Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis
Pulmonary function tests (PFTs) play an important role in screening and following-up pulmonary involvement in systemic sclerosis (SSc). However, some patients are not able to perform PFTs due to contraindications. In addition, it is unclear how lung function is affected by changes in lung structure...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10330905/ |
_version_ | 1797401006921744384 |
---|---|
author | Jingnan Jia Emiel R. Marges Jeska K. De Vries-Bouwstra Maarten K. Ninaber Lucia J. M. Kroft Anne A. Schouffoer Marius Staring Berend C. Stoel |
author_facet | Jingnan Jia Emiel R. Marges Jeska K. De Vries-Bouwstra Maarten K. Ninaber Lucia J. M. Kroft Anne A. Schouffoer Marius Staring Berend C. Stoel |
author_sort | Jingnan Jia |
collection | DOAJ |
description | Pulmonary function tests (PFTs) play an important role in screening and following-up pulmonary involvement in systemic sclerosis (SSc). However, some patients are not able to perform PFTs due to contraindications. In addition, it is unclear how lung function is affected by changes in lung structure in SSc. Therefore, this study aims to explore the potential of automatically estimating PFT results from chest CT scans of SSc patients and how different regions influence the estimation of PFTs. Deep regression networks were developed with transfer learning to estimate PFTs from 316 SSc patients. Segmented lungs and vessels were used to mask the CT images to train the network with different inputs: from entire CT scan, lungs-only to vessels-only. The network trained on entire CT scans with transfer learning achieved an ICC of 0.71, 0.76, 0.80, and 0.81 for the estimation of DLCO, FEV1, FVC and TLC, respectively. The performance of the networks gradually decreased when trained on data from lungs-only and vessels-only. Regression attention maps showed that regions close to large vessels were highlighted more than other regions, and occasionally regions outside the lungs were highlighted. These experiments show that apart from the lungs and large vessels, other regions contribute to PFT estimation. In addition, adding manually designed biomarkers increased the correlation (R) from 0.75, 0.74, 0.82, and 0.83 to 0.81, 0.83, 0.88, and 0.90, respectively. This suggests that that manually designed imaging biomarkers can still contribute to explaining the relation between lung function and structure. |
first_indexed | 2024-03-09T02:03:39Z |
format | Article |
id | doaj.art-4ef96f01e6904a6ea575d4029a153c1c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-09T02:03:39Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-4ef96f01e6904a6ea575d4029a153c1c2023-12-08T00:04:08ZengIEEEIEEE Access2169-35362023-01-011113527213528210.1109/ACCESS.2023.333763910330905Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic SclerosisJingnan Jia0https://orcid.org/0000-0002-1025-2557Emiel R. Marges1https://orcid.org/0000-0003-1829-533XJeska K. De Vries-Bouwstra2Maarten K. Ninaber3Lucia J. M. Kroft4Anne A. Schouffoer5Marius Staring6https://orcid.org/0000-0003-2885-5812Berend C. Stoel7https://orcid.org/0000-0002-5975-8559Department of Radiology, Division of Image Processing, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Pulmonology, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Rheumatology, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Pulmonology, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Radiology, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Rheumatology, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Radiology, Division of Image Processing, Leiden University Medical Center (LUMC), Leiden, The NetherlandsDepartment of Radiology, Division of Image Processing, Leiden University Medical Center (LUMC), Leiden, The NetherlandsPulmonary function tests (PFTs) play an important role in screening and following-up pulmonary involvement in systemic sclerosis (SSc). However, some patients are not able to perform PFTs due to contraindications. In addition, it is unclear how lung function is affected by changes in lung structure in SSc. Therefore, this study aims to explore the potential of automatically estimating PFT results from chest CT scans of SSc patients and how different regions influence the estimation of PFTs. Deep regression networks were developed with transfer learning to estimate PFTs from 316 SSc patients. Segmented lungs and vessels were used to mask the CT images to train the network with different inputs: from entire CT scan, lungs-only to vessels-only. The network trained on entire CT scans with transfer learning achieved an ICC of 0.71, 0.76, 0.80, and 0.81 for the estimation of DLCO, FEV1, FVC and TLC, respectively. The performance of the networks gradually decreased when trained on data from lungs-only and vessels-only. Regression attention maps showed that regions close to large vessels were highlighted more than other regions, and occasionally regions outside the lungs were highlighted. These experiments show that apart from the lungs and large vessels, other regions contribute to PFT estimation. In addition, adding manually designed biomarkers increased the correlation (R) from 0.75, 0.74, 0.82, and 0.83 to 0.81, 0.83, 0.88, and 0.90, respectively. This suggests that that manually designed imaging biomarkers can still contribute to explaining the relation between lung function and structure.https://ieeexplore.ieee.org/document/10330905/Pulmonary lung functiondeep learningcomputerized tomographysystemic sclerosis |
spellingShingle | Jingnan Jia Emiel R. Marges Jeska K. De Vries-Bouwstra Maarten K. Ninaber Lucia J. M. Kroft Anne A. Schouffoer Marius Staring Berend C. Stoel Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis IEEE Access Pulmonary lung function deep learning computerized tomography systemic sclerosis |
title | Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis |
title_full | Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis |
title_fullStr | Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis |
title_full_unstemmed | Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis |
title_short | Automatic Pulmonary Function Estimation From Chest CT Scans Using Deep Regression Neural Networks: The Relation Between Structure and Function in Systemic Sclerosis |
title_sort | automatic pulmonary function estimation from chest ct scans using deep regression neural networks the relation between structure and function in systemic sclerosis |
topic | Pulmonary lung function deep learning computerized tomography systemic sclerosis |
url | https://ieeexplore.ieee.org/document/10330905/ |
work_keys_str_mv | AT jingnanjia automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT emielrmarges automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT jeskakdevriesbouwstra automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT maartenkninaber automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT luciajmkroft automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT anneaschouffoer automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT mariusstaring automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis AT berendcstoel automaticpulmonaryfunctionestimationfromchestctscansusingdeepregressionneuralnetworkstherelationbetweenstructureandfunctioninsystemicsclerosis |