Bilgisayarlı Tomografi Görüntüleri Üzerinde Karaciğer Bölgesinin Bilgisayar Destekli Otomatik Bölütleme Uygulaması

Abstract

In this study, an automated computer-assisted method for the segmentation of the liver on abdominal computed tomography (CT) images is proposed and an application software is developed for segmentation. The segmentation process is performed by using Region Growing (RG) and Fuzzy C-Means (FCM) methods by means of the developed application software. The similarities of segmentation results obtained by RG and FCM algorithms and the liver regions determined by the physician are measured quantitatively using the application software. As a result of experimental studies, RG algorithm is more successful than FCM algorithm both in terms of similarity rates and statistical results. Figure A. Liver segmentation procedure on CT scans using proposed method Purpose: The liver is a vital organ in the body. In liver-related diseases, especially CT scans, the delineation of the liver is essential for diagnosis and treatment planning. In order to improve the accuracy of the segmentation of liver, a computer-assisted method based on RG and FCM and an application software are proposed on abdominal CT images in this paper. Theory and Methods: For the segmentation of the liver region, RG and FCM algorithms are used. In order to measure the performance of segmentation with these algorithms, a physician marked out the boundary of the liver. In the study, the segmentation results obtained by the RG and FCM algorithms are compared on the developed application software using physician selection criteria. Jaccard similarity criterion are used to compare segmentation results. Results: In the experimental studies on 88 CT images, average performance values are obtained for 91.15% in the RG algorithm and 75.16% in the FCM algorithm according to the Jaccard similarity criterion. In computational times, the RG algorithm is more successful than the FCM algorithm, measured on average from 3.15 seconds to 7.50 seconds. Conclusion: In the study, segmentation with the RG algorithm is more successful. In addition, the statistical significance of quantitative values obtained from similarity measurements is measured. It is concluded that the segmentation results obtained by the RG algorithm revealed a significant difference by evaluating the significance tests. Moreover, the segmentation process times are compared with both segmentation methods and segmentation with RG is found to be faster. The findings show that the proposed method can be used as a secondary tool in the decision-making process of physicians.

Aircraft Detection System Based on Regions with Convolutional Neural Networks

“…In the target detection process used in applications that form the backbone of defence systems such as unmanned aerial vehicles, important outputs can be presented to decision support systems with the help of high-level information that can be obtained from the images. [1], [2]. In general, if it is desired to define the problem of object recognition from high-resolution images, it can be said that this definition is based on determining the position of the object in the given image.…”

“…The _______________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________________ 1 Electrical and Electronics Eng. Firat University, Elazig -23019, Turkey ORCID ID: 0000-0001-9366-6124 2 Mechatronics Eng. Firat University, Elazig -23019, Turkey ORCID ID: 0000-0002-3625-5027 3 Electrical and Electronics Eng.…”