article Open AccessTop 1% cited

Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs

European Radiology · 2019 · Vol. 29(10) · pp. 5469–5477

Chi‐Tung Cheng(National Yang Ming Chiao Tung University)Tsung‐Ying Ho(Chang Gung University)Tao-Yi Lee(University of California, Irvine)C. C. Chang(Chang Gung University)Ching-Cheng Chou(Chang Gung University)Chih-Chi Chen(Chang Gung University)I‐Fang Chung(National Yang Ming Chiao Tung University)Chien‐Hung Liao✉(Chang Gung Memorial Hospital)

View via DOI Full-text PDF

Abstract

• Automated detection of hip fractures on frontal pelvic radiographs may facilitate emergent screening and evaluation efforts for primary physicians. • Good visualization of the fracture site by Grad-CAM enables the rapid integration of this tool into the current medical system. • The feasibility and efficiency of utilizing a deep neural network have been confirmed for the screening of hip fractures.

Hip and Femur Fractures Pelvic and Acetabular Injuries Medical Imaging and AnalysisMedicineRadiographyConvolutional neural networkRadiologyHip fractureFalse positive rateReceiver operating characteristicAlgorithmDiagnostic accuracyVisualization

MeSH terms

Deep LearningAdultAgedAged, 80 and overAlgorithmsFalse Negative ReactionsFeasibility StudiesFemaleHip FracturesHumansMaleMiddle AgedPrognosisRadiographic Image Interpretation, Computer-AssistedRadiography, Abdominal

Citations

303

FWCI

34.24

field-weighted impact

References

Percentile

100%

vs. same field & year

Citations per year

References

The worldwide problem of osteoporosis: Insights afforded by epidemiology