A navigation system for shoulder arthroscopic surgery

Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images

The tracking of the knee femoral condyle cartilage during ultrasound-guided minimally invasive procedures is important to avoid damaging this structure during such interventions. In this study, we propose a new deep learning method to track, accurately and efficiently, the femoral condyle cartilage in ultrasound sequences, which were acquired under several clinical conditions, mimicking realistic surgical setups. Our solution, that we name Siam-U-Net, requires minimal user initialization and combines a deep learning segmentation method with a siamese framework for tracking the cartilage in temporal and spatio-temporal sequences of 2D ultrasound images. Through extensive performance validation given by the Dice Similarity Coefficient, we demonstrate that our algorithm is able to track the femoral condyle cartilage with an accuracy which is comparable to experienced surgeons. It is additionally shown that the proposed method outperforms state-of-the-art segmentation models and trackers in the localization of the cartilage. We claim that the proposed solution has the potential for ultrasound guidance in minimally invasive knee procedures.

3D Ultrasound for Orthopedic Interventions

Ultrasound is a real-time, non-radiation-based imaging modality with an ability to acquire two-dimensional (2D) and three-dimensional (3D) data. Due to these capabilities, research has been carried out in order to incorporate it as an intraoperative imaging modality for various orthopedic surgery procedures. However, high levels of noise, different imaging artifacts, and bone surfaces appearing blurred with several mm in thickness have prohibited the widespread use of ultrasound as a standard of care imaging modality in orthopedics. In this chapter, we provided a detailed overview of numerous applications of 3D ultrasound in the domain of orthopedic surgery. Specifically, we discuss the advantages and disadvantages of methods proposed for segmentation and enhancement of bone ultrasound data and the successful application of these methods in clinical domain. Finally, a number of challenges are identified which need to be overcome in order for ultrasound to become a preferred imaging modality in orthopedics.

A novel method of image-based navigation in fracture surgery

The treatment of three- and four-part fractures of the humeral head is still controversially discussed. Some advocate primary arthroplasty while the results of primary fixation seem to be superior if no necrosis of the humeral head develops. Today navigation is used in orthopaedic surgery mainly for interventions on the spine, the pelvis and arthroplasty. In trauma surgery it is still rarely used and some technical problems need to be overcome. We report on a case of a three part fracture of the humeral head with mini-open reduction and fixation with image-based guided headless compression screws. For the fixation each screw was placed on the first trial, total radiation time was 60 s. At 12-month follow-up assessment radiographs showed a consolidated fracture, no loosening of the screws and a good glenohumeral articulation. The patient had free function of the shoulder and no pain, the constant score was 98 and the dash score 0. There is no evidence of a necrosis of the humeral head. The literature focuses on shoulder arthroplasty. There are no reports on the use of image-based guidance in shoulder traumatology so far. In conclusion, the described technique allows an accurate fixation of the humeral head fracture as the guidance system (Surgix) ensures the "first try first hit" screw positioning. The new system was integrated in the workflow and supports the surgeon as an aiming device. The role of navigation system in enhancing minimally invasive surgery of the shoulder should be further explored.