A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs
Pelvic radiographs (PXRs) are essential for detecting proximal femur and pelvis injuries in trauma patients, but none of the currently available algorithms can detect all kinds of trauma-related radiographic findings. Here, the authors develop a multiscale deep learning algorithm trained with weakly...
Main Authors: | Chi-Tung Cheng, Yirui Wang, Huan-Wu Chen, Po-Meng Hsiao, Chun-Nan Yeh, Chi-Hsun Hsieh, Shun Miao, Jing Xiao, Chien-Hung Liao, Le Lu |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-02-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-021-21311-3 |
Similar Items
-
Pelvic injury prognosis is more closely related to vascular injury severity than anatomical fracture complexity: the WSES classification for pelvic trauma makes sense
by: Yu-Tung Wu, et al.
Published: (2020-08-01) -
Automatic Hip Detection in Anteroposterior Pelvic Radiographs—A Labelless Practical Framework
by: Feng-Yu Liu, et al.
Published: (2021-06-01) -
Usefulness of Pelvic Radiographs in the Initial Trauma Evaluation with Concurrent CT: Is Additional Radiation Exposure Necessary?
by: Anne K. Misiura, et al.
Published: (2018-01-01) -
Pelvic radiograph in skeletal dysplasias: An approach
by: Manisha Jana, et al.
Published: (2017-04-01) -
Interpreting trauma radiographs
by: Hardy, Maryann L., et al.
Published: (2020)