Fulop, Timea and Gyorfi, Agnes and Suranyi, Bela and Kovacs, Levente and Szilagyi, Laszlo (2020) Brain Tumor Segmentation from MRI Data Using Ensemble Learning and Multi-Atlas. In: 18th IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI 2020, Herl'any, Slovakia), 23-25 Jan 2020, Herl'any, Slovakia.
|
Text
2020-SAMI-egyik.pdf Download (2MB) | Preview |
Abstract
Atlases are frequently employed to assist medical image segmentation with prior information. This paper introduces a multi-atlas architecture that is trained to locally characterize the appearance (average intensity and standard deviation) of normal tissues in various observed and computed data channels of brain MRI records. The multiple atlas is then deployed to enhance the accuracy of an ensemble learning based brain tumor segmentation procedure that uses binary decision trees. The proposed method is validated using the low-grade tumor volumes of the BraTS 2016 train data set. The use of atlases improve the segmentation quality, causing a rise of up to 1.5% in average Dices scores.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Uncontrolled Keywords: | Atlas-based image segmentation, multi-atlas, brain tumor segmentation, magnetic resonance imaging |
| Subjects: | Q Science / természettudomány > QA Mathematics / matematika > QA76 Computer software / programozás |
| Depositing User: | Dr. László Szilágyi |
| Date Deposited: | 23 Sep 2020 13:29 |
| Last Modified: | 23 Sep 2020 13:29 |
| URI: | http://real.mtak.hu/id/eprint/114302 |
Actions (login required)
 |
Edit Item |
