Automated Multi-Contrast Brain Pat hological Area Extraction from 2D MR Images
Fuente:
Redalyc
Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Universidad Nacional Autónoma de México
2015
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1876432705487372288 |
|---|---|
| author | P. Dvorak |
| author_facet | P. Dvorak |
| contents | Automated Multi-Contrast Brain Pat hological Area Extraction from 2D MR Images P. Dvorak K. Bartusek W. G. Kropatsch Z. Smekal Ingeniería MR I MR I Multi Multi Brain Tumor The aim of this work is to propose the fully automated pa thological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresholding. The proposed algorithm first detects the presence of pathology and then starts its extraction. T2 images are used for the presence detection and the multi-contrast MRI is used for the extraction, concretely T2 and FLAIR images. The extraction is based on thresholding, where Otsu's algorithm is used for the automatic determination of the threshold. Since the method is based on symmetry, it works for both ax ial and coronal planes. In both these planes of healthy brain, the approximate left-right symmetr y exists and it is used as the prior knowledge for searching the approximate pathology location. It is assumed that this area is not loca ted symmetrically in both hemispheres, which is met in most cases. The detection algorithm was tested on 203 T2-wei ghted images and reached the tr ue positive rate of 87.52% and true negative rate of 93.14%. The extraction algorith m was tested on 357 axial and 443 coronal real images from publicly available BRATS databases containing 3D volumes brain tumor patients. The results were evaluated by Dice Coefficient (axial: 0.85±0.11, coro nal 0.82±0.18) and by Accuracy (axial: 0.96±0.05, coronal 0.94±0.09). 2015 artículo científico 1665-6423 https://www.redalyc.org/articulo.oa?id=47436895005 en http://www.redalyc.org/revista.oa?id=474 Journal of Applied Research and Technology application/pdf Universidad Nacional Autónoma de México Journal of Applied Research and Technology (México) Num.1 Vol.13 |
| format | Artículo científico |
| id | redalyc_47436895005 |
| institution | Redalyc |
| language | en |
| publishDate | 2015 |
| publisher | Universidad Nacional Autónoma de México |
| spellingShingle | Automated Multi-Contrast Brain Pat hological Area Extraction from 2D MR Images P. Dvorak Ingeniería MR I MR I Multi Multi Brain Tumor Automated Multi-Contrast Brain Pat hological Area Extraction from 2D MR Images P. Dvorak K. Bartusek W. G. Kropatsch Z. Smekal Ingeniería MR I MR I Multi Multi Brain Tumor The aim of this work is to propose the fully automated pa thological area extraction from multi-parametric 2D MR images of brain. The proposed method is based on multi-resolution symmetry analysis and automatic thresholding. The proposed algorithm first detects the presence of pathology and then starts its extraction. T2 images are used for the presence detection and the multi-contrast MRI is used for the extraction, concretely T2 and FLAIR images. The extraction is based on thresholding, where Otsu's algorithm is used for the automatic determination of the threshold. Since the method is based on symmetry, it works for both ax ial and coronal planes. In both these planes of healthy brain, the approximate left-right symmetr y exists and it is used as the prior knowledge for searching the approximate pathology location. It is assumed that this area is not loca ted symmetrically in both hemispheres, which is met in most cases. The detection algorithm was tested on 203 T2-wei ghted images and reached the tr ue positive rate of 87.52% and true negative rate of 93.14%. The extraction algorith m was tested on 357 axial and 443 coronal real images from publicly available BRATS databases containing 3D volumes brain tumor patients. The results were evaluated by Dice Coefficient (axial: 0.85±0.11, coro nal 0.82±0.18) and by Accuracy (axial: 0.96±0.05, coronal 0.94±0.09). 2015 artículo científico 1665-6423 https://www.redalyc.org/articulo.oa?id=47436895005 en http://www.redalyc.org/revista.oa?id=474 Journal of Applied Research and Technology application/pdf Universidad Nacional Autónoma de México Journal of Applied Research and Technology (México) Num.1 Vol.13 |
| title | Automated Multi-Contrast Brain Pat hological Area Extraction from 2D MR Images |
| topic | Ingeniería MR I MR I Multi Multi Brain Tumor |
| url | https://www.redalyc.org/articulo.oa?id=47436895005 |