Development of Mesh-Defect Removal Algorithm to Enhance the Fitting of 3D-Printed Parts for Comminuted Bone Fractures

Automated 2D and 3D finite element overclosure adjustment and mesh morphing using generalized regression neural networks

Computer representations of three-dimensional (3D) geometries are crucial for simulating systems and processes in engineering and science. In medicine, and more specifically, biomechanics and orthopaedics, obtaining and using 3D geometries is critical to many workflows. However, while many tools exist to obtain 3D geometries of organic structures, little has been done to make them usable for their intended medical purposes. Furthermore, many of the proposed tools are proprietary, limiting their use. This work introduces two novel algorithms based on Generalized Regression Neural Networks (GRNN) and 4 processes to perform mesh morphing and overclosure adjustment. These algorithms were implemented, and test cases were used to validate them against existing algorithms to demonstrate improved performance. The resulting algorithms demonstrate improvements to existing techniques based on Radial Basis Function (RBF) networks by converting to GRNN-based implementations. Implementations in MATLAB of these algorithms and the source code are publicly available at the following locations: https://github.com/thor-andreassen/femors; https://simtk.org/projects/femors-rbf; https://www.mathworks.com/matlabcentral/fileexchange/120353-finite-element-morphing-overclosure-reduction-and-slicing.

An automatic reduction method of 3D bone fragments based on a novel section contour point descriptor

Comminuted fractures are orthopedic traumas with greater surgical difficulty. In clinical treatment, a great challenge is precise reduction of multiple broken bone fragments; Another great challenge is personalized and precise internal fixation after reduction. For these two issues, we designed an automated method framework for precise reduction and internal fixation of comminuted fractures. First, the Gaussian mixture model (GMM) is used to distinguish section points and noise points in a broken bone model; Second, ellipse fitting is carried out to achieve section points matching and a descriptor is proposed to describe the section features; Then, the Convolution Auto-Encoder (CAE) and genetic algorithm are used to extract feature vectors; Finally, after broken bone models registration, internal fixed plate can be reconstructed. Three verification experiments for comminuted bone fracture show this method has high accuracy and good efficiency. It can provide support for minimally invasive treatment for comminuted fractures.

Imaging, post-processing and navigation: Surgical applications in pelvic fracture treatment

Technical advancements of the past decade have led to massive improvements regarding imaging and visualization in trauma care. Digital imaging technology has fundamentally changed most processes in fracture management. However, the digital revolution in trauma surgery has just begun. Optical tracking navigation is currently the gold standard for positioning of implants for advanced applications in trauma surgery. Digital technology may enable the surgeon to achieve the same level of safety even in non-navigated placement of screws: We developed a new planning tool to transcript a preoperative into a semi-transparent "fluoroscopic like" image that can be identified intraoperatively and used as a map for the safe placement of sacro-iliac screws based on the "vestibule concept". In the future, development of artificial intelligence algorithms may provide features like automated segmentation of bone-fragments and other applications for a systematic fracture analysis to improve the standard of care in trauma surgery. Digital transformation has massive impact on diagnostics and surgical management of pelvic fractures. Improved visualization technology provides a better understanding of the surgical anatomy of the pelvis and may enable the surgeon to achieve greatest safety in percutaneous placement of screws even without using optical tracking navigation tools. The "para-axial fusion technique" is a useful tool to plan fluoroscopic views based on a 3D dataset prior to the surgery.

A topic analysis method based on a three-dimensional strategic diagram

With the tremendous growth of scientific literature in recent years, methods of detecting and analysing research topics have become more and more important. This study proposes a topic analysis method combining latent Dirichlet allocation (LDA) and a three-dimensional strategic diagram. This study constructs the three-dimensional strategic diagram by three dimensions of centrality, density and novelty, and we classify topics into seven categories according to their strategic positions. Using this topic analysis method, the paper analyses 62,340 publications in the field of medical informatics between 1991 and 2018. Results show that the research scope of medical informatics has become increasingly interdisciplinary. Data analytical methods and technologies are sub-domains with persistent popularity. New health technologies, drug safety, algorithm optimisation and standardisation of medical information are emerging research topics. We hope the findings could help researchers identify potential research topics and facilitate in-depth analysis of the current state of various fields.