English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Elbow fractures are one of the most common fracture types. Diagnoses on elbowfractures often need the help of radiographic imaging to be read and analyzedby a specialized radiologist with years of training. Thanks to the recentadvances of deep learning, a model that can classify and detect different typesof bone fractures needs only hours of training and has shown promising results.However, most existing deep learning models are purely data-driven, lackingincorporation of known domain knowledge from human experts. In this work, wepropose a novel deep learning method to diagnose elbow fracture from elbowX-ray images by integrating domain-specific medical knowledge into a curriculumlearning framework. In our method, the training data are permutated by samplingwithout replacement at the beginning of each training epoch. The samplingprobability of each training sample is guided by a scoring criterionconstructed based on clinically known knowledge from human experts, where thescoring indicates the diagnosis difficultness of different elbow fracturesubtypes. We also propose an algorithm that updates the sampling probabilitiesat each epoch, which is applicable to other sampling-based curriculum learningframeworks. We design an experiment with 1865 elbow X-ray images for afracture/normal binary classification task and compare our proposed method to abaseline method and a previous method using multiple metrics. Our results showthat the proposed method achieves the highest classification performance. Also,our proposed probability update algorithm boosts the performance of theprevious method.

Medical Knowledge-Guided Deep Curriculum Learning for Elbow Fracture Diagnosis from X-Ray Images