Background: Medical image processing tasks represented by multi-object segmentation are of great significance for surgical planning, robot-assisted surgery, and surgical safety. However, the exceptionally low contrast among tissues and limited available annotated data makes developing an automatic segmentation algorithm for pelvic CT challenging. Methods: A bi-direction constrained dual-task consistency model named PICT is proposed to improve segmentation quality by leveraging free unlabeled data. First, to learn more unmarked data features, it encourages the model prediction of the interpolated image to be consistent with the interpolation of the model prediction at the pixel, model, and data levels. Moreover, to constrain the error prediction of interpolation interference, PICT designs an auxiliary pseudo-supervision task that focuses on the underlying information of non-interpolation data. Finally, an effective loss algorithm for both consistency tasks is designed to ensure the complementary manner and produce more reliable predictions. Results: Quantitative experiments show that the proposed PICT achieves 87.18%, 96.42%, and 79.41% mean DSC score on ACDC, CTPelvic1k, and the individual Multi-tissue Pelvis dataset with gains of around 0.8%, 0.5%, and 1% compared to the state-of-the-art semi-supervised method. Compared to the baseline supervised method, the PICT brings over 3–9% improvements. Conclusions: The developed PICT model can effectively leverage unlabeled data to improve segmentation quality of low contrast medical images. The segmentation result could improve the precision of surgical path planning and provide input for robot-assisted surgery.

Background: Robot-assisted pelvic fracture closed reduction (RPFCR) positively contributes to patient treatment. However, the current path planning suffers from incomplete obstacle avoidance and long paths. Method:A collision detection method is proposed for applications in the pelvic environment to improve the safety of RPFCR surgery. Meanwhile, a defined orientation planning strategy (OPS) and linear sampling search (LSS) are coupled into the A* algorithm to optimise the reduction path. Subsequently, pelvic in vitro experimental platform is built to verify the augmented A*algorithm's feasibility. Results:The augmented A* algorithm planned the shortest path for the same fracture model, and the paths planned by the A* algorithm and experience-based increased by 56.12% and 89.02%, respectively. Conclusions:The augmented A* algorithm effectively improves surgical safety and shortens the path length, which can be adopted as an effective model for developing RPFCR path planning. K E Y W O R D SA* algorithm, collision detection, path planning, pelvic closed reduction | INTRODUCTIONUnstable pelvic fractures are the most severe injury in the body, accounting for 2%-8% of all fractures and a mortality rate of 6%-31%. 1,2 A safe and precise anatomical reduction is the cornerstone of treating pelvic fractures. 3 As a modern technology with high precision, reliability, and intelligence, robotics is widely used in medical, industrial, and aerospace fields. Therefore, the reduction movements during pelvic fracture closed reduction surgery can be performed by controlling the robot. [4][5][6] With the rapid development and application of medical robotics, 7 the path planning for robot-assisted pelvic fracture closed reduction (RPFCR) has attracted broad researchers. The RPFCR path planning can be divided into two steps: collision detection and path search.The pelvic environment is complex, with many soft and hard tissues. 8 Thus, it is necessary to detect collisions between bones or between bones and soft tissues in preoperative path planning. Meanwhile, a rational and effective path search method is required to cut the surgical intervention time.The main contribution of this paper is to propose a path-planning method for RPFCR, which improves the surgery's safety and the universality of the path planning and reduces the length of the reduction path. Firstly, the fracture model is discretised into computable point cloud data. Based on the point set of the sacrum, the space where the sacrum is located is divided into several small subspaces using the Octree data structure. Then, the point set of the dislocated ilium is traversed to conduct overlap tests with the sacral subspace to detect the collision between objects. Secondly, this paper defined an orientation planning strategy (OPS), which means changing the ilium's orientation with a small step length to avoid high reduction resistance caused by a one-time adjustment. And a linear sampling search (LSS) method is proposed to shorten the reduction path further. Finally, the

No abstract