The paper takes a practical approach to estimating the bone age of children and young adults based on hand radiography, by constructing an end-to-end pipeline that involves bone segmentation, deep regression algorithms and model explainability. Unlike previous approaches reported in the literature for bone age regression, we employ a methodology coined as integral regression that, in conjunction with the popular pretrained ResNeSt-50 model, exploiting also features extracted in the segmentation step, establishes new State-Of-The-Art results on the RSNA data set. Our experiments demonstrate clear advantages in favour of the integral regression layer over the much more common linear regression layer in the deep learning framework, while the explainability module showcases the robustness of our approach.
This article is authored also by Synbrain data scientists and collaborators. READ THE FULL ARTICLE