Detail publikace

Automated 3D Brain Tumor Edema Segmentation in FLAIR MRI

Originální název

Automated 3D Brain Tumor Edema Segmentation in FLAIR MRI

Anglický název

Automated 3D Brain Tumor Edema Segmentation in FLAIR MRI

Jazyk

en

Originální abstrakt

The aim of this work is to develop a fully automatic method for peritumoral region segmentation in 3D FLAIR MRI. FLAIR was selected because of the visibility and manifestation of tumor edemas in this image type. The main reason for the edema segmentation is the tumor classification. This will be carried out by applying the resulting mask to perfusion MR images. Since perfusion images are of a very low contrast, the pathological area, it means the tumor and a potential edema around it, has to be detected and segmented in another type of MR images.

Anglický abstrakt

The aim of this work is to develop a fully automatic method for peritumoral region segmentation in 3D FLAIR MRI. FLAIR was selected because of the visibility and manifestation of tumor edemas in this image type. The main reason for the edema segmentation is the tumor classification. This will be carried out by applying the resulting mask to perfusion MR images. Since perfusion images are of a very low contrast, the pathological area, it means the tumor and a potential edema around it, has to be detected and segmented in another type of MR images.

BibTex 


@misc{BUT100785,
  author="Pavel {Dvořák} and Karel {Bartušek}",
  title="Automated 3D Brain Tumor Edema Segmentation in FLAIR MRI",
  annote="The aim of this work is to develop a fully automatic method for peritumoral region segmentation in 3D FLAIR MRI. FLAIR was selected because of the visibility and manifestation of tumor edemas in this image type. The main reason for the edema segmentation is the tumor classification. This will be carried out by applying the resulting mask to perfusion MR images. Since perfusion images are of a very low contrast, the pathological area, it means the tumor and a potential edema around it, has to be detected and segmented in another type of MR images.",
  address="Springer",
  chapter="100785",
  doi="10.1007/s10334-013-0385-4",
  institution="Springer",
  number="1 Supplement",
  year="2013",
  month="october",
  pages="489--490",
  publisher="Springer",
  type="abstract"
}