Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis
We investigated the feasibility of a new deep-learning (DL)-based lung analysis method for the evaluation of interstitial lung disease (ILD) by comparing it with evaluation using the traditional computer-aided diagnosis (CAD) system and patients’ clinical outcomes. We prospectively included 104 pati...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/12/3038 |
| _version_ | 1827641072939958272 |
|---|---|
| author | Ryo Aoki Tae Iwasawa Tomoki Saka Tsuneo Yamashiro Daisuke Utsunomiya Toshihiro Misumi Tomohisa Baba Takashi Ogura |
| author_facet | Ryo Aoki Tae Iwasawa Tomoki Saka Tsuneo Yamashiro Daisuke Utsunomiya Toshihiro Misumi Tomohisa Baba Takashi Ogura |
| author_sort | Ryo Aoki |
| collection | DOAJ |
| description | We investigated the feasibility of a new deep-learning (DL)-based lung analysis method for the evaluation of interstitial lung disease (ILD) by comparing it with evaluation using the traditional computer-aided diagnosis (CAD) system and patients’ clinical outcomes. We prospectively included 104 patients (84 with and 20 without ILD). An expert radiologist defined regions of interest in the typical areas of normal, ground-glass opacity, consolidation, consolidation with fibrosis (traction bronchiectasis), honeycombing, reticulation, traction bronchiectasis, and emphysema, and compared them with the CAD and DL-based analysis results. Next, we measured the extent of ILD lesions with the CAD and DL-based analysis and compared them. Finally, we compared the lesion extent on computed tomography (CT) images, as measured with the DL-based analysis, with pulmonary function tests results and patients’ overall survival. Pearson’s correlation analysis revealed a significant correlation between DL-based analysis and CAD results. Forced vital capacity was significantly correlated with DL-based analysis (r = 0.789, <i>p</i> < 0.001 for normal lung volume and r = −0.316, <i>p</i> = 0.001 for consolidation with fibrosis volume). Consolidation with fibrosis measured using DL-based analysis was independently associated with poor survival. The lesion extent measured using DL-based analysis showed a negative correlation with the pulmonary function test results and prognosis. |
| first_indexed | 2024-03-09T17:08:14Z |
| format | Article |
| id | doaj.art-48c01a370f654f47893d2b15cdaedb39 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T17:08:14Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-48c01a370f654f47893d2b15cdaedb392023-11-24T14:17:35ZengMDPI AGDiagnostics2075-44182022-12-011212303810.3390/diagnostics12123038Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and PrognosisRyo Aoki0Tae Iwasawa1Tomoki Saka2Tsuneo Yamashiro3Daisuke Utsunomiya4Toshihiro Misumi5Tomohisa Baba6Takashi Ogura7Diagnostic Radiology, Yokohama City University Graduate School of Medicine, 3-9 Fukuura, Kanazawa-ku, Yokohama 236-0004, Kanagawa, JapanDiagnostic Radiology, Yokohama City University Graduate School of Medicine, 3-9 Fukuura, Kanazawa-ku, Yokohama 236-0004, Kanagawa, JapanKanazawa Institute of Technology, 7-1 Ohgigaoka, Nonoichi 921-8501, Ishikawa, JapanDiagnostic Radiology, Yokohama City University Graduate School of Medicine, 3-9 Fukuura, Kanazawa-ku, Yokohama 236-0004, Kanagawa, JapanDiagnostic Radiology, Yokohama City University Graduate School of Medicine, 3-9 Fukuura, Kanazawa-ku, Yokohama 236-0004, Kanagawa, JapanDepartment of Biostatistics, Yokohama City University School of Medicine, 3-9 Fukuura, Kanazawa-ku, Yokohama 236-0004, Kanagawa, JapanDepartment of Respiratory Medicine, Kanagawa Cardiovascular and Respiratory Center, 6-16-1 Tomioka-higashi, Kanazawa-ku, Yokohama 236-0051, Kanagawa, JapanDepartment of Respiratory Medicine, Kanagawa Cardiovascular and Respiratory Center, 6-16-1 Tomioka-higashi, Kanazawa-ku, Yokohama 236-0051, Kanagawa, JapanWe investigated the feasibility of a new deep-learning (DL)-based lung analysis method for the evaluation of interstitial lung disease (ILD) by comparing it with evaluation using the traditional computer-aided diagnosis (CAD) system and patients’ clinical outcomes. We prospectively included 104 patients (84 with and 20 without ILD). An expert radiologist defined regions of interest in the typical areas of normal, ground-glass opacity, consolidation, consolidation with fibrosis (traction bronchiectasis), honeycombing, reticulation, traction bronchiectasis, and emphysema, and compared them with the CAD and DL-based analysis results. Next, we measured the extent of ILD lesions with the CAD and DL-based analysis and compared them. Finally, we compared the lesion extent on computed tomography (CT) images, as measured with the DL-based analysis, with pulmonary function tests results and patients’ overall survival. Pearson’s correlation analysis revealed a significant correlation between DL-based analysis and CAD results. Forced vital capacity was significantly correlated with DL-based analysis (r = 0.789, <i>p</i> < 0.001 for normal lung volume and r = −0.316, <i>p</i> = 0.001 for consolidation with fibrosis volume). Consolidation with fibrosis measured using DL-based analysis was independently associated with poor survival. The lesion extent measured using DL-based analysis showed a negative correlation with the pulmonary function test results and prognosis.https://www.mdpi.com/2075-4418/12/12/3038computed tomographydeep-learninginterstitial lung diseasequantitative analyses |
| spellingShingle | Ryo Aoki Tae Iwasawa Tomoki Saka Tsuneo Yamashiro Daisuke Utsunomiya Toshihiro Misumi Tomohisa Baba Takashi Ogura Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis Diagnostics computed tomography deep-learning interstitial lung disease quantitative analyses |
| title | Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis |
| title_full | Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis |
| title_fullStr | Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis |
| title_full_unstemmed | Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis |
| title_short | Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis |
| title_sort | effects of automatic deep learning based lung analysis on quantification of interstitial lung disease correlation with pulmonary function test results and prognosis |
| topic | computed tomography deep-learning interstitial lung disease quantitative analyses |
| url | https://www.mdpi.com/2075-4418/12/12/3038 |
| work_keys_str_mv | AT ryoaoki effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT taeiwasawa effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT tomokisaka effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT tsuneoyamashiro effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT daisukeutsunomiya effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT toshihiromisumi effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT tomohisababa effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis AT takashiogura effectsofautomaticdeeplearningbasedlunganalysisonquantificationofinterstitiallungdiseasecorrelationwithpulmonaryfunctiontestresultsandprognosis |