Artificial intelligence for analyzing orthopedic trauma radiographs

Abstract

Background and purpose — Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs.Methods — We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd’s Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network’s performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network.Results — All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen’s kappa under these conditions was 0.76.Interpretation — This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics.

Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age

“…In several reports, deep learning with convolutional neural networks as AI has been used in medicine . The accuracies of this method with deep learning have been published and were 0.997 for histopathological diagnosis of breast cancer, 0.90‐0.83 for the early diagnosis of Alzheimer's disease, 0.83 for urological dysfunctions, 0.72 and 0.50 for colposcopy, 0.83 for the diagnostic imaging of orthopedic trauma, and 0.98 for the morphological quality of blastocysts and evaluation by embryologist . In one report, embryos with fair‐quality images that were classified as poor and good quality were scored as 0.509 and 0.614, respectively, for the likelihood of achieving a positive live birth .…”

Computer vs human: Deep learning versus perceptual training for the detection of neck of femur fractures

“…Artificial intelligence has gained great momentum in recent years with studies showing its ability to perform complex interpretation at the level of healthcare specialists . These studies have fuelled hope and concern that AI systems will replace radiologists in the near future.…”

“…In computer science, DCNNs have become state of the art for interpreting images and are the model of choice for the annual ImageNet Large Scale Visual Recognition Competition . AI has already shown potential across healthcare with examples including dermatology for skin lesion identification, ophthalmology for the detection of diabetic retinopathy, orthopaedics for hand and ankle fractures and in radiology for interpreting chest X‐rays for tuberculosis and interpreting CT and MRI for detecting strokes to name a few.…”

Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types

“…In medicine, several studies have used AI for deep learning with convolutional neural networks (48,49). The accuracy values of AI with deep learning have been published and include 0.997 for the histopathological diagnosis of breast cancer (50), 0.980 for the morphological quality of blastocysts and evaluation by an embryologist (51), 0.640-0.880 for predicting live birth from a blastocyst image of patients by age (4,52), 0.650 for predicting live birth without aneuploidy from a blastocyst image (53), 0.823 (3), 0.720 (54) and 0.500 (55) for colposcopy, 0.830 to 0.900 for the early diagnosis of Alzheimer's disease (56), 0.830 for urological dysfunctions (57) and 0.830 for the diagnostic imaging of orthopedic trauma (58). A number of studies have reported a limitation of conventional colposcopy.…”