Hsuan-Yu Chen1,2,3, Benny Wei-Yun Hsu4, Yu-Kai Yin4, Feng-Huei Lin1, Tsung-Han Yang2,3, Rong-Sen Yang2, Chih-Kuo Lee5, Vincent S Tseng4. 1. Institute of Biomedical Engineering, National Taiwan University, Taipei City, Taiwan. 2. Department of Orthopedics, National Taiwan University College of Medicine and National Taiwan University Hospital, Taipei, Taiwan. 3. Department of Orthopedics, National Taiwan University HsinChu Hospital, Hsin-Chu, Taiwan. 4. Institute of Computer Science and Engineering, National Chiao Tung University, Hsinchu, Taiwan. 5. Department of Internal Medicine, National Taiwan University HsinChu Hospital, HsinChu, Taiwan.
Abstract
BACKGROUND: Identification of vertebral fractures (VFs) is critical for effective secondary fracture prevention owing to their association with the increasing risks of future fractures. Plain abdominal frontal radiographs (PARs) are a common investigation method performed for a variety of clinical indications and provide an ideal platform for the opportunistic identification of VF. This study uses a deep convolutional neural network (DCNN) to identify the feasibility for the screening, detection, and localization of VFs using PARs. METHODS: A DCNN was pretrained using ImageNet and retrained with 1306 images from the PARs database obtained between August 2015 and December 2018. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were evaluated. The visualization algorithm gradient-weighted class activation mapping (Grad-CAM) was used for model interpretation. RESULTS: Only 46.6% (204/438) of the VFs were diagnosed in the original PARs reports. The algorithm achieved 73.59% accuracy, 73.81% sensitivity, 73.02% specificity, and an AUC of 0.72 in the VF identification. CONCLUSION: Computer driven solutions integrated with the DCNN have the potential to identify VFs with good accuracy when used opportunistically on PARs taken for a variety of clinical purposes. The proposed model can help clinicians become more efficient and economical in the current clinical pathway of fragile fracture treatment.
BACKGROUND: Identification of vertebral fractures (VFs) is critical for effective secondary fracture prevention owing to their association with the increasing risks of future fractures. Plain abdominal frontal radiographs (PARs) are a common investigation method performed for a variety of clinical indications and provide an ideal platform for the opportunistic identification of VF. This study uses a deep convolutional neural network (DCNN) to identify the feasibility for the screening, detection, and localization of VFs using PARs. METHODS: A DCNN was pretrained using ImageNet and retrained with 1306 images from the PARs database obtained between August 2015 and December 2018. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were evaluated. The visualization algorithm gradient-weighted class activation mapping (Grad-CAM) was used for model interpretation. RESULTS: Only 46.6% (204/438) of the VFs were diagnosed in the original PARs reports. The algorithm achieved 73.59% accuracy, 73.81% sensitivity, 73.02% specificity, and an AUC of 0.72 in the VF identification. CONCLUSION: Computer driven solutions integrated with the DCNN have the potential to identify VFs with good accuracy when used opportunistically on PARs taken for a variety of clinical purposes. The proposed model can help clinicians become more efficient and economical in the current clinical pathway of fragile fracture treatment.
Authors: Luca Bogoni; Jane P Ko; Jeffrey Alpert; Vikram Anand; John Fantauzzi; Charles H Florin; Chi Wan Koo; Derek Mason; William Rom; Maria Shiau; Marcos Salganicoff; David P Naidich Journal: J Digit Imaging Date: 2012-12 Impact factor: 4.056
Authors: Pierre D Delmas; Lex van de Langerijt; Nelson B Watts; Richard Eastell; Harry Genant; Andreas Grauer; David L Cahall Journal: J Bone Miner Res Date: 2004-12-06 Impact factor: 6.741
Authors: Dennis M Black; Pierre D Delmas; Richard Eastell; Ian R Reid; Steven Boonen; Jane A Cauley; Felicia Cosman; Péter Lakatos; Ping Chung Leung; Zulema Man; Carlos Mautalen; Peter Mesenbrink; Huilin Hu; John Caminis; Karen Tong; Theresa Rosario-Jansen; Joel Krasnow; Trisha F Hue; Deborah Sellmeyer; Erik Fink Eriksen; Steven R Cummings Journal: N Engl J Med Date: 2007-05-03 Impact factor: 91.245
Authors: A Svedbom; E Hernlund; M Ivergård; J Compston; C Cooper; J Stenmark; E V McCloskey; B Jönsson; J A Kanis Journal: Arch Osteoporos Date: 2013-10-11 Impact factor: 2.617
Authors: Rachel Y L Kuo; Conrad Harrison; Terry-Ann Curran; Benjamin Jones; Alexander Freethy; David Cussons; Max Stewart; Gary S Collins; Dominic Furniss Journal: Radiology Date: 2022-03-29 Impact factor: 29.146