Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method
Abstract The computer-aided diagnosis (CAD) for chest X-rays was developed more than 50 years ago. However, there are still unmet needs for its versatile use in our medical fields. We planned this study to develop a multipotent CAD model suitable for general use including in primary care areas. We p...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-11-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-21841-w |
_version_ | 1811230374140837888 |
---|---|
author | Minji Kang Tai Joon An Deokjae Han Wan Seo Kangwon Cho Shinbum Kim Jun-Pyo Myong Sung Won Han |
author_facet | Minji Kang Tai Joon An Deokjae Han Wan Seo Kangwon Cho Shinbum Kim Jun-Pyo Myong Sung Won Han |
author_sort | Minji Kang |
collection | DOAJ |
description | Abstract The computer-aided diagnosis (CAD) for chest X-rays was developed more than 50 years ago. However, there are still unmet needs for its versatile use in our medical fields. We planned this study to develop a multipotent CAD model suitable for general use including in primary care areas. We planned this study to solve the problem by using computed tomography (CT) scan with its one-to-one matched chest X-ray dataset. The data was extracted and preprocessed by pulmonology experts by using the bounding boxes to locate lesions of interest. For detecting multiple lesions, multi-object detection by faster R-CNN and by RetinaNet was adopted and compared. A total of twelve diagnostic labels were defined as the followings: pleural effusion, atelectasis, pulmonary nodule, cardiomegaly, consolidation, emphysema, pneumothorax, chemo-port, bronchial wall thickening, reticular opacity, pleural thickening, and bronchiectasis. The Faster R-CNN model showed higher overall sensitivity than RetinaNet, nevertheless the values of specificity were opposite. Some values such as cardiomegaly and chemo-port showed excellent sensitivity (100.0%, both). Others showed that the unique results such as bronchial wall thickening, reticular opacity, and pleural thickening can be described in the chest area. As far as we know, this is the first study to develop an object detection model for chest X-rays based on chest area defined by CT scans in one-to-one matched manner, preprocessed and conducted by a group of experts in pulmonology. Our model can be a potential tool for detecting the whole chest area with multiple diagnoses from a simple X-ray that is routinely taken in most clinics and hospitals on daily basis. |
first_indexed | 2024-04-12T10:29:26Z |
format | Article |
id | doaj.art-8416979ac5b54fc6bad2535c2bbe696e |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-12T10:29:26Z |
publishDate | 2022-11-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-8416979ac5b54fc6bad2535c2bbe696e2022-12-22T03:36:54ZengNature PortfolioScientific Reports2045-23222022-11-011211910.1038/s41598-022-21841-wDevelopment of a multipotent diagnostic tool for chest X-rays by multi-object detection methodMinji Kang0Tai Joon An1Deokjae Han2Wan Seo3Kangwon Cho4Shinbum Kim5Jun-Pyo Myong6Sung Won Han7School of Industrial and Management Engineering, Korea UniversityDivision of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of KoreaDoctors on the CloudDivision of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of KoreaDivision of Pulmonary, Allergy, and Critical Care Medicine, Department of Internal Medicine, Changwon Fatima HospitalDivision of Pulmonary, Allergy, and Critical Care Medicine, Department of Internal Medicine, Andong Sungso HospitalDepartment of Occupational and Environmental Medicine, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of KoreaSchool of Industrial and Management Engineering, Korea UniversityAbstract The computer-aided diagnosis (CAD) for chest X-rays was developed more than 50 years ago. However, there are still unmet needs for its versatile use in our medical fields. We planned this study to develop a multipotent CAD model suitable for general use including in primary care areas. We planned this study to solve the problem by using computed tomography (CT) scan with its one-to-one matched chest X-ray dataset. The data was extracted and preprocessed by pulmonology experts by using the bounding boxes to locate lesions of interest. For detecting multiple lesions, multi-object detection by faster R-CNN and by RetinaNet was adopted and compared. A total of twelve diagnostic labels were defined as the followings: pleural effusion, atelectasis, pulmonary nodule, cardiomegaly, consolidation, emphysema, pneumothorax, chemo-port, bronchial wall thickening, reticular opacity, pleural thickening, and bronchiectasis. The Faster R-CNN model showed higher overall sensitivity than RetinaNet, nevertheless the values of specificity were opposite. Some values such as cardiomegaly and chemo-port showed excellent sensitivity (100.0%, both). Others showed that the unique results such as bronchial wall thickening, reticular opacity, and pleural thickening can be described in the chest area. As far as we know, this is the first study to develop an object detection model for chest X-rays based on chest area defined by CT scans in one-to-one matched manner, preprocessed and conducted by a group of experts in pulmonology. Our model can be a potential tool for detecting the whole chest area with multiple diagnoses from a simple X-ray that is routinely taken in most clinics and hospitals on daily basis.https://doi.org/10.1038/s41598-022-21841-w |
spellingShingle | Minji Kang Tai Joon An Deokjae Han Wan Seo Kangwon Cho Shinbum Kim Jun-Pyo Myong Sung Won Han Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method Scientific Reports |
title | Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method |
title_full | Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method |
title_fullStr | Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method |
title_full_unstemmed | Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method |
title_short | Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method |
title_sort | development of a multipotent diagnostic tool for chest x rays by multi object detection method |
url | https://doi.org/10.1038/s41598-022-21841-w |
work_keys_str_mv | AT minjikang developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT taijoonan developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT deokjaehan developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT wanseo developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT kangwoncho developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT shinbumkim developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT junpyomyong developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod AT sungwonhan developmentofamultipotentdiagnostictoolforchestxraysbymultiobjectdetectionmethod |