A Data-Driven Approach for Assembling Intertrochanteric Fractures by Axis-Position Alignment

In clinics, the reduction of femoral intertrochanteric fractures should meet the medical demands of both axis alignment and position alignment. State-of-the-art approaches are designed for merely position alignment, not allowing for axis alignment. The axis-position alignment can be formulated as a least square optimization problem with the inequality constraints. The main challenges include how to solve this constrained optimization problem and effectively extract the semantic of the randomly fractured bone pieces. To address these problems, a semi-automatic data-driven method is introduced. First, the medical semantic parameters are computed, at the beginning of when the 3D input pieces' anatomical areas are labeled by using the deep neural network. A statistical shape model is leveraged to generate the synthetic training data so as to learn the anatomical landmarks of the pieces, greatly reducing the labeling costs for training. The final reduction position of the pieces is obtained through iterative axis alignment and position alignment. Our method is evaluated by three baselines, i.e., the manual assembly of the orthopaedic specialists and two typical bone assembling methods. The presented method solves an optimization problem for assembling intertrochanteric fracture by axis-position alignment. All cases can be successfully assembled with the developed algorithm which is proved to be capable of reaching the clinical demand.