Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods
Image segmentation can be defined as segregation or partitioning of images into multiple regions with the same predefined homogeneity criterion. Image segmentation is a crucial process in medical image analysis. This paper explores and investigates several unsupervised image segmentation approaches...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Medical Project Poland
2020
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/90798/1/LimJiaQi2020_DetectionofBrainTumourin2DMRIImplementation.pdf |
| _version_ | 1796865101637091328 |
|---|---|
| author | Lim, Jia Qi Alias, Norma Johar, Farhana |
| author_facet | Lim, Jia Qi Alias, Norma Johar, Farhana |
| author_sort | Lim, Jia Qi |
| collection | ePrints |
| description | Image segmentation can be defined as segregation or partitioning of images into multiple regions with the same predefined homogeneity criterion. Image segmentation is a crucial process in medical image analysis. This paper explores and investigates several unsupervised image segmentation approaches and their viability and performances in delineating tumour region in contrast enhanced T1-weighted brain MRI (Magnetic Resonance Imaging) scans. First and foremost, raw CE T1-weighted brain MR images are downloaded from a free online database. The images are then pre-processed and undergo an important process called skull stripping. Then, image segmentation techniques such as k-means clustering, Gaussian mixture model segmentation and fuzzy c-means are applied to the pre-processed MR images. The image segmentation results are evaluated using several performance measures, such as precision, recall, Tanimoto coefficient and Dice similarity index in reference to ground truth images. The highest average Dice coefficient is achieved by k-means (0.189) before post-processing and GMM (0.208) after post-processing. Unsupervised clustering-based brain tumour segmentation based on just image pixel intensity in single-spectral brain MRI without adaptive post-processing algorithm cannot achieve efficient and robust segmentation results. |
| first_indexed | 2024-03-05T20:51:50Z |
| format | Article |
| id | utm.eprints-90798 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:51:50Z |
| publishDate | 2020 |
| publisher | Medical Project Poland |
| record_format | dspace |
| spelling | utm.eprints-907982021-04-30T14:57:25Z http://eprints.utm.my/90798/ Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods Lim, Jia Qi Alias, Norma Johar, Farhana QA Mathematics Image segmentation can be defined as segregation or partitioning of images into multiple regions with the same predefined homogeneity criterion. Image segmentation is a crucial process in medical image analysis. This paper explores and investigates several unsupervised image segmentation approaches and their viability and performances in delineating tumour region in contrast enhanced T1-weighted brain MRI (Magnetic Resonance Imaging) scans. First and foremost, raw CE T1-weighted brain MR images are downloaded from a free online database. The images are then pre-processed and undergo an important process called skull stripping. Then, image segmentation techniques such as k-means clustering, Gaussian mixture model segmentation and fuzzy c-means are applied to the pre-processed MR images. The image segmentation results are evaluated using several performance measures, such as precision, recall, Tanimoto coefficient and Dice similarity index in reference to ground truth images. The highest average Dice coefficient is achieved by k-means (0.189) before post-processing and GMM (0.208) after post-processing. Unsupervised clustering-based brain tumour segmentation based on just image pixel intensity in single-spectral brain MRI without adaptive post-processing algorithm cannot achieve efficient and robust segmentation results. Medical Project Poland 2020-04 Article PeerReviewed application/pdf en http://eprints.utm.my/90798/1/LimJiaQi2020_DetectionofBrainTumourin2DMRIImplementation.pdf Lim, Jia Qi and Alias, Norma and Johar, Farhana (2020) Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods. Onkologia i Radioterapia, 14 (2). pp. 1-10. ISSN 1896-8961 https://www.oncologyradiotherapy.com/articles/detection-of-brain-tumour-in-2d-mri-implementation-and-critical-review-of-clusteringbased-image-segmentation-methods.pdf |
| spellingShingle | QA Mathematics Lim, Jia Qi Alias, Norma Johar, Farhana Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods |
| title | Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods |
| title_full | Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods |
| title_fullStr | Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods |
| title_full_unstemmed | Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods |
| title_short | Detection of brain tumour in 2d MRI: implementation and critical review of clustering-based image segmentation methods |
| title_sort | detection of brain tumour in 2d mri implementation and critical review of clustering based image segmentation methods |
| topic | QA Mathematics |
| url | http://eprints.utm.my/90798/1/LimJiaQi2020_DetectionofBrainTumourin2DMRIImplementation.pdf |
| work_keys_str_mv | AT limjiaqi detectionofbraintumourin2dmriimplementationandcriticalreviewofclusteringbasedimagesegmentationmethods AT aliasnorma detectionofbraintumourin2dmriimplementationandcriticalreviewofclusteringbasedimagesegmentationmethods AT joharfarhana detectionofbraintumourin2dmriimplementationandcriticalreviewofclusteringbasedimagesegmentationmethods |