Deep Morphing: Detecting bone structures in fluoroscopic X-ray images with prior knowledge
This addresses a domain-specific challenge in medical image processing for healthcare applications, but it is incremental as it builds on existing deep learning and prior knowledge methods.
The authors tackled the problem of localizing objects in low-quality, low-contrast fluoroscopic X-ray images with limited training data by incorporating prior knowledge like geometrical or statistical models, achieving a solution through computationally efficient two-stage deep learning approaches.
We propose approaches based on deep learning to localize objects in images when only a small training dataset is available and the images have low quality. That applies to many problems in medical image processing, and in particular to the analysis of fluoroscopic (low-dose) X-ray images, where the images have low contrast. We solve the problem by incorporating high-level information about the objects, which could be a simple geometrical model, like a circular outline, or a more complex statistical model. A simple geometrical representation can sufficiently describe some objects and only requires minimal labeling. Statistical shape models can be used to represent more complex objects. We propose computationally efficient two-stage approaches, which we call deep morphing, for both representations by fitting the representation to the output of a deep segmentation network.