TELKOMNIKA Telecommunication, Computing, Electronics and Control
Brain tumor segmentation using multi-level Otsu thresholding and Chan-Vese active contour model

TELKOMNIKA Telecommunication, Computing, Electronics and Control
Brain tumor segmentation using multi-level Otsu thresholding and Chan-Vese active contour model

Active contour model, Brain tumor, MRI, Multi-level threshold, Segmentation

Research on brain tumor segmentation has been developed, ranging from threshold-based methods to the use of the deep learning algorithm. In this study, we proposed a region-based brain tumor segmentation method, namely the active contour model (ACM). Tumor segmentation was carried out using fluid attenuated inversion recovery (FLAIR) modality magnetic resonance imaging (MRI) image data obtained from the multimodal brain tumor image segmentation benchmark (BRATS) 2015 dataset of 86 images. The initial stage of our segmentation method is to find the initial initialization point/area for the ACM algorithm using multi-level Otsu thresholding, with the level used in this study is 3 levels. After the initial initialization area has been obtained, the segmentation process is continued with ACM which explores the tumor area to obtain a full and accurate tumor area result. The results of this study obtained dice similarity (DS) for our study of 0.7856 with a total time required of 28.080722 seconds, which better than other method that we also compared with ours, 0.75 compared to 0.78 in term of DS.

Heru Pramono Hadi, Edi Faisal, Eko Hari Rachmawanto

DOI: 10.12928/TELKOMNIKA.v20i4.21679

Universitas Ahmad Dahlan

August 2022

Sri Wahyuni

ISSN: 1693-6930

http://journal.uad.ac.id/index.php/TELKOMNIKA

PDF

English

Text

TELKOMNIKA Telecommunication, Computing, Electronics and Control