Automated abnormality detection in lower extremity radiographs using deep learning
| Autor: | Bhavik N. Patel, Li Fei-Fei, Jin Long, Jared Dunnmon, Nishith Khandwala, Katie Shpanskaya, Mandy Lu, Matthew P. Lungren, Rachel Gardner, Maya Varma, Christopher F. Beaulieu, Pranav Rajpurkar |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0301 basic medicine
Computer Networks and Communications business.industry Computer science Radiography Deep learning Pattern recognition Convolutional neural network Triage Task (project management) Human-Computer Interaction 03 medical and health sciences Identification (information) 030104 developmental biology 0302 clinical medicine Artificial Intelligence Computer Vision and Pattern Recognition Artificial intelligence Abnormality business 030217 neurology & neurosurgery Software Abnormality detection |
| Zdroj: | Nature Machine Intelligence. 1:578-583 |
| ISSN: | 2522-5839 |
| DOI: | 10.1038/s42256-019-0126-0 |
| Popis: | Musculoskeletal disorders are a major healthcare challenge around the world. We investigate the utility of convolutional neural networks (CNNs) in performing generalized abnormality detection on lower extremity radiographs. We also explore the effect of pretraining, dataset size and model architecture on model performance to provide recommendations for future deep learning analyses on extremity radiographs, especially when access to large datasets is challenging. We collected a large dataset of 93,455 lower extremity radiographs of multiple body parts, with each exam labelled as normal or abnormal. A 161-layer densely connected, pretrained CNN achieved an AUC-ROC of 0.880 (sensitivity = 0.714, specificity = 0.961) on this abnormality classification task. Our findings show that a single CNN model can be effectively utilized for the identification of diverse abnormalities in highly variable radiographs of multiple body parts, a result that holds potential for improving patient triage and assisting with diagnostics in resource-limited settings. Identifying abnormalities in medical images across different viewing angles and body parts is a time-consuming task. Deep learning techniques hold great promise for supporting radiologists and improving patient triage decisions. A new study tests the viability of such approaches in resource-limited settings, exploring the effect of pretraining, dataset size and choice of deep learning model in the task of abnormality detection in lower-limb radiographs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink