Improved detection of air trapping on expiratory computed tomography using deep learning.
<h4>Background</h4>Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0248902 |
| _version_ | 1817998087338065920 |
|---|---|
| author | Sundaresh Ram Benjamin A Hoff Alexander J Bell Stefanie Galban Aleksa B Fortuna Oliver Weinheimer Mark O Wielpütz Terry E Robinson Beverley Newman Dharshan Vummidi Aamer Chughtai Ella A Kazerooni Timothy D Johnson MeiLan K Han Charles R Hatt Craig J Galban |
| author_facet | Sundaresh Ram Benjamin A Hoff Alexander J Bell Stefanie Galban Aleksa B Fortuna Oliver Weinheimer Mark O Wielpütz Terry E Robinson Beverley Newman Dharshan Vummidi Aamer Chughtai Ella A Kazerooni Timothy D Johnson MeiLan K Han Charles R Hatt Craig J Galban |
| author_sort | Sundaresh Ram |
| collection | DOAJ |
| description | <h4>Background</h4>Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in limited efficacy for monitoring disease progression.<h4>Objective</h4>To investigate the effectiveness of a convolutional neural network (CNN) model for quantifying and monitoring AT, and to compare it with other quantitative AT measures obtained from threshold-based techniques.<h4>Materials and methods</h4>Paired volumetric whole lung inspiratory and expiratory CT scans were obtained at four time points (0, 3, 12 and 24 months) on 36 subjects with mild CF lung disease. A densely connected CNN (DN) was trained using AT segmentation maps generated from a personalized threshold-based method (PTM). Quantitative AT (QAT) values, presented as the relative volume of AT over the lungs, from the DN approach were compared to QAT values from the PTM method. Radiographic assessment, spirometric measures, and clinical scores were correlated to the DN QAT values using a linear mixed effects model.<h4>Results</h4>QAT values from the DN were found to increase from 8.65% ± 1.38% to 21.38% ± 1.82%, respectively, over a two-year period. Comparison of CNN model results to intensity-based measures demonstrated a systematic drop in the Dice coefficient over time (decreased from 0.86 ± 0.03 to 0.45 ± 0.04). The trends observed in DN QAT values were consistent with clinical scores for AT, bronchiectasis, and mucus plugging. In addition, the DN approach was found to be less susceptible to variations in expiratory deflation levels than the threshold-based approach.<h4>Conclusion</h4>The CNN model effectively delineated AT on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring AT in CF patients. |
| first_indexed | 2024-04-14T02:48:01Z |
| format | Article |
| id | doaj.art-7bdca52d398445798eb22bb77e7b08be |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-14T02:48:01Z |
| publishDate | 2021-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-7bdca52d398445798eb22bb77e7b08be2022-12-22T02:16:26ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01163e024890210.1371/journal.pone.0248902Improved detection of air trapping on expiratory computed tomography using deep learning.Sundaresh RamBenjamin A HoffAlexander J BellStefanie GalbanAleksa B FortunaOliver WeinheimerMark O WielpützTerry E RobinsonBeverley NewmanDharshan VummidiAamer ChughtaiElla A KazerooniTimothy D JohnsonMeiLan K HanCharles R HattCraig J Galban<h4>Background</h4>Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients with cystic fibrosis (CF). However, standard techniques for quantitative assessment of AT are highly variable, resulting in limited efficacy for monitoring disease progression.<h4>Objective</h4>To investigate the effectiveness of a convolutional neural network (CNN) model for quantifying and monitoring AT, and to compare it with other quantitative AT measures obtained from threshold-based techniques.<h4>Materials and methods</h4>Paired volumetric whole lung inspiratory and expiratory CT scans were obtained at four time points (0, 3, 12 and 24 months) on 36 subjects with mild CF lung disease. A densely connected CNN (DN) was trained using AT segmentation maps generated from a personalized threshold-based method (PTM). Quantitative AT (QAT) values, presented as the relative volume of AT over the lungs, from the DN approach were compared to QAT values from the PTM method. Radiographic assessment, spirometric measures, and clinical scores were correlated to the DN QAT values using a linear mixed effects model.<h4>Results</h4>QAT values from the DN were found to increase from 8.65% ± 1.38% to 21.38% ± 1.82%, respectively, over a two-year period. Comparison of CNN model results to intensity-based measures demonstrated a systematic drop in the Dice coefficient over time (decreased from 0.86 ± 0.03 to 0.45 ± 0.04). The trends observed in DN QAT values were consistent with clinical scores for AT, bronchiectasis, and mucus plugging. In addition, the DN approach was found to be less susceptible to variations in expiratory deflation levels than the threshold-based approach.<h4>Conclusion</h4>The CNN model effectively delineated AT on expiratory CT scans, which provides an automated and objective approach for assessing and monitoring AT in CF patients.https://doi.org/10.1371/journal.pone.0248902 |
| spellingShingle | Sundaresh Ram Benjamin A Hoff Alexander J Bell Stefanie Galban Aleksa B Fortuna Oliver Weinheimer Mark O Wielpütz Terry E Robinson Beverley Newman Dharshan Vummidi Aamer Chughtai Ella A Kazerooni Timothy D Johnson MeiLan K Han Charles R Hatt Craig J Galban Improved detection of air trapping on expiratory computed tomography using deep learning. PLoS ONE |
| title | Improved detection of air trapping on expiratory computed tomography using deep learning. |
| title_full | Improved detection of air trapping on expiratory computed tomography using deep learning. |
| title_fullStr | Improved detection of air trapping on expiratory computed tomography using deep learning. |
| title_full_unstemmed | Improved detection of air trapping on expiratory computed tomography using deep learning. |
| title_short | Improved detection of air trapping on expiratory computed tomography using deep learning. |
| title_sort | improved detection of air trapping on expiratory computed tomography using deep learning |
| url | https://doi.org/10.1371/journal.pone.0248902 |
| work_keys_str_mv | AT sundareshram improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT benjaminahoff improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT alexanderjbell improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT stefaniegalban improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT aleksabfortuna improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT oliverweinheimer improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT markowielputz improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT terryerobinson improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT beverleynewman improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT dharshanvummidi improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT aamerchughtai improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT ellaakazerooni improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT timothydjohnson improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT meilankhan improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT charlesrhatt improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning AT craigjgalban improveddetectionofairtrappingonexpiratorycomputedtomographyusingdeeplearning |