Aims and objectives
The Advanced Trauma Life Support (ATLS) protocol is widely considered the standard of care for the management of acute trauma cases (Kortbeek et al.
2008).
The protocol involves a primary survey which addresses the detection and management of life-threatening issues,
which includes pelvic radiography to identify post-traumatic injuries which can be a source of severe bleeding and potentially death (Thiyam et al.
2015). Therefore,
rapid and accurate interpretation of pelvic radiographs is essential in the evaluation of trauma patients to help with a wide range...
Methods and materials
Patient Population and Labels:
The study employed a retrospective case-control study concerning routinely performed exams at two academic tertiary care hospitals.
We performed a keyphrase electronic search for adult patients who had underwent emergency pelvic radiograph studies from January 2006 to December 2017.
5560 frontal pelvic radiographs were identified.
We then identified 613 positive cases of acute fracture or dislocation and 4947 negative controls.
All positive cases were reviewed by a radiology fellow in order to label the presence,
and specific involved image quadrant(s) of...
Results
The model obtained an Test set AUC of 0.808 on the Full View (‘FULL’) test set and 0.888 on the Quadrant View (‘QUADS’) test set (Fig. 2).
The utilization of sub-quadrant augmentation yielded higher resolution class-activation maps resolving finer details than Full View class-activation maps.
Contrary to initial expectations,
the presence of visual artifacts such as surgical clips,
radiopaque debris,
or a trauma board did not interfere significantly with detection or findings localization.
Class-activation maps showed stronger activation for large displaced or radio-opaque fractures (Fig....
Conclusion
In this preliminary study,
we aimed to train a deep learning model to detect the presence of pelvic fracture or dislocation on routine trauma antero-posterior radiographs.
This initial proof of concept demonstrated some early network trainability given the limited training gold standard of single reviewer labels.
Generalizability of this system could perhaps be improved with a more comprehensive dataset and and consensus review of training labels.
Early AUC results are encouraging.
However,
even if an AUC of 0.888 is similar to prior bone fracture studies...
References
Adams M,
Chen W,
Holcdorf D,
McCusker MW,
Howe PD,
Gaillard F.
Computer vs uman: Deep learning versus perceptual training for the detection of neck of femur fractures.
J Med Imaging Radiat Oncol.
2018 Nov 8.
doi:10.1111/1754-9485.12828.
DeLong ER,
DeLong DM,
Clarke-Pearson DL.
Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach.
Biometrics.
1988 Sep;44(3):837-45.
Gale,
W.,
Oakden-Rayner,
L.,
Carneiro,
G.,
Bradley,
A.P.,
& Palmer,
L.J.
(Nov 2017).
Detecting hip fractures with radiologist-level performance using deep neural networks.
CoRR,...