Medical knowledge-guided deep curriculum learning for elbow fracture diagnosis from x-ray images

Abstract

Elbow fractures are one of the most common fracture types. Diagnoses on elbow fractures often need the help of radiographic imaging to be read and analyzed by a specialized radiologist with years of training. Thanks to the recent advances of deep learning, a model that can classify and detect different types of bone fractures needs only hours of training and has shown promising results. However, most existing deep learning models are purely data-driven, lacking incorporation of known domain knowledge from human experts. In this work, we propose a novel deep learning method to diagnose elbow fracture from elbow X-ray images by integrating domain-specific medical knowledge into a curriculum learning framework. In our method, the training data are permutated by sampling without replacement at the beginning of each training epoch. The sampling probability of each training sample is guided by a scoring criterion constructed based on clinically known knowledge from human experts, where the scoring indicates the diagnosis difficultness of different elbow fracture subtypes. We also propose an algorithm that updates the sampling probabilities at each epoch, which is applicable to other sampling-based curriculum learning frameworks. We design an experiment with 1865 elbow X-ray images for a fracture/normal binary classification task and compare our proposed method to a baseline method and a previous method using multiple metrics. Our results show that the proposed method achieves the highest classification performance. Also, our proposed probability update algorithm boosts the performance of the previous method.

A Deep Learning Framework for Timely Bone Fracture Detection and Prevention

“…Their approach correctly diagnoses healthy and damaged bone with a 90.14% accuracy. On a small dataset, Yahalomi et al [12] and Abbas et al [13] used a pretrained Faster R-CNN model and achieved accuracies of 96% and 97%, respectively. Luo et al [14] developed a decision tree-based technique for identifying broken bones, with an accuracy of 86.57%.…”

A Bone Fracture Detection using AI-Based Techniques

“…The authors of [44,3] used pre-trained R-CNN was applied to the small dataset and achieved 96% and 97% accuracy, respectively. The authors of [29] have applied their experiences and designed a decision tree for the identification of fractures. Their method achieved a classification accuracy of, of 86.57%.…”

Hybrid SFNet Model for Bone Fracture Detection and Classification Using ML/DL

“…Yahalomi et al [ 22 ] and Abbas et al [ 23 ] applied pre-trained faster R-CNN on a small dataset and achieved an accuracy of 96% and 97%, respectively. Luo et al [ 24 ] applied their expert knowledge and designed a decision tree for fractured bone diagnosis. Their method achieved an accuracy of 86.57%.…”