Hermanto, Yusuf Puji (2019) Segmentasi Citra MRI Tumor Otak Menggunakan Gaussian Mixture Model dengan Pendekatan Algoritma Reversible Jump Markov Chain Monte Carlo. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211440000095-Undergraduate_Theses.pdf Download (2MB) | Preview |
Abstract
Tumor otak merupakan penyakit mematikan yang menduduki peringkat ke-15 di Indonesia menurut Badan Kesehatan Dunia (WHO) pada tahun 2018. Dalam dunia medis, tumor otak dapat dideteksi melalui Magnetic Resonance Imaging (MRI). Permasalahan utama adalah bagaimana memisahkan area tumor otak sebagai Wilayah yang diminati (ROI) dengan bagian sehat lainnya (Non-ROI) di MRI. Dalam statistika komputasi, metode yang digunakan dalam segmentasi gambar adalah analisis cluster. Clustering Berbasis Model dengan Gaussian Mixture Model (GMM) sering digunakan untuk menemukan kluster tempat tumor tumbuh. Algoritma EM dan Bayesian digabungkan dengan Markov Chain Monte Carlo (MCMC) dapat digunakan untuk mengoptimalkan GMM. Namun, baik EM dan Bayesian MCMC diasumsikan bahwa jumlah cluster adalah tetap. Oleh karena itu, untuk memilih jumlah cluster yang optimal, kita harus menggunakan kriteria pemilihan cluster tertentu. Proses ini membuat segmentasi menjadi cukup rumit dan tidak otomatis. Penelitian ini mencoba menggunakan GMM menggunakan Algoritma Reversible Jump Markov Chain Monte Carlo (GMM-RJMCMC) untuk mensegmentasi tumor otak dan membandingkannya dengan GMM-EM. Penggunaan RJMCMC diharapkan dapat mempercepat proses perhitungan. Selain itu, segmentasi citra MRI dapat menjadi lebih adaptif. Hasilnya menunjukkan bahwa dari Correct Classification Ratio (CCR), metode GMM-RJMCMC dapat memberikan hasil segmentasi yang lebih baik dibandingkan dengan GMM-EM.
==================================================================================================================================
A brain tumor is the 15th deadly disease in Indonesia according to the WHO in 2018. In medical treatment, brain tumors can be detected through Magnetic Resonance Imaging (MRI). The main problem is how to separate the brain tumor area as the Region of interest (ROI) with the other healthy part (Non-ROI) in the MRI. In the computational statistics, a method used in image segmentation is cluster analysis. Model Based Clustering with Gaussian Mixture Model (GMM) is often used to find the cluster where the tumor is placed. The EM Algorithm and Bayesian coupled with Markov chain Monte Carlo (MCMC) could be used to optimize the GMM. However, both EM and Bayesian MCMC are assumed that the number of clusters is fixed. Therefore, to select the optimum number of the clusters, we have to use the certain cluster selection criteria. This process makes the segmentation quite complicated and is not automatic. This study tries to employ the GMM using Reversible Jump Markov Chain Monte Carlo Algorithm (GMM-RJMCMC) to segment the MRIbased brain tumor and compare it with the GMM-EM. The use of RJMCMC is expected to accelerate the calculation process. Moreover, the MRI image segmentation could become more adaptive. The result shows that from the Correct Classification Ratio (CCR), the GMM-RJMCMC could provide better segmentation results compared to the GMM-EM.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSSt 519.233 Her s-1 2019 |
| Uncontrolled Keywords: | Bayessian, Brain Tumor, Gaussian, Mixture Model, MRI Segmentation, RJMCMC |
| Subjects: | H Social Sciences > HA Statistics |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Yusuf Puji Hermanto |
| Date Deposited: | 25 Apr 2024 07:32 |
| Last Modified: | 25 Apr 2024 07:32 |
| URI: | http://repository.its.ac.id/id/eprint/64771 |
Actions (login required)
 |
View Item |