Automatic colonic polyp detection using multiobjective evolutionary techniques

Abstract

Colonic polyps appear like elliptical protrusions on the inner wall of the colon. Curvature based features for colonic polyp detection have proved to be successful in several computer-aided diagnostic CT colonography (CTC) systems. Some simple thresholds are set for those features for creating initial polyp candidates, sophisticated classification scheme are then applied on these polyp candidates to reduce false positives. There are two objective functions, the number of missed polyps and false positive rate, that need to be minimized when setting those thresholds. These two objectives conflict and it is usually difficult to optimize them both by a gradient search. In this paper, we utilized a multiobjective evolutionary method, the Strength Pareto Evolutionary Algorithm (SPEA2), 1 to optimize those thresholds. SPEA2 incorporates the concept of Pareto dominance and applies genetic techniques to evolve individual solutions to the Pareto front. The SPEA2 algorithm was applied to colon CT images from 27 patients each having a prone and a supine scan. There are 40 colonoscopically confirmed polyps resulting in 72 positive detections in CTC reading. The results obtained by SPEA2 were compared with those obtained by our old system, where an appropriate value was set for each of those thresholds by a histogram examination method. If we keep the sensitivity the same as that of our old system, the SPEA2 algorithm reduced false positive rate by 76.4% from average false positive 55.6 to 13.3 per data set. If the false positive rate is kept the same for both systems, SPEA2 increased the sensitivity by 13.1% from 53 to 61 among 72 ground truth detections.

Wavelet method for CT colonography computer-aided polyp detectiona)

“…For each vertex on the colon surface, geometric and curvature features are calculated and filtered. Candidate polyps are formed on the surface from connected clusters of filtered vertices (12). The filtering and clustering are optimized by a multiobjective evolutional technique (12, 13).…”

“…Candidate polyps are formed on the surface from connected clusters of filtered vertices (12). The filtering and clustering are optimized by a multiobjective evolutional technique (12, 13). A knowledge-based polyp segmentation is performed on the 3D volume data, starting from the identified surface region (14).…”

Maximum Coverage at Minimum Cost for Multi-Domain IP/MPLS Networks

“…The problem was formulated as a multi-objective integer program, and solved by means of a new evolutionary algorithm named Maximum Coverage at minimum Cost (MC 2 ) that we proposed and tested in this work. We have shown that MC 2 is able to find much better solutions than the powerful and widely used EMA SPEA2 [3]- [5]. The key is the way in which we exploit the knowledge about the concavity of common pricing functions of ISPs.…”

“…• We show that our EMA is capable of finding much better solutions than another powerful and highly utilized EMA, namely, the Strength Pareto Evolutionary Algorithm version 2 (SPEA2) [3]- [5], while complying with the network capacity and budget constraints.…”

“…The strengths of SPEA2 lie in its elitism preservation, its fitness assignment, its density preservation technique, and as MC 2 , it uses an external archive where non-dominated solutions are stored. SPEA -and particularly SPEA2 -has become a reference EMA as it is being actively used to solve large multi-objective problems in many different fields, including medicine, engineering, etc [4], [5]. The simulation results shown here have a preconfigured limit of 3000 generations for both MC 2 and SPEA2, and SPEA2 is set up with the usual archive size of 100 individuals.…”