Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle
In this study, we present a deep learning model for fracture classification on shoulder radiographs using a convolutional neural network (CNN). The primary aim was to evaluate the classification performance of the CNN for proximal humeral fractures (PHF) based on the AO/OTA classification system. Se...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10468075/?tool=EBI |
| _version_ | 1797692809056092160 |
|---|---|
| author | Martin Magnéli Petter Ling Jacob Gislén Johan Fagrell Yilmaz Demir Erica Domeij Arverud Kristofer Hallberg Björn Salomonsson Max Gordon |
| author_facet | Martin Magnéli Petter Ling Jacob Gislén Johan Fagrell Yilmaz Demir Erica Domeij Arverud Kristofer Hallberg Björn Salomonsson Max Gordon |
| author_sort | Martin Magnéli |
| collection | DOAJ |
| description | In this study, we present a deep learning model for fracture classification on shoulder radiographs using a convolutional neural network (CNN). The primary aim was to evaluate the classification performance of the CNN for proximal humeral fractures (PHF) based on the AO/OTA classification system. Secondary objectives included evaluating the model’s performance for diaphyseal humerus, clavicle, and scapula fractures. The training dataset consisted of 6,172 examinations, including 2–7 radiographs per examination. The overall area under the curve (AUC) for fracture classification was 0.89, indicating good performance. For PHF classification, 12 out of 16 classes achieved an AUC of 0.90 or greater. Additionally, the CNN model had excellent overall AUC for diaphyseal humerus fractures (0.97), clavicle fractures (0.96), and good AUC for scapula fractures (0.87). Despite the limitations of the study, such as the reliance on ground truth labels provided by students with limited radiographic assessment experience, our findings are in concordance with previous studies, further consolidating CNN as potent fracture classifiers in plain radiographs. The inclusion of multiple radiographs with different views from each examination, as well as the generally unselected nature of the sample, contributed to the overall generalizability of the study. This is the fifth study published by our group on AI in orthopaedic radiographs, which has consistently shown promising results. The next challenge for the orthopaedic research community will be to transfer these results from the research setting into clinical practice. External validation of the CNN model should be conducted in the future before it is considered for use in a clinical setting. |
| first_indexed | 2024-03-12T02:32:56Z |
| format | Article |
| id | doaj.art-8a1122a6fa5f401284c65e914daa399e |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-03-12T02:32:56Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-8a1122a6fa5f401284c65e914daa399e2023-09-05T05:31:43ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01188Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicleMartin MagnéliPetter LingJacob GislénJohan FagrellYilmaz DemirErica Domeij ArverudKristofer HallbergBjörn SalomonssonMax GordonIn this study, we present a deep learning model for fracture classification on shoulder radiographs using a convolutional neural network (CNN). The primary aim was to evaluate the classification performance of the CNN for proximal humeral fractures (PHF) based on the AO/OTA classification system. Secondary objectives included evaluating the model’s performance for diaphyseal humerus, clavicle, and scapula fractures. The training dataset consisted of 6,172 examinations, including 2–7 radiographs per examination. The overall area under the curve (AUC) for fracture classification was 0.89, indicating good performance. For PHF classification, 12 out of 16 classes achieved an AUC of 0.90 or greater. Additionally, the CNN model had excellent overall AUC for diaphyseal humerus fractures (0.97), clavicle fractures (0.96), and good AUC for scapula fractures (0.87). Despite the limitations of the study, such as the reliance on ground truth labels provided by students with limited radiographic assessment experience, our findings are in concordance with previous studies, further consolidating CNN as potent fracture classifiers in plain radiographs. The inclusion of multiple radiographs with different views from each examination, as well as the generally unselected nature of the sample, contributed to the overall generalizability of the study. This is the fifth study published by our group on AI in orthopaedic radiographs, which has consistently shown promising results. The next challenge for the orthopaedic research community will be to transfer these results from the research setting into clinical practice. External validation of the CNN model should be conducted in the future before it is considered for use in a clinical setting.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10468075/?tool=EBI |
| spellingShingle | Martin Magnéli Petter Ling Jacob Gislén Johan Fagrell Yilmaz Demir Erica Domeij Arverud Kristofer Hallberg Björn Salomonsson Max Gordon Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle PLoS ONE |
| title | Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle |
| title_full | Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle |
| title_fullStr | Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle |
| title_full_unstemmed | Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle |
| title_short | Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle |
| title_sort | deep learning classification of shoulder fractures on plain radiographs of the humerus scapula and clavicle |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10468075/?tool=EBI |
| work_keys_str_mv | AT martinmagneli deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT petterling deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT jacobgislen deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT johanfagrell deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT yilmazdemir deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT ericadomeijarverud deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT kristoferhallberg deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT bjornsalomonsson deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle AT maxgordon deeplearningclassificationofshoulderfracturesonplainradiographsofthehumerusscapulaandclavicle |