Jan Bredow1, Birte Wenk1, Ralf Westphal2, Friedrich Wahl2, Stefan Budde3, Peer Eysel1, Johannes Oppermann1. 1. Department of Orthopaedic and Trauma Surgery, University of Cologne, Hannover, Germany. 2. Institute for Robotics and Process Control, Technical University of Braunschweig, Braunschweig, Germany. 3. Department of Orthopaedic Surgery, Annastift Hospital, Hannover Medical School, Hannover, Germany.
Abstract
BACKGROUND: Revision joint replacements are challenging surgical tasks. Knowing the exact type of primary prosthesis is essential to avoid long preoperative organisation, long operation times, and especially loss of bone and soft-tissue during operation. In daily routine there is often no information about the primary prosthesis. OBJECTIVE: We are developing methods for identifying implanted prostheses from x-ray images by means of matching template images generated from prosthesis CAD data. METHODS: The application is separated into three major components: The "Template Image Generation" adds 3d models of endoprostheses to a database. The "X-ray Image Segmentation" extracts endoprostheses from provided sets of x-ray images. The "Template Matching" finds the best matching prosthesis types in the data base. At the current stage, one prosthesis model (Corin, Knee ProthesisUniglide) was used for evaluating these algorithms. RESULTS: Very accurate identifications with accuracies of about 90% for lateral and over 70% for frontal images could be achieved. CONCLUSIONS: The current results of this feasibility study are very promising. A reliable and fast prosthesis identification process seems realistic to support the surgeon when planning and performing revision arthroplasty. Further improvements of segmentation accuracies and extending the prosthesis data base are intended next steps towards this goal.
BACKGROUND: Revision joint replacements are challenging surgical tasks. Knowing the exact type of primary prosthesis is essential to avoid long preoperative organisation, long operation times, and especially loss of bone and soft-tissue during operation. In daily routine there is often no information about the primary prosthesis. OBJECTIVE: We are developing methods for identifying implanted prostheses from x-ray images by means of matching template images generated from prosthesis CAD data. METHODS: The application is separated into three major components: The "Template Image Generation" adds 3d models of endoprostheses to a database. The "X-ray Image Segmentation" extracts endoprostheses from provided sets of x-ray images. The "Template Matching" finds the best matching prosthesis types in the data base. At the current stage, one prosthesis model (Corin, Knee ProthesisUniglide) was used for evaluating these algorithms. RESULTS: Very accurate identifications with accuracies of about 90% for lateral and over 70% for frontal images could be achieved. CONCLUSIONS: The current results of this feasibility study are very promising. A reliable and fast prosthesis identification process seems realistic to support the surgeon when planning and performing revision arthroplasty. Further improvements of segmentation accuracies and extending the prosthesis data base are intended next steps towards this goal.