Using Transfer Learning and Class Activation Maps Supporting Detection and Localization of Femoral Fractures on Anteroposterior Radiographs
| Autor: | Barbaros S. Erdal, Sarah M. Yu, Luciano M. Prevedello, Vikash Gupta, Matthew T. Bigelow, Joseph S. Yu, Richard D. White, Mutlu Demirer |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
medicine.medical_specialty
Musculoskeletal imaging business.industry Radiography 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Quality of life medicine Life expectancy In patient 030212 general & internal medicine Radiology business Transfer of learning |
| Zdroj: | ISBI |
| DOI: | 10.1109/isbi45749.2020.9098436 |
| Popis: | Acute Proximal Femoral Fractures are a growing health concern among the aging population. These fractures are often associated with significant morbidity and mortality as well as reduced quality of life. Furthermore, with the increasing life expectancy owing to advances in healthcare, the number of proximal femoral fractures may increase by a factor of 2 to 3, since the majority of fractures occur in patients over the age of 65. In this paper, we show that by using transfer learning and leveraging pre-trained models, we can achieve very high accuracy in detecting fractures and that they can be localized utilizing class activation maps. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|