Deep Morphing: Detecting bone structures in fluoroscopic X-ray images with prior knowledge

TL;DR

This paper introduces deep morphing methods that leverage high-level geometric or statistical models to improve object localization in low-quality, limited-data fluoroscopic X-ray images using deep learning.

Contribution

It presents novel two-stage deep morphing approaches that incorporate prior shape knowledge for enhanced localization in challenging medical imaging scenarios.

Findings

Effective localization with minimal training data

Utilizes simple geometric and complex statistical shape models

Computationally efficient two-stage approach

Abstract

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.