Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules
Abstract Background To develop a fully automated CNN detection system based on magnetic resonance imaging (MRI) for ACL injury, and to explore the feasibility of CNN for ACL injury detection on MRI images. Methods Including 313 patients aged 16 – 65 years old, the raw data are 368 pieces with injure...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-09-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-023-01091-6 |
| _version_ | 1797555668340703232 |
|---|---|
| author | Chen Liang Xiang Li Yong Qin Minglei Li Yingkai Ma Ren Wang Xiangning Xu Jinping Yu Songcen Lv Hao Luo |
| author_facet | Chen Liang Xiang Li Yong Qin Minglei Li Yingkai Ma Ren Wang Xiangning Xu Jinping Yu Songcen Lv Hao Luo |
| author_sort | Chen Liang |
| collection | DOAJ |
| description | Abstract Background To develop a fully automated CNN detection system based on magnetic resonance imaging (MRI) for ACL injury, and to explore the feasibility of CNN for ACL injury detection on MRI images. Methods Including 313 patients aged 16 – 65 years old, the raw data are 368 pieces with injured ACL and 100 pieces with intact ACL. By adding flipping, rotation, scaling and other methods to expand the data, the final data set is 630 pieces including 355 pieces of injured ACL and 275 pieces of intact ACL. Using the proposed CNN model with two attention mechanism modules, data sets are trained and tested with fivefold cross-validation. Results The performance is evaluated using accuracy, precision, sensitivity, specificity and F1 score of our proposed CNN model, with results of 0.8063, 0.7741, 0.9268, 0.6509 and 0.8436. The average accuracy in the fivefold cross-validation is 0.8064. For our model, the average area under curves (AUC) for detecting injured ACL has results of 0.8886. Conclusion We propose an effective and automatic CNN model to detect ACL injury from MRI of human knees. This model can effectively help clinicians diagnose ACL injury, improving diagnostic efficiency and reducing misdiagnosis and missed diagnosis. |
| first_indexed | 2024-03-10T16:50:47Z |
| format | Article |
| id | doaj.art-6ab002d17de14ee0922868143e351f5b |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-03-10T16:50:47Z |
| publishDate | 2023-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-6ab002d17de14ee0922868143e351f5b2023-11-20T11:18:40ZengBMCBMC Medical Imaging1471-23422023-09-0123111310.1186/s12880-023-01091-6Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modulesChen Liang0Xiang Li1Yong Qin2Minglei Li3Yingkai Ma4Ren Wang5Xiangning Xu6Jinping Yu7Songcen Lv8Hao Luo9Department of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Control Science and Engineering, Harbin Institute of TechnologyDepartment of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Control Science and Engineering, Harbin Institute of TechnologyDepartment of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Minimally Invasive Surgery and Sports Medicine, The 2Nd Affiliated Hospital of Harbin Medical UniversityDepartment of Control Science and Engineering, Harbin Institute of TechnologyAbstract Background To develop a fully automated CNN detection system based on magnetic resonance imaging (MRI) for ACL injury, and to explore the feasibility of CNN for ACL injury detection on MRI images. Methods Including 313 patients aged 16 – 65 years old, the raw data are 368 pieces with injured ACL and 100 pieces with intact ACL. By adding flipping, rotation, scaling and other methods to expand the data, the final data set is 630 pieces including 355 pieces of injured ACL and 275 pieces of intact ACL. Using the proposed CNN model with two attention mechanism modules, data sets are trained and tested with fivefold cross-validation. Results The performance is evaluated using accuracy, precision, sensitivity, specificity and F1 score of our proposed CNN model, with results of 0.8063, 0.7741, 0.9268, 0.6509 and 0.8436. The average accuracy in the fivefold cross-validation is 0.8064. For our model, the average area under curves (AUC) for detecting injured ACL has results of 0.8886. Conclusion We propose an effective and automatic CNN model to detect ACL injury from MRI of human knees. This model can effectively help clinicians diagnose ACL injury, improving diagnostic efficiency and reducing misdiagnosis and missed diagnosis.https://doi.org/10.1186/s12880-023-01091-6Anterior cruciate ligament (ACL) injuryConvolutional neural network (CNN)Magnetic resonance imaging (MRI)Artificial intelligence (AI) |
| spellingShingle | Chen Liang Xiang Li Yong Qin Minglei Li Yingkai Ma Ren Wang Xiangning Xu Jinping Yu Songcen Lv Hao Luo Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules BMC Medical Imaging Anterior cruciate ligament (ACL) injury Convolutional neural network (CNN) Magnetic resonance imaging (MRI) Artificial intelligence (AI) |
| title | Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules |
| title_full | Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules |
| title_fullStr | Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules |
| title_full_unstemmed | Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules |
| title_short | Effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules |
| title_sort | effective automatic detection of anterior cruciate ligament injury using convolutional neural network with two attention mechanism modules |
| topic | Anterior cruciate ligament (ACL) injury Convolutional neural network (CNN) Magnetic resonance imaging (MRI) Artificial intelligence (AI) |
| url | https://doi.org/10.1186/s12880-023-01091-6 |
| work_keys_str_mv | AT chenliang effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT xiangli effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT yongqin effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT mingleili effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT yingkaima effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT renwang effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT xiangningxu effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT jinpingyu effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT songcenlv effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules AT haoluo effectiveautomaticdetectionofanteriorcruciateligamentinjuryusingconvolutionalneuralnetworkwithtwoattentionmechanismmodules |