RESEARCH Tumor segmentation in br e

he le to ed ts a it me characterization of abnormalities are still a challenging and difficult task because of the variety of the possible brain tumor segmentation task, and quantified a 20 % ± 15 % variation within individuals repeating the task three El-Melegy and Mokhtar EURASIP Journal on Image and Video Processing 2014, 2014:21 http://jivp.eurasipjournals.com/content/2014/1/21geous since they are not subject to this variation, and thus,1Electrical Engineering Department, Assiut University, Assiut 71516, Egypt Full list of author information is available at the end of the articleshapes, locations and image intensities of various types of tumors. This task involves various disciplines includ-ing medicine, MRI physic, radiologist's perception, and image analysis based on intensity and shape. times at one month intervals. This statistic demonstrates that the manual segmentation has no confidence in track-ing the tumor volume during the patient follow-up process and the automatic methods that could achieve a sufficient level of accuracy would be highly desirable for their ability to perform high-throughput segmentation. On the other hand, automatic methods would be advanta- * Correspondence