Fully Automated Brain Tumor Segmentation Using Two MRI Modalities

Autor:	Russell Greiner, Mohamed Ben Salah, Idanis Diaz, Bret Hoehn, Albert Murtha, Pierre Boulanger
Rok vydání:	2013
Předmět:	Active contour model Modalities medicine.diagnostic_test business.industry Computer science Magnetic resonance imaging Sørensen–Dice coefficient Fully automated Histogram medicine Computer vision Segmentation Artificial intelligence business Brain tumor segmentation
Zdroj:	Advances in Visual Computing ISBN: 9783642419133 ISVC (1)
Popis:	An algorithm is presented for fully automated brain tumor segmentation from only two magnetic resonance image modalities. The technique is based on three steps: 1 alternating different levels of automatic histogram-based multi-thresholding step, 2 performing an effective and fully automated procedure for skull-stripping by evolving deformable contours, and 3 segmenting both Gross Tumor Volume and edema. The method is tested using 19 hand-segmented real tumors which shows very accurate results in comparison to a very recent method STS in terms of the Dice coefficient. Improvements of 5% and 20% respectively for segmentation of edema and Gross Tumor Volume have been recorded.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::22aa012cce25e1a4b55492b3737a93a5 https://doi.org/10.1007/978-3-642-41914-0_4 Zobrazit plný text záznamu