliográficos
Autores principales: Holbrook, Matthew D., Clark, Darin P., Patel, Rutulkumar, Qi, Yi, Bassil, Alex M., Mowery, Yvonne M., Badea, Cristian T.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8396172/
https://www.ncbi.nlm.nih.gov/pubmed/34449750
http://dx.doi.org/10.3390/tomography7030032
_version_ 1783744311331913728
author Holbrook, Matthew D.
Clark, Darin P.
Patel, Rutulkumar
Qi, Yi
Bassil, Alex M.
Mowery, Yvonne M.
Badea, Cristian T.
author_facet Holbrook, Matthew D.
Clark, Darin P.
Patel, Rutulkumar
Qi, Yi
Bassil, Alex M.
Mowery, Yvonne M.
Badea, Cristian T.
author_sort Holbrook, Matthew D.
collection PubMed
description We are developing imaging methods for a co-clinical trial investigating synergy between immunotherapy and radiotherapy. We perform longitudinal micro-computed tomography (micro-CT) of mice to detect lung metastasis after treatment. This work explores deep learning (DL) as a fast approach for automated lung nodule detection. We used data from control mice both with and without primary lung tumors. To augment the number of training sets, we have simulated data using real augmented tumors inserted into micro-CT scans. We employed a convolutional neural network (CNN), trained with four competing types of training data: (1) simulated only, (2) real only, (3) simulated and real, and (4) pretraining on simulated followed with real data. We evaluated our model performance using precision and recall curves, as well as receiver operating curves (ROC) and their area under the curve (AUC). The AUC appears to be almost identical (0.76–0.77) for all four cases. However, the combination of real and synthetic data was shown to improve precision by 8%. Smaller tumors have lower rates of detection than larger ones, with networks trained on real data showing better performance. Our work suggests that DL is a promising approach for fast and relatively accurate detection of lung tumors in mice.
format Online
Article
Text
id pubmed-8396172
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83961722021-08-28 Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning Holbrook, Matthew D. Clark, Darin P. Patel, Rutulkumar Qi, Yi Bassil, Alex M. Mowery, Yvonne M. Badea, Cristian T. Tomography Article We are developing imaging methods for a co-clinical trial investigating synergy between immunotherapy and radiotherapy. We perform longitudinal micro-computed tomography (micro-CT) of mice to detect lung metastasis after treatment. This work explores deep learning (DL) as a fast approach for automated lung nodule detection. We used data from control mice both with and without primary lung tumors. To augment the number of training sets, we have simulated data using real augmented tumors inserted into micro-CT scans. We employed a convolutional neural network (CNN), trained with four competing types of training data: (1) simulated only, (2) real only, (3) simulated and real, and (4) pretraining on simulated followed with real data. We evaluated our model performance using precision and recall curves, as well as receiver operating curves (ROC) and their area under the curve (AUC). The AUC appears to be almost identical (0.76–0.77) for all four cases. However, the combination of real and synthetic data was shown to improve precision by 8%. Smaller tumors have lower rates of detection than larger ones, with networks trained on real data showing better performance. Our work suggests that DL is a promising approach for fast and relatively accurate detection of lung tumors in mice. MDPI 2021-08-07 /pmc/articles/PMC8396172/ /pubmed/34449750 http://dx.doi.org/10.3390/tomography7030032 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
Holbrook, Matthew D.
Clark, Darin P.
Patel, Rutulkumar
Qi, Yi
Bassil, Alex M.
Mowery, Yvonne M.
Badea, Cristian T.
Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning
title Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning
title_full Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning
title_fullStr Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning
title_full_unstemmed Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning
title_short Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning
title_sort detection of lung nodules in micro-ct imaging using deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8396172/
https://www.ncbi.nlm.nih.gov/pubmed/34449750
http://dx.doi.org/10.3390/tomography7030032
work_keys_str_mv AT holbrookmatthewd detectionoflungnodulesinmicroctimagingusingdeeplearning
AT clarkdarinp detectionoflungnodulesinmicroctimagingusingdeeplearning
AT patelrutulkumar detectionoflungnodulesinmicroctimagingusingdeeplearning
AT qiyi detectionoflungnodulesinmicroctimagingusingdeeplearning
AT bassilalexm detectionoflungnodulesinmicroctimagingusingdeeplearning
AT moweryyvonnem detectionoflungnodulesinmicroctimagingusingdeeplearning
AT badeacristiant detectionoflungnodulesinmicroctimagingusingdeeplearning