Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis
Abstract
:1. Introduction
2. Materials and Methods
2.1. Patient Population
2.2. CT Examination Protocol
2.3. ILD Classification with CAD and the DL-Based Algorithm
- CAD system (Gaussian histogram normalized correlation segmentation [GHNC] estimation)
- DL-based analysis (QZIP-ILD)
2.4. Comparison of Lung Region Volume Measured by CAD and DL-Based Method
2.5. Accuracy for ILD Classification by CAD and DL-Based Method
2.6. Relationship of DL Lung Analysis, Pulmonary Functional Tests, and Patients’ Prognosis
2.7. Statistical Analysis
3. Results
3.1. ILD Classification, Volumetry, and Accuracy by CAD and DL-Based Method
3.2. Correlation with Pulmonary Function and Prognosis
4. Discussion
The Training Process of DL-Based Analysis Model (Pre-Clinical Study)
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Wijsenbeek, M.; Cottin, V. Spectrum of Fibrotic Lung Diseases. N. Engl. J. Med. 2020, 383, 958–968. [Google Scholar] [CrossRef] [PubMed]
- Raghu, G.; Remy-Jardin, M.; Richeldi, L.; Thomson, C.C.; Inoue, Y.; Johkoh, T.; Kreuter, M.; Lynch, D.A.; Maher, T.M.; Martinez, F.J.; et al. Idiopathic Pulmonary Fibrosis (an Update) and Progressive Pulmonary Fibrosis in Adults: An Official ATS/ERS/JRS/ALAT Clinical Practice Guideline. Am. J. Respir. Crit. Care Med. 2022, 205, e18–e47. [Google Scholar] [CrossRef]
- Chen, A.; Karwoski, R.A.; Gierada, D.S.; Bartholmai, B.J.; Koo, C.W. Quantitative CT Analysis of Diffuse Lung Disease. Radio Graph. 2019, 40, 28–43. [Google Scholar] [CrossRef] [PubMed]
- Yang, C.-C.; Chen, C.-Y.; Kuo, Y.-T.; Ko, C.-C.; Wu, W.-J.; Liang, C.-H.; Yun, C.-H.; Huang, W.-M. Radiomics for the Prediction of Response to Antifibrotic Treatment in Patients with Idiopathic Pulmonary Fibrosis: A Pilot Study. Diagnostics 2022, 12, 1002. [Google Scholar] [CrossRef]
- Risoli, C.; Nicolò, M.; Colombi, D.; Moia, M.; Rapacioli, F.; Anselmi, P.; Michieletti, E.; Ambrosini, R.; Di Terlizzi, M.; Grazioli, L.; et al. Different Lung Parenchyma Quantification Using Dissimilar Segmentation Software: A Multi-Center Study for COVID-19 Patients. Diagnostics 2022, 12, 1501. [Google Scholar] [CrossRef]
- Park, B.; Park, H.; Lee, S.M.; Seo, J.B.; Kim, N. Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks. J. Digit. Imaging 2019, 32, 1019–1026. [Google Scholar] [CrossRef]
- Fischer, A.M.; Varga-Szemes, A.; van Assen, M.; Griffith, L.P.; Sahbaee, P.; Sperl, J.I.; Nance, J.W.; Schoepf, U.J. Comparison of Artificial Intelligence-Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function Testing. AJR Am. J. Roentgenol. 2020, 214, 1065–1071. [Google Scholar] [CrossRef]
- Bratt, A.; Williams, J.M.; Liu, G.; Panda, A.; Patel, P.P.; Walkoff, L.; Sykes, A.G.; Tandon, Y.K.; Francois, C.J.; Blezek, D.J.; et al. Predicting Usual Interstitial Pneumonia Histopathology from Chest CT with Deep Learning. Chest 2022, 162, 815–823. [Google Scholar] [CrossRef]
- Choe, J.; Hwang, H.J.; Seo, J.B.; Lee, S.M.; Yun, J.; Kim, M.J.; Jeong, J.; Lee, Y.; Jin, K.; Park, R.; et al. Content-based Image Retrieval by Using Deep Learning for Interstitial Lung Disease Diagnosis with Chest CT. Radiology 2022, 302, 187–197. [Google Scholar] [CrossRef]
- Handa, T.; Tanizawa, K.; Oguma, T.; Uozumi, R.; Watanabe, K.; Tanabe, N.; Niwamoto, T.; Shima, H.; Mori, R.; Nobashi, T.W.; et al. Novel Artificial Intelligence-based Technology for Chest Computed Tomography Analysis of Idiopathic Pulmonary Fibrosis. Ann. Am. Thorac. Soc. 2021, 19, 399–406. [Google Scholar] [CrossRef]
- Huang, C.-Y.; Wu, P.W.; Wong, Y.-C.; Kao, K.-C.; Huang, C.-C. Effects of High-Resolution CT Changes on Prognosis Predictability in Acute Respiratory Distress Syndrome with Diffuse Alveolar Damage. J. Clin. Med. 2022, 11, 2458. [Google Scholar] [CrossRef] [PubMed]
- Fujisawa, T.; Horiike, Y.; Egashira, R.; Sumikawa, H.; Iwasawa, T.; Matsushita, S.; Sugiura, H.; Kataoka, K.; Hashisako, M.; Yasui, H.; et al. Radiological pleuroparenchymal fibroelastosis-like lesion in idiopathic interstitial pneumonias. Respir. Res. 2021, 22, 290. [Google Scholar] [CrossRef] [PubMed]
- Sumikawa, H.; Johkoh, T.; Iwasawa, T.; Nakanishi, K.; Tomiyama, N. Pleuroparenchymal fibroelastosis-like lesions on chest computed tomography in routine clinical practice. Jpn. J. Radiol. 2019, 37, 230–236. [Google Scholar] [CrossRef] [PubMed]
- Sumikawa, H.; Johkoh, T.; Egashira, R.; Sugiura, H.; Yamano, Y.; Kataoka, K.; Kondoh, Y.; Arakawa, H.; Nakamura, M.; Kuriu, A.; et al. Pleuroparenchymal fibroelastosis-like lesions in patients with interstitial pneumonia diagnosed by multidisciplinary discussion with surgical lung biopsy. Eur. J. Radiol. Open 2020, 7, 100298. [Google Scholar] [CrossRef]
- Egashira, R.; Yamaguchi, K.; Kondo, T.; Nakazono, T.; Fukui, S.; Irie, H. Pleuroparenchymal fibroelastosis (PPFE)-like finding on CT in daily practice—Prevalence and serial changes. Eur. J. Radiol. Open 2020, 7, 100296. [Google Scholar] [CrossRef]
- Oda, T.; Sekine, A.; Tabata, E.; Iwasawa, T.; Takemura, T.; Ogura, T. Comparison of Clinical Characteristics and Outcomes between Idiopathic and Secondary Pleuroparenchymal Fibroelastosis. J. Clin. Med. 2021, 10, 846. [Google Scholar] [CrossRef]
- Maldonado, F.; Moua, T.; Rajagopalan, S.; Karwoski, R.A.; Raghunath, S.; Decker, P.A.; Hartman, T.E.; Bartholmai, B.J.; Robb, R.A.; Ryu, J.H. Automated quantification of radiological patterns predicts survival in idiopathic pulmonary fibrosis. Eur. Respir. J. 2014, 43, 204–212. [Google Scholar] [CrossRef] [Green Version]
- Iwasawa, T.; Kanauchi, T.; Hoshi, T.; Ogura, T.; Baba, T.; Gotoh, T.; Oba, M.S. Multicenter study of quantitative computed tomography analysis using a computer-aided three-dimensional system in patients with idiopathic pulmonary fibrosis. Jpn. J. Radiol. 2016, 34, 16–27. [Google Scholar] [CrossRef]
- Salisbury, M.L.; Lynch, D.A.; van Beek, E.J.; Kazerooni, E.A.; Guo, J.; Xia, M.; Murray, S.; Anstrom, K.J.; Yow, E.; Martinez, F.J.; et al. Idiopathic Pulmonary Fibrosis: The Association between the Adaptive Multiple Features Method and Fibrosis Outcomes. Am. J. Respir. Crit. Care Med. 2017, 195, 921–929. [Google Scholar] [CrossRef] [Green Version]
- Travis, W.D.; Costabel, U.; Hansell, D.M.; King, T.E., Jr.; Lynch, D.A.; Nicholson, A.G.; Ryerson, C.J.; Ryu, J.H.; Selman, M.; Wells, A.U.; et al. An official American Thoracic Society/European Respiratory Society statement: Update of the international multidisciplinary classification of the idiopathic interstitial pneumonias. Am. J. Respir. Crit. Care Med. 2013, 188, 733–748. [Google Scholar] [CrossRef]
- Raghu, G.; Remy-Jardin, M.; Myers, J.L.; Richeldi, L.; Ryerson, C.J.; Lederer, D.J.; Behr, J.; Cottin, V.; Danoff, S.K.; Morell, F.; et al. Diagnosis of Idiopathic Pulmonary Fibrosis. An Official ATS/ERS/JRS/ALAT Clinical Practice Guideline. Am. J. Respir. Crit. Care Med. 2018, 198, e44–e68. [Google Scholar] [CrossRef]
- Iwao, Y.; Gotoh, T.; Kagei, S.; Iwasawa, T.; Tsuzuki, M.d.S.G. Integrated lung field segmentation of injured region with anatomical structure analysis by failure–recovery algorithm from chest CT images. Biomed. Signal Process. Control. 2014, 12, 28–38. [Google Scholar] [CrossRef] [Green Version]
- Iwasawa, T.; Takemura, T.; Okudera, K.; Gotoh, T.; Iwao, Y.; Kitamura, H.; Baba, T.; Ogura, T.; Oba, M.S. The importance of subpleural fibrosis in the prognosis of patients with idiopathic interstitial pneumonias. Eur. J. Radiol. 2017, 90, 106–113. [Google Scholar] [CrossRef]
- Iwasawa, T.; Iwao, Y.; Takemura, T.; Okudela, K.; Gotoh, T.; Baba, T.; Ogura, T.; Oba, M.S. Extraction of the subpleural lung region from computed tomography images to detect interstitial lung disease. Jpn. J. Radiol. 2017, 35, 681–688. [Google Scholar] [CrossRef]
- Iwasawa, T.; Okudela, K.; Takemura, T.; Fukuda, T.; Matsushita, S.; Baba, T.; Ogura, T.; Tajiri, M.; Yoshizawa, A. Computer-aided Quantification of Pulmonary Fibrosis in Patients with Lung Cancer: Relationship to Disease-free Survival. Radiology 2019, 292, 489–498. [Google Scholar] [CrossRef]
- Yamakawa, H.; Hagiwara, E.; Kitamura, H.; Iwasawa, T.; Otoshi, R.; Aiko, N.; Katano, T.; Shintani, R.; Ikeda, S.; Okuda, R.; et al. Predictive Factors for the Long-Term Deterioration of Pulmonary Function in Interstitial Lung Disease Associated with Anti-Aminoacyl-tRNA Synthetase Antibodies. Respiration 2018, 96, 210–221. [Google Scholar] [CrossRef]
- Aoki, R.; Iwasawa, T.; Hagiwara, E.; Komatsu, S.; Utsunomiya, D.; Ogura, T. Pulmonary vascular enlargement and lesion extent on computed tomography are correlated with COVID-19 disease severity. Jpn. J. Radiol. 2021, 39, 451–458. [Google Scholar] [CrossRef]
- Kato, S.; Ishiwata, Y.; Aoki, R.; Iwasawa, T.; Hagiwara, E.; Ogura, T.; Utsunomiya, D. Imaging of COVID-19: An update of current evidences. Diagn. Interv. Imaging 2021, 102, 493–500. [Google Scholar] [CrossRef]
- Lee, J.E.; Chae, K.J.; Suh, Y.J.; Jeong, W.G.; Lee, T.; Kim, Y.-H.; Jin, G.Y.; Jeong, Y.J. Prevalence and Long-term Outcomes of CT Interstitial Lung Abnormalities in a Health Screening Cohort. Radiology 2022, 221172. [Google Scholar] [CrossRef]
- Wu, F.Z.; Huang, Y.L.; Wu, C.C.; Tang, E.K.; Chen, C.S.; Mar, G.Y.; Yen, Y.; Wu, M.T. Assessment of Selection Criteria for Low-Dose Lung Screening CT Among Asian Ethnic Groups in Taiwan: From Mass Screening to Specific Risk-Based Screening for Non-Smoker Lung Cancer. Clin. Lung Cancer 2016, 17, e45–e56. [Google Scholar] [CrossRef]
- National Lung Screening Trial Research Team. Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening. N. Engl. J. Med. 2011, 365, 395–409. [Google Scholar] [CrossRef]
Demographics and Clinical Characteristics | Number (%), or Mean (SD) | ||
---|---|---|---|
Total Number of Patients | 104 | ||
Age (years) | 69 (9.5) | ||
Sex (M/F) | 73/31 (70.2/29.8%) | ||
Clinical diagnosis | ILD | IPF | 40 (38.5%) |
CTD-ILD | 18 (17.3%) | ||
Unclassifiable idiopathic interstitial pneumonia | 16 (15.4%) | ||
Nonspecific interstitial pneumonia | 3 (2.9%) | ||
Chronic hypersensitivity pneumonia | 4 (3.8%) | ||
Organizing pneumonia | 1 (1.0%) | ||
Idiopathic pleuroparenchymal fibroelastosis | 2 (1.9%) | ||
Non-ILD | COPD | 12 (11.5%) | |
Pulmonary nodules | 4 (3.8%) | ||
Pleural plaques | 2 (1.9%) | ||
No lesion | 2 (1.9%) | ||
Follow-up period (days) | 1035 (490.2) |
Classification | ||
---|---|---|
Lesion characteristics | CAD (GHNC) | DL (QZIP) |
Normal | NCAD | NDL |
Emphysema | ECAD | EDL |
Ground glass opacity | GCAD | GDL |
Consolidation | CCAD | CDL |
Consolidation with fibrosis (traction bronchiectasis) | - | CFDL |
Reticulation | RCAD | RDL |
Honeycombing | HCAD | HDL |
Traction bronchiectasis | - | TDL |
Total fibrotic lesion | FibCAD = RCAD + HCAD | FibDL = CFDL + RDL + HDL + TDL |
Lesion Pattern | Volume (mm3) | Paired-Samples t-Test | Pearson Correlation (r, p-Value) | Bland-Altman Analysis (Bias [95%CI]) | |
---|---|---|---|---|---|
CAD System (Mean [SD]) | DL-Based Analysis (Mean [SD]) | ||||
Whole lung | 4059.8 (1180.1) | 4178.2 (1180.0) | p < 0.001 | r = 0.999, p < 0.001 | −118.3 (−130.2 to −106.4) |
Normal lung | NCAD: 2883.8 (1158.3) | NDL: 3331.5 (1398.1) | p < 0.001 | r = 0.950, p < 0.001 | −447.8 (−533.0 to −362.5) |
GGO | GCAD: 278.6 (131.7) | GDL: 197.0 (203.7) | p < 0.001 | r = 0.719, p < 0.001 | 81.6 (53.9 to 109.3) |
Consolidation | CCAD: 14.7 (35.5) | CDL: 54.7 (61.7) | p < 0.001 | r = 0.742, p < 0.001 | −40.0 (−48.3 to −31.7) |
Total fibrotic lesion | HCAD: 337.5 (205.7) | CFDL: 39.8 (64.1) | p < 0.001 | r = 0.936, p < 0.001 | 151.5 (126.3 to 176.7) |
HDL: 71.4 (161.4) | |||||
RCAD: 131.0 (128.0) | RDL: 152.1 (156.9) | ||||
TDL: 53.9 (58.1) | |||||
Emphysema | ECAD: 414.3 (647.0) | EDL: 55.8 (130.0) | p < 0.001 | r = 0.795, p < 0.001 | 136.4 (59.7 to 213.1) |
Number of ROIs | DL-Based Analysis Accuracy (95% Confidence Interval) | CAD Accuracy (95% Confidence Interval) | |
---|---|---|---|
Normal | 108 | 1.00 | 0.995 |
(1.00–0.989) | (1.00–0.989) | ||
Emphysema | 66 | 0.995 | 0.887 |
(1.00–0.988) | (0.941–0.831) | ||
Ground-glass opacities | 85 | 0.922 | 0.529 |
(0.986–0.959) | (0.600–0.446) | ||
Consolidation | 63 | 0.995 | 0.803 |
(1.00–0.980) | (0.762–0.563) | ||
Consolidation with fibrosis | 48 | 0.973 | - |
(0.993–0.958) | |||
Honeycomb | 39 | 0.976 | 0.792 |
(0.996–0.957) | (0.857–0.727) | ||
Reticulation | 82 | 0.984 | 0.706 |
(0.995–0.975) | (0.771–0.639) | ||
Traction bronchiectasis | 58 | 0.943 | - |
(0.963–0.915) |
Pulmonary Function Test | N | Categories in the DL-Based Analysis | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
Whole Lung | NDL | GDL | CDL | CFDL | HDL | RDL | TDL | EDL | FibDL | ||
TLC | 85 | r = 0.924 | r = 0.836 | r = −0.234 | r = −0.321 | r = −0.224 | r = −0.145 | r = −0.369 | r = −0.246 | r = 0.301 | r = −0.323 |
p < 0.001 | p < 0.001 | p = 0.031 | p = 0.003 | p = 0.039 | p = 0.186 | p = 0.001 | p = 0.023 | p = 0.005 | p 0.003 | ||
FVC | 100 | r = 0.832 | r = 0.789 | r = −0.306 | r = −0.291 | r = −0.316 | r = −0.073 | r = −0.338 | r = −0.233 | r = 0.134 | r = −0.288 |
p < 0.001 | p < 0.001 | p = 0.002 | p = 0.003 | p = 0.001 | p = 0.470 | p = 0.001 | p = 0.002 | p = 0.185 | p 0.004 | ||
FEV1 | 100 | r = 0.682 | r = 0.701 | r = −0.158 | r = −0.148 | r = −0.191 | r = −0.089 | r = −0.199 | r = −0.114 | r = −0.102 | r = −0.188 |
p < 0.001 | p < 0.001 | p = 0.117 | p = 0.142 | p = 0.057 | p = 0.379 | p = 0.048 | p = 0.257 | p 0.314 | p 0.061 | ||
DLCO | 85 | r = 0.617 | r = 0.794 | r = −0.204 | r = −0.206 | r = −0.399 | r = −0.440 | r = −0.491 | r = −0.463 | r = −0.130 | r = −0.597 |
p < 0.001 | p < 0.001 | p = 0.061 | p = 0.059 | p < 0.001 | p < 0.001 | p < 0.001 | p < 0.001 | p 0.235 | p < 0.001 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. 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/).
Share and Cite
Aoki, R.; Iwasawa, T.; Saka, T.; Yamashiro, T.; Utsunomiya, D.; Misumi, T.; Baba, T.; Ogura, T. Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis. Diagnostics 2022, 12, 3038. https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12123038
Aoki R, Iwasawa T, Saka T, Yamashiro T, Utsunomiya D, Misumi T, Baba T, Ogura T. Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis. Diagnostics. 2022; 12(12):3038. https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12123038
Chicago/Turabian StyleAoki, Ryo, Tae Iwasawa, Tomoki Saka, Tsuneo Yamashiro, Daisuke Utsunomiya, Toshihiro Misumi, Tomohisa Baba, and Takashi Ogura. 2022. "Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis" Diagnostics 12, no. 12: 3038. https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12123038