A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation
The detection of a brain tumor through magnetic resonance imaging (MRI) is still challenging when the image is in low quality. Image segmentation could be done to provide a clear brain tumor area as the region of interest. In this study, we propose an improved model-based clustering approach for MRI...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/14/4892 |
| _version_ | 1797562290177835008 |
|---|---|
| author | Anindya Apriliyanti Pravitasari Nur Iriawan Kartika Fithriasari Santi Wulan Purnami Irhamah Widiana Ferriastuti |
| author_facet | Anindya Apriliyanti Pravitasari Nur Iriawan Kartika Fithriasari Santi Wulan Purnami Irhamah Widiana Ferriastuti |
| author_sort | Anindya Apriliyanti Pravitasari |
| collection | DOAJ |
| description | The detection of a brain tumor through magnetic resonance imaging (MRI) is still challenging when the image is in low quality. Image segmentation could be done to provide a clear brain tumor area as the region of interest. In this study, we propose an improved model-based clustering approach for MRI-based image segmentation. The main contribution is the use of the adaptive neo-normal distributions in the form of a finite mixture model that could handle both symmetrical and asymmetrical patterns in an MRI image. The neo-normal mixture model (Nenomimo) also resolves the limitation of the Gaussian mixture model (GMM) and the generalized GMM (GGMM), which are limited by the short-tailed form of their distributions and their sensitivity against noise. Model estimation is done through an optimization process using the Bayesian method coupled with a Markov chain Monte Carlo (MCMC) approach, and it employs a silhouette coefficient to find the optimum number of clusters. The performance of the Nenomimo was evaluated against the GMM and the GGMM using the misclassification ratio (<i>MCR</i>). Finally, this study discovered that the Nenomimo provides better segmentation results for both simulated and real data sets, with an average <i>MCR</i> for MRI brain tumor image segmentation of less than 3%. |
| first_indexed | 2024-03-10T18:26:09Z |
| format | Article |
| id | doaj.art-d132e7cbe8a44ced87ac3885d467d944 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:26:09Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d132e7cbe8a44ced87ac3885d467d9442023-11-20T07:00:46ZengMDPI AGApplied Sciences2076-34172020-07-011014489210.3390/app10144892A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor SegmentationAnindya Apriliyanti Pravitasari0Nur Iriawan1Kartika Fithriasari2Santi Wulan Purnami3Irhamah4Widiana Ferriastuti5Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Jl. Raya Bandung-Sumedang KM. 21, Bandung 45363, IndonesiaDepartment of Statistics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember, Jl. Arif Rahman Hakim Surabaya 60111, IndonesiaDepartment of Statistics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember, Jl. Arif Rahman Hakim Surabaya 60111, IndonesiaDepartment of Statistics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember, Jl. Arif Rahman Hakim Surabaya 60111, IndonesiaDepartment of Statistics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember, Jl. Arif Rahman Hakim Surabaya 60111, IndonesiaDepartment of Radiology, Faculty of Medicine, Universitas Airlangga, Surabaya 60132, IndonesiaThe detection of a brain tumor through magnetic resonance imaging (MRI) is still challenging when the image is in low quality. Image segmentation could be done to provide a clear brain tumor area as the region of interest. In this study, we propose an improved model-based clustering approach for MRI-based image segmentation. The main contribution is the use of the adaptive neo-normal distributions in the form of a finite mixture model that could handle both symmetrical and asymmetrical patterns in an MRI image. The neo-normal mixture model (Nenomimo) also resolves the limitation of the Gaussian mixture model (GMM) and the generalized GMM (GGMM), which are limited by the short-tailed form of their distributions and their sensitivity against noise. Model estimation is done through an optimization process using the Bayesian method coupled with a Markov chain Monte Carlo (MCMC) approach, and it employs a silhouette coefficient to find the optimum number of clusters. The performance of the Nenomimo was evaluated against the GMM and the GGMM using the misclassification ratio (<i>MCR</i>). Finally, this study discovered that the Nenomimo provides better segmentation results for both simulated and real data sets, with an average <i>MCR</i> for MRI brain tumor image segmentation of less than 3%.https://www.mdpi.com/2076-3417/10/14/4892MRIimage segmentationneo-normalmixture modelBayesianMCMC |
| spellingShingle | Anindya Apriliyanti Pravitasari Nur Iriawan Kartika Fithriasari Santi Wulan Purnami Irhamah Widiana Ferriastuti A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation Applied Sciences MRI image segmentation neo-normal mixture model Bayesian MCMC |
| title | A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation |
| title_full | A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation |
| title_fullStr | A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation |
| title_full_unstemmed | A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation |
| title_short | A Bayesian Neo-Normal Mixture Model (Nenomimo) for MRI-Based Brain Tumor Segmentation |
| title_sort | bayesian neo normal mixture model nenomimo for mri based brain tumor segmentation |
| topic | MRI image segmentation neo-normal mixture model Bayesian MCMC |
| url | https://www.mdpi.com/2076-3417/10/14/4892 |
| work_keys_str_mv | AT anindyaapriliyantipravitasari abayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT nuririawan abayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT kartikafithriasari abayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT santiwulanpurnami abayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT irhamah abayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT widianaferriastuti abayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT anindyaapriliyantipravitasari bayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT nuririawan bayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT kartikafithriasari bayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT santiwulanpurnami bayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT irhamah bayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation AT widianaferriastuti bayesianneonormalmixturemodelnenomimoformribasedbraintumorsegmentation |