Geometric Feature Extraction for Precise Measurements in Intramedullary Nail images

Angelos Skembris, Elias Koukoutsis, Constantin Papaodysseus, Eleftherios Kayafas
Abstract:
Closed Intramedullary Nailing (CIN) is a surgical procedure which requires that the surgeon accurately locates the optimal drilling position for inserting locking screws to stabilize and lock into position a nail inserted into the patient's bone. This procedure is difficult and is usually accomplished via X-ray fluoroscopic imaging, which results in large radiation exposure for both the patient and the surgical team. In this paper we present a method for making precise measurements of the nail geometric characteristics depicted in Xray images in order to assist the surgeon during the determination of the nail body's position, assessment of any possible deformation during the insertion process, and the position and orientation of the nail holes' axes. This is achieved by firstly segmenting nail image to extract the area of the nail. Then, the nail body's shape is measured with the use of a deformable polygon that approximates the shape of the nail. The projections of the nail holes are then approximated with piecewise ellipses with the use of the Nelder-Mead minimization algorithm. Preliminary results show that using this method, we can achieve precise measurements of the nail body and hole projections in the X-ray image. These measurements can be used to construct a 3D model of the nail relative to the bone, which can in turn be used for the determination of the optimal drilling angle.
Keywords:
biomedical measurements, Pattern recognition, Intramedullary Nailing, Deformable shapes recognition
Download:
IMEKO-TC4-2013-045.pdf
DOI:
-
Event details
IMEKO TC:
TC4
Event name:
TC4 Symposium 2013
Title:
19th IMEKO TC4 Symposium Measurements of Electrical Quantities (together with 17th TC4 IWADC Workshop on ADC and DAC Modelling and Testing)
Place:
Barcelona, SPAIN
Time:
18 July 2013 - 19 July 2013