A bone age assessment system for real-world X-ray images based on convolutional neural networks.

It is of vast significance to assess the bone age of hand radiographs automatically in pediatric radiology and legal medicine. In the literature, many papers focus on improving the assessment accuracy but neglecting the existence of poor-quality X-ray images. However, in real medical scenarios, the existence of poor-quality X-ray images is unavoidable. To tackle this problem, we propose a bone age assessment system for real-world X-ray images. Specifically, we first establish a regression model ‘BoNet+’ based on densely connected convolutional networks. Then, to handle poor-quality X-ray images, we introduce three model architectures that are different in the way of improving image quality. Experiment results show that the proposed models can estimate the bone age of poor-quality images accurately. We also tentatively put forward that if the expressivity of CNN model is enough high, multiple tasks can be handled together just by a single model.