Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network
- 277 Downloads
To compare performances in diagnosing intertrochanteric hip fractures from proximal femoral radiographs between a convolutional neural network and orthopedic surgeons.
Materials and methods
In total, 1773 patients were enrolled in this study. Hip plain radiographs from these patients were cropped to display only proximal fractured and non-fractured femurs. Images showing pseudarthrosis after femoral neck fracture and those showing artificial objects were excluded. This yielded a total of 3346 hip images (1773 fractured and 1573 non-fractured hip images) that were used to compare performances between the convolutional neural network and five orthopedic surgeons.
The convolutional neural network and orthopedic surgeons had accuracies of 95.5% (95% CI = 93.1–97.6) and 92.2% (95% CI = 89.2–94.9), sensitivities of 93.9% (95% CI = 90.1–97.1) and 88.3% (95% CI = 83.3–92.8), and specificities of 97.4% (95% CI = 94.5–99.4) and 96.8% (95% CI = 95.1–98.4), respectively.
The performance of the convolutional neural network exceeded that of orthopedic surgeons in detecting intertrochanteric hip fractures from proximal femoral radiographs under limited conditions. The convolutional neural network has a significant potential to be a useful tool for screening for fractures on plain radiographs, especially in the emergency room, where orthopedic surgeons are not readily available.
KeywordsFracture Deep learning Orthopedics Convolutional neural network
The authors express their appreciation to Kamimura K, Fujita Y, and Wakui J for reviewing images and would like to thank Editage (www.editage.jp) for English language editing.
The study was conducted without any external funding or grant.
Compliance with ethical standards
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. For this type of study, formal consent is not required.
Conflict of interest
The authors declare that they have no conflicts of interest.
- 2.Jamaludin A, Lootus M, Kadir T, et al. Genodisc consortium. ISSLS prize in bioengineering science 2017: automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. Eur Spine J. 2017;26(5):1374–83.CrossRefGoogle Scholar
- 5.Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv [Internet]. 2014 [cited 2017 Dec 10] Available from: https://arxiv.org/abs/1409.1556
- 7.Chung SW, Han SS, Lee JW, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018; https://doi.org/10.1080/17453674.2018.1453714.
- 10.Abadi M, Agarwal A, Barham P, et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv [Internet]. 2016 [cited 2017 Dec 10] Available from: https://arxiv.org/abs/1603.04467
- 11.No authors listed. TesnorFlow-Slim image classification model library. [Internet]. [cited 2017 Dec 10] Available from: https://github.com/tensorflow/models/tree/master/research/slim
- 13.Geron A. Training deep neural network. In: Geron A, editor. Hands-on machine learning with scikit-learn & TensorFlow. Sebastopol: O’Reilly Media; 2017. p. 275–312.Google Scholar
- 14.No authors listed. tf.keras.preprocessing.image.ImageDataGenerator. [Internet]. [cited 2017 Dec 10] Available from: https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator
- 15.Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv [Internet]. 2014 [cited 2017 Dec 10] Available from: https://arxiv.org/abs/1412.6980
- 17.Baumgaertner MR, Higgins TF. Femoral neck fractures. In: Bucholz BW, Heckman JD, editors. Rockwood and Green’s fractures in adults. 5th ed. Philadelphia: Lippincott Williams & Wilkins; 2001. p. 1579–634.Google Scholar