Dr. Karl Fritscher,\u00a0Department for Biomedical Image Analysis, UMIT, Austria<\/a>.<\/p>\nMulti Atlas Based Segmentation (MABS) is a methodology for automatic image segmentation that\u00a0is proving to be able to provides robust and reliable results.
\nThe rationale behind MABS is to use a set of digital atlases (anatomical image plus labels) and\u00a0image registration technique to \u201cbring\u201d the the contours from the atlases to the query image.\u00a0Applying a statistical methodology to all the deformed labels the final segmentation will be\u00a0extracted. Of course the number and the \u201ctype\u201d of the atlases that will be used in this process can\u00a0significantly influence the quality of the final results and also the time required to get them. In fact\u00a0it would be advantageous to not include in the workflow the atlases that introduce redundant or\u00a0noisy information. This filtering process is usually called \u201catlas selection\u201d.
\nIn our work we are implementing a MABS algorithm into the Plastimatch project\u00a0(www.plastimatch.org). In this software have been introduced many interesting and unique features\u00a0in order to solve scientific and practical issues related to this type of algorithms. Complete and\u00a0smart workflow that allows to use data directly from a clinical enviroment, atlas selection based on\u00a0different strategies, multiple ways for final contour extracting (gaussian and\/or staple), fast and\u00a0accurate image registration process are the main advantages of our implementation.
\nSeveral tests are running on head and neck CT dataset (radiotherapy purpose) and brain MRI dataset (neuroscience application) to validate the proposed metodology and its innovative features.<\/p>\n
![\"MABS2\"](\"https:\/\/i1.wp.com\/www.imagenglab.com\/newsite\/wp-content\/uploads\/2016\/03\/MABS2.png?resize=640%2C271\")
<\/p>\n
\n