Ultrasound-based Navigation of Scaphoid-fixation
Fractures of the scaphoid, which make up 2% of all bone fractures, may be treated with minimally-invasive surgery. In order to join the bone fragments, an osteosynthesis screw is inserted into the bone. Conventionally, the procedure is performed under fluoroscopy. This exhibits both, the patient and the surgeon to ionizing radiation. Ultrasound offers a cheap and widely available alternative imaging technique.
For a navigated screw placement, the relative position of osteosynthesis screw and scaphoid bone needs to be known. The chair of medical engineering develops a pipeline that computes this transformation fully automatically and in near real time. Starting from a volumetric ultrasound image, a cascade of deep neural networks is applied to segment the scaphoid bone in the image and register it to a pre-operatively obtained three-dimensional model. Given the registration, the current position of the screw can be compared to the planed position.
- P. Brößner, B. Hohlmann, K. Welle & K. Radermacher: Ultrasound-Based Registration for the Computer-Assisted Navigated Percutaneous Scaphoid Fixation. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2023, 70(9), pp. 1064-1072 [DOI: 10.1109/TUFFC.2023.3291387]
- P. Broessner, B. Hohlmann & K. Radermacher: Ultrasound-based Navigation of Scaphoid Fracture Surgery. In: C. Palm, T.M. Deserno, H. Handels, A. Maier, K. Maier-Hein & T. Tolxdorff (ed.): Bildverarbeitung für die Medizin 2021, Springer, 2021, pp. 28-33 [DOI: 10.1007/978-3-658-33198-6_8]
- P. Brößner, B. Hohlmann, K. Welle & K. Radermacher: Validation of Automated Ultrasound-based Registration for Navigated Scaphoid Fixation: Evaluation of registration performance regarding simulated screw placement. Current Directions in Biomedical Engineering, 7(1), 2021, pp. 116-120 [DOI: 10.1515/cdbme-2021-1025]
- B. Hohlmann, P. Brößner, K. Welle & K. Radermacher: Segmentation of the Scaphoid Bone in Ultrasound Images: A comparison of two machine learning architectures for in-vivo segmentation. Current Directions in Biomedical Engineering, 7(1), 2021, pp. 76-80 [DOI: 10.1515/cdbme-2021-1017]