Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume
This work addresses the scarcity of intra-operative US data for surgeons performing spinal surgery, though it is incremental as it builds on existing simulation and segmentation methods.
The paper tackles the problem of unavailable clinical ultrasound (US) data for bone segmentation and registration in spinal surgery by proposing a framework that synthesizes realistic US images from diagnostic CT volumes, enabling training of a lightweight vision transformer model. The results show a Chamfer distance of 0.599mm for segmentation and Dice accuracy of 0.93 with registration accuracy of 0.13~3.37mm.
This paper aims to tackle the issues on unavailable or insufficient clinical US data and meaningful annotation to enable bone segmentation and registration for US-guided spinal surgery. While the US is not a standard paradigm for spinal surgery, the scarcity of intra-operative clinical US data is an insurmountable bottleneck in training a neural network. Moreover, due to the characteristics of US imaging, it is difficult to clearly annotate bone surfaces which causes the trained neural network missing its attention to the details. Hence, we propose an In silico bone US simulation framework that synthesizes realistic US images from diagnostic CT volume. Afterward, using these simulated bone US we train a lightweight vision transformer model that can achieve accurate and on-the-fly bone segmentation for spinal sonography. In the validation experiments, the realistic US simulation was conducted by deriving from diagnostic spinal CT volume to facilitate a radiation-free US-guided pedicle screw placement procedure. When it is employed for training bone segmentation task, the Chamfer distance achieves 0.599mm; when it is applied for CT-US registration, the associated bone segmentation accuracy achieves 0.93 in Dice, and the registration accuracy based on the segmented point cloud is 0.13~3.37mm in a complication-free manner. While bone US images exhibit strong echoes at the medium interface, it may enable the model indistinguishable between thin interfaces and bone surfaces by simply relying on small neighborhood information. To overcome these shortcomings, we propose to utilize a Long-range Contrast Learning Module to fully explore the Long-range Contrast between the candidates and their surrounding pixels.