Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study
Abstract Background Chest radiography is the standard investigation for identifying rib fractures. The application of artificial intelligence (AI) for detecting rib fractures on chest radiographs is limited by image quality control and multilesion screening. To our knowledge, few studies have develo...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-01-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-023-00975-x |
| _version_ | 1811171496938176512 |
|---|---|
| author | Jiangfen Wu Nijun Liu Xianjun Li Qianrui Fan Zhihao Li Jin Shang Fei Wang Bowei Chen Yuanwang Shen Pan Cao Zhe Liu Miaoling Li Jiayao Qian Jian Yang Qinli Sun |
| author_facet | Jiangfen Wu Nijun Liu Xianjun Li Qianrui Fan Zhihao Li Jin Shang Fei Wang Bowei Chen Yuanwang Shen Pan Cao Zhe Liu Miaoling Li Jiayao Qian Jian Yang Qinli Sun |
| author_sort | Jiangfen Wu |
| collection | DOAJ |
| description | Abstract Background Chest radiography is the standard investigation for identifying rib fractures. The application of artificial intelligence (AI) for detecting rib fractures on chest radiographs is limited by image quality control and multilesion screening. To our knowledge, few studies have developed and verified the performance of an AI model for detecting rib fractures by using multi-center radiographs. And existing studies using chest radiographs for multiple rib fracture detection have used more complex and slower detection algorithms, so we aimed to create a multiple rib fracture detection model by using a convolutional neural network (CNN), based on multi-center and quality-normalised chest radiographs. Methods A total of 1080 radiographs with rib fractures were obtained and randomly divided into the training set (918 radiographs, 85%) and the testing set (162 radiographs, 15%). An object detection CNN, You Only Look Once v3 (YOLOv3), was adopted to build the detection model. Receiver operating characteristic (ROC) and free-response ROC (FROC) were used to evaluate the model’s performance. A joint testing group of 162 radiographs with rib fractures and 233 radiographs without rib fractures was used as the internal testing set. Furthermore, an additional 201 radiographs, 121 with rib fractures and 80 without rib fractures, were independently validated to compare the CNN model performance with the diagnostic efficiency of radiologists. Results The sensitivity of the model in the training and testing sets was 92.0% and 91.1%, respectively, and the precision was 68.0% and 81.6%, respectively. FROC in the testing set showed that the sensitivity for whole-lesion detection reached 91.3% when the false-positive of each case was 0.56. In the joint testing group, the case-level accuracy, sensitivity, specificity, and area under the curve were 85.1%, 93.2%, 79.4%, and 0.92, respectively. At the fracture level and the case level in the independent validation set, the accuracy and sensitivity of the CNN model were always higher or close to radiologists’ readings. Conclusions The CNN model, based on YOLOv3, was sensitive for detecting rib fractures on chest radiographs and showed great potential in the preliminary screening of rib fractures, which indicated that CNN can help reduce missed diagnoses and relieve radiologists’ workload. In this study, we developed and verified the performance of a novel CNN model for rib fracture detection by using radiography. |
| first_indexed | 2024-04-10T17:14:57Z |
| format | Article |
| id | doaj.art-44b32b1fdc574a79a3b76806094f5497 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-04-10T17:14:57Z |
| publishDate | 2023-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-44b32b1fdc574a79a3b76806094f54972023-02-05T12:27:11ZengBMCBMC Medical Imaging1471-23422023-01-0123111210.1186/s12880-023-00975-xConvolutional neural network for detecting rib fractures on chest radiographs: a feasibility studyJiangfen Wu0Nijun Liu1Xianjun Li2Qianrui Fan3Zhihao Li4Jin Shang5Fei Wang6Bowei Chen7Yuanwang Shen8Pan Cao9Zhe Liu10Miaoling Li11Jiayao Qian12Jian Yang13Qinli Sun14Department of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityInferVision Institute of ResearchGE HealthcareDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversitySchool of Information Science and Technology, Northwest UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityInferVision Institute of ResearchDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Radiology, The First Affiliated Hospital of Xi’an Jiaotong UniversityAbstract Background Chest radiography is the standard investigation for identifying rib fractures. The application of artificial intelligence (AI) for detecting rib fractures on chest radiographs is limited by image quality control and multilesion screening. To our knowledge, few studies have developed and verified the performance of an AI model for detecting rib fractures by using multi-center radiographs. And existing studies using chest radiographs for multiple rib fracture detection have used more complex and slower detection algorithms, so we aimed to create a multiple rib fracture detection model by using a convolutional neural network (CNN), based on multi-center and quality-normalised chest radiographs. Methods A total of 1080 radiographs with rib fractures were obtained and randomly divided into the training set (918 radiographs, 85%) and the testing set (162 radiographs, 15%). An object detection CNN, You Only Look Once v3 (YOLOv3), was adopted to build the detection model. Receiver operating characteristic (ROC) and free-response ROC (FROC) were used to evaluate the model’s performance. A joint testing group of 162 radiographs with rib fractures and 233 radiographs without rib fractures was used as the internal testing set. Furthermore, an additional 201 radiographs, 121 with rib fractures and 80 without rib fractures, were independently validated to compare the CNN model performance with the diagnostic efficiency of radiologists. Results The sensitivity of the model in the training and testing sets was 92.0% and 91.1%, respectively, and the precision was 68.0% and 81.6%, respectively. FROC in the testing set showed that the sensitivity for whole-lesion detection reached 91.3% when the false-positive of each case was 0.56. In the joint testing group, the case-level accuracy, sensitivity, specificity, and area under the curve were 85.1%, 93.2%, 79.4%, and 0.92, respectively. At the fracture level and the case level in the independent validation set, the accuracy and sensitivity of the CNN model were always higher or close to radiologists’ readings. Conclusions The CNN model, based on YOLOv3, was sensitive for detecting rib fractures on chest radiographs and showed great potential in the preliminary screening of rib fractures, which indicated that CNN can help reduce missed diagnoses and relieve radiologists’ workload. In this study, we developed and verified the performance of a novel CNN model for rib fracture detection by using radiography.https://doi.org/10.1186/s12880-023-00975-xRib fractureConvolutional neural networkYOLODetection modelRadiograph |
| spellingShingle | Jiangfen Wu Nijun Liu Xianjun Li Qianrui Fan Zhihao Li Jin Shang Fei Wang Bowei Chen Yuanwang Shen Pan Cao Zhe Liu Miaoling Li Jiayao Qian Jian Yang Qinli Sun Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study BMC Medical Imaging Rib fracture Convolutional neural network YOLO Detection model Radiograph |
| title | Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study |
| title_full | Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study |
| title_fullStr | Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study |
| title_full_unstemmed | Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study |
| title_short | Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study |
| title_sort | convolutional neural network for detecting rib fractures on chest radiographs a feasibility study |
| topic | Rib fracture Convolutional neural network YOLO Detection model Radiograph |
| url | https://doi.org/10.1186/s12880-023-00975-x |
| work_keys_str_mv | AT jiangfenwu convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT nijunliu convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT xianjunli convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT qianruifan convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT zhihaoli convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT jinshang convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT feiwang convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT boweichen convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT yuanwangshen convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT pancao convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT zheliu convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT miaolingli convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT jiayaoqian convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT jianyang convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy AT qinlisun convolutionalneuralnetworkfordetectingribfracturesonchestradiographsafeasibilitystudy |