Reconstruction of freehand 3D ultrasound based on kernel regression

Xiankang Chen, Tiexiang Wen, Xingmin Li, Wenjian Qin, Donglai Lan, Weizhou Pan, Jia Gu

Freehand three-dimensional (3D) ultrasound has the advantages of flexibility for allowing cliniciansto manipulate the ultrasound probe over the examined body surface with less constraint in comparisonwith other scanning protocols. Thus it is widely used in clinical diagnose and image-guided surgery.However, as the data scanning of freehand¿style is subjective, the collected B-scan images are usuallyirregular and highly sparse. One of the key procedures in freehand ultrasound imaging system is thevolume reconstruction, which plays an important role in improving the reconstructed image quality.System and MethodsA novel freehand 3D ultrasound volume reconstruction method based on kernel regression model isproposed in this paper. Our method consists of two steps: bin-filling and regression. Firstly, thebin-filling step is used to map each pixel in the sampled B-scan images to its corresponding voxelin the reconstructed volume data. Secondly, the regression step is used to make the nonparametricestimation for the whole volume data from the previous sampled sparse data. The kernel penalizesdistance away from the current approximation center within a local neighborhood.Experiments and resultsTo evaluate the quality and performance of our proposed kernel regression algorithm for freehand 3Dultrasound reconstruction, a phantom and an in-vivo liver organ of human subject are scanned with ourfreehand 3D ultrasound imaging system. Root mean square error (RMSE) is used for the quantitativeevaluation. Both of the qualitative and quantitative experimental results demonstrate that our methodcan reconstruct image with less artifacts and higher quality.