دانلود رایگان مقاله پیش بینی موقعیت نسبی برشCT با سیستم هوش محاسباتی

Abstract

One of the most common techniques in radiology is the computerized tomography (CT) scan. Automatically determining the relative position of a single CT slice within the human body can be very useful. It can allow for an efficient retrieval of slices from the same body region taken in other volume scans and provide useful information to the non-expert user. This work addresses the problem of determining which portion of the body is shown by a stack of axial CT image slices. To tackle this problem, this work proposes a computational intelligence system that combines semantics-based operators for Genetic Programming with a local search algorithm, coupling the exploration ability of the former with the exploitation ability of the latter. This allows the search process to quickly converge towards (near-)optimal solutions. Experimental results, using a large database of CT images, have confirmed the suitability of the proposed system for the prediction of the relative position of a CT slice. In particular, the new method achieves a median localization error of 3.4 cm on unseen data, outperforming standard Genetic Programming and other techniques that have been applied to the same dataset. In summary, this paper makes two contributions: (i) in the radiology domain, the proposed system outperforms current state-of-the-art techniques; (ii) from the computational intelligence perspective, the results show that including a local searcher in Geometric Semantic Genetic Programming can speed up convergence without degrading test performance.

4. Conclusions

This paper proposes a computational intelligence system to automatically determine the relative position of a single CT slice within a full body scan. Knowing the relative position in a scan allows the efficient retrieval of similar slices from the same body region in other volume scans. Moreover, the relative position is often important information for a non-expert user that only has access to a single CT slice of a scan. The proposed system is based on a variant of GP. In particular, the GP system makes use of particular genetic operators that, differently from the standard genetic operators used in GP, work on the semantics ofthe solutions.While the use of semantic methods in GP has been successfully investigated and applied, several important problems that do not allow to efficiently use these methods are still open. In particular, the GP system that uses semantics operators (GSGP) requires a large amount of generations to converge towards optimal solutions. In this perspective,this work integrated the GSGP framework with a local search optimizer. The use of a local searcher improved the convergence speed of GSGP, while not overfitting the training data. That is, by combining the exploration ability of GSGP with the exploitation ability of a local search method the proposed system outperformed state-of-the-art performance. Experimental results, achieved using a large database of CT images, have shown the suitability of the proposed system for the studied problem. In particular, the new method provides a median localization error of 3.4 cm on unseen data, outperforming standard GP, the basic GSGP algorithm and all other existing state-of-the-art techniques for this application.