Félix Paulano

3D segmentation and labeling of fractured bone from CT images

The segmentation of fractured bone from computed tomographies (CT images) is an important process in medical visualization and simulation, because it enables such applications to use data of a specific patient. On the other hand, the labeling of fractured bone usually requires the participation of an expert. Moreover, close fragment can be joined after the segmentation because of their proximity and the resolution of the CT image. Classical methods perform well in the segmentation of healthy bone, but they are not able to identify bone fragments separately. In this paper, we propose a method to segment and label bone fragments from CT images. Labeling involves the identification of bone fragments separately. The method is based on 2D region growing and requires minimal user interaction. In addition, the presented method is able to separate wrongly joined fragments during the segmentation process.

Identification of fractured bone tissue from CT images

The identification of fractured bone from computed tomographic (CT) images is a helpful task in medical visualisation and simulation. In many cases, specialists need to manually revise 2D and 3D CT images and detect bone fragments in order to check a fracture. The automation of this process would allow them to save time. In visualisation, it allows the reduction of image noise and the removal of undesirable parts. In simulation, the utilisation of models reconstructed from CT images of patients allows customisation of the simulation, because the result of the segmentation can be used to perform a reconstruction that provides a 3D model of the patient anatomy. In this paper, the main issues to be considered in order to identify both healthy and fractured bones are described. The identification of fractured bone requires not only to segment bone tissue but also to label bone fragments. Moreover, some fragments can appear together after the segmentation process, hence additional processing can be required. Currently proposed approaches for identifying healthy and fractured bones are analysed and classified. Finally, the aspects to be improved in the described methods are outlined and the work to do is identified.

Fractured Bone Identification from CT Images, Fragment Separation and Fracture Zone Detection

The automation of the detection of fractured bone tissue would allow to save time in medicine. In many cases, specialists need to manually revise 2D and 3D CT images and detect bone fragments and fracture regions in order to check a fracture. The identification of bone fragments from CT images allows to remove image noise and undesirable parts and thus improves image visualization. In addition, the utilization of models reconstructed from CT images of patients allows to customize the simulation, since the result of the identification can be used to perform a reconstruction that provides a 3D model of the patient anatomy. The detection of fracture zones increases the information provided to specialists and enables the simulation of some medical procedures, such as fracture reduction. In this paper, the main issues to be considered in order to identify bone tissue and the additional problems that arise if the bone is fractured are described. The identification of fractured bone includes not only bone tissue segmentation, but also bone fragments labelling and fracture region detection. Moreover, some fragments can appear together after the segmentation process, hence additional processing can be required to separate them. After that, currently proposed approaches to identify fractured bone are analysed and classified. The most recently proposed methods to segment healthy bone are also reviewed in order to justify that the techniques used for this type of bone are not always suitable for fractured bone. Finally, the aspects to be improved in the described methods are outlined and future work is identified.

Simulation of bone fractures via geometric techniques: an overview

ABSTRACT The simulation of realistic fracture cases on geometric models representing bone structures is almost an unexplored field of research. These fractured models have several applications in computer-assisted methods that support specialist in fracture reduction interventions. For instance, the generation of specific fracture patterns can provide uncommon cases for training simulators or can be used to improve machine-learning applications. This paper focuses on the issues to be considered in the generation of fractures on geometric models that represent bone structures. The main recent contributions for fracturing geometric models are examined and the challenges in terms of the application of real bone fracture patterns on geometric models are presented. Moreover, different alternatives for the evaluation of the results obtained by the geometric fracture generation algorithms when applied to bone structures are discussed. Finally, the potential applications of the virtual generation of specific bone fractures are described.