Abstract
This paper presents an automatic segmentation and monocular marker-less tracking method of the gallbladder in minimally invasive laparoscopic cholecystectomy intervention that can be used for the construction of an adaptive calibrationfree medical augmented reality system. In particular, the proposed method consists of three steps, namely, a segmentation of 2D laparoscopic images using a combination of photometric population-based statistical approach and edge detection techniques, a PSO-based detection of the targeted anatomical structure (the gallbladder) and, finally, the 3D model waveletbased multi-resolution analysis and adaptive 2D/3D registration. The proposed population-based statistical segmentation approach of 2D laparoscopic images differs from classical approaches (histogram thresholding), in that we consider anatomical structures and surgical instruments in terms of distributions of RGB color triples. This allows an efficient handling, superior robustness and to readily integrate current intervention information. The result of this step consists in a set of point clouds with a loosely gradient information that can cover various anatomical structures. In order to enhance both sensitivity and specificity, the detection of the targeted structure (the gallbladder) is based on a modified PSO (particles swarm optimization) scheme which maximizes both internal features density and the divergence with neighboring structures such as, the liver. Finally, a multi-particles based representation of the targeted structure is constructed, thanks to a proposed wavelet-based multi-resolution analysis of the 3D model of the targeted structure which is registered adaptively with the 2D particles generated during the previous step. Results are shown on both synthetic and real data. © 2018, (IJACSA) International Journal of Advanced Computer Science and Applications.