Metacarpal Bones Localization in X-ray Imagery Using Particle Filter Segmentation
This work addresses a domain-specific medical imaging task for bone localization, presenting an incremental improvement by adapting existing particle filter segmentation techniques to metacarpal bones.
The paper tackled the problem of localizing metacarpal bones in X-ray images by developing a method that combines a global shape model and local appearance features, achieving a unique labeling of bone boundaries and background points in test data.
Statistical methods such as sequential Monte Carlo Methods were proposed for detection, segmentation and tracking of objects in digital images. A similar approach, called Shape Particle Filters was introduced for the segmentation of vertebra, lungs and hearts [1]. In this contribution, a global shape and a local appearance model are derived from specific object annotated X-ray images of the metacarpal bones. In the test data a unique labeling of the bone boundary and the background points and a manual annotation is given. Using a set of local features (Haar-like) in the neighborhood of each pixel a probabilistic pixel classifier is built using the random forest algorithm. To fit the shape model to a new image, a label probability map is extracted and then the optimal shape is obtained by maximizing the probability of each landmark with the Differential Evolution algorithm.