Abstract |
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).
|
Authors | Idanis Diaz, Pierre Boulanger, Russell Greiner, Bret Hoehn, Lindsay Rowe, Albert Murtha |
Journal | Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
(Annu Int Conf IEEE Eng Med Biol Soc)
Vol. 2013
Pg. 3339-42
( 2013)
ISSN: 2694-0604 [Electronic] United States |
PMID | 24110443
(Publication Type: Journal Article, Research Support, Non-U.S. Gov't)
|
Topics |
- Algorithms
- Automation
- Brain Edema
(pathology)
- Brain Neoplasms
(pathology)
- Humans
- Image Processing, Computer-Assisted
- Magnetic Resonance Imaging
- Signal Processing, Computer-Assisted
- Tumor Burden
|