View Publication

An Automatic Brain Tumor Segmentation Tool

Idanis Diaz
Pierre Boulanger
Russ Greiner, Dept of Computing Science; PI of AICML
Bret Hoehn
Lindsay Rowe
Albert Murtha, Cross Cancer Institute, Edmonton

This paper introduces an automatic brain tumor segmentation method (ABTS) for segmenting multiple components of brain tumor using four magnetic resonance image modalities. ABTS's four stages involve automatic histogram multi-thresholding and morphological operations including geodesic dilation. Our empirical results, on 16 real tumors, show that ABTS works very effectively, achieving a Dice accuracy compared to expert segmentation of 81% in segmenting edema and 85% in segmenting gross tumor volume (GTV).

Citation

I. Diaz, P. Boulanger, R. Greiner, B. Hoehn, L. Rowe, A. Murtha. "An Automatic Brain Tumor Segmentation Tool". Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp 3339-3342, July 2013.

Keywords:	BTAP, MRI, brain tumor, segmentation
Category:	In Conference
Web Links:	IEEE
	DOI

BibTeX

@incollection{Diaz+al:EMBC13,
  author = {Idanis Diaz and Pierre Boulanger and Russ Greiner and Bret Hoehn
    and Lindsay Rowe and Albert Murtha},
  title = {An Automatic Brain Tumor Segmentation Tool},
  Pages = {3339-3342},
  booktitle = { Annual International Conference of the IEEE Engineering in
    Medicine and Biology Society},
  year = 2013,
}

Last Updated: February 12, 2020
Submitted by Sabina P

Not Logged In

PapersDB

An Automatic Brain Tumor Segmentation Tool

Citation

BibTeX