Genetic Adaptation of Level Sets Parameters for Medical Imaging Segmentation

Abstract

This chapter presents a method based on level sets to segment organs using computer tomography (CT) medical images. Initially, the organ boundary is manually set in one slice as an initial solution, and then the method automatically segments the organ in all other slices, sequentially. In each step of iteration it fits a Gaussian curve to the organ’s slice histogram to model the speed image in which the level sets propagate. The parameters of our method are estimated using genetic algorithms (GA) and a database of reference segmentations. The method was tested to segment the liver using 20 different exams and five different measures of performance, and the results obtained confirm the potential of the method. The cases in which the method presented a poor performance are also discussed in order to instigate further research.

A survey on image segmentation using metaheuristic-based deformable models: state of the art and critical analysis

“…Moreover, many deformable models are based on partial differential equations which can be solved by traditional numerical methods. However, metaheuristics have demonstrated to be very useful for learning the parameters of the model [196][197][198][199][200], to refine the results obtained by the geometric approach [201], to initialize the contour and/or extract the prior information which is to be used by the level set method [195,198,202] or to directly guide the optimization process avoiding local minima [190][191][192][193]203]. An important advantage of using metaheuristics is that they can optimize the level set function without the need to compute derivatives, thereby permitting a straightforward introduction of new curve-evolution terms [198].…”

The introduction of navigation in liver surgery in Brazil

“…In some centers, hepatic navigation has the potential to provide: 1) more radicality, precisely defining the required limits or by aiding in the location of lesions that have become sub-millimetrical or disappeared from imaging after chemotherapy; 2) realtime monitoring of the needle location and the ablation area, without interference from the steam, as in intraoperative ultrasonography; 3) greater security with fewer accidents and less bleeding; 4) gain in time in laparoscopic operations; 5) reducing related costs by enabling more judicious use of automatic vascular staplers; and 6) acceleration of the learning curve in laparoscopic liver surgery. Several obstacles exist for surgical navigation to be sufficiently precise and reliable, especially the need for the navigation monitor to follow the deformity of the liver caused by real time mobilization and eliminating errors resulting from liver movement during ventilation 9,10 . These initial procedures show that it is possible to use surgical navigation equipment in liver operations.…”

Automatic 3D CT liver segmentation based on fast global minimization of probabilistic active contour

“…In recent years, many automatic liver segmentation methods have been developed, mainly including threshold methods, 3 region‐growing methods, 4 graph cuts‐based methods, 5–9 shape model‐based methods, 10–14 machine learning‐based methods, 15–20 and active contour model‐based methods 21,22 …”