Title :
An Improved Level Set Method for Automatically Volume Measure: Application in Tumor Tracking from MRI Images
Author :
Li, X. ; Lebonvallet, S. ; Qiu, T. ; Ruan, S.
Author_Institution :
IUT de Troyes, Troyes
Abstract :
This paper presents an automatic segmentation system aimed at tracking the tumor volume during a therapeutic treatment from MRI images (an examination every four months). An improved level set method is proposed to automatically segment the tumor slice by slice for each examination and tracking the segmented volume for the following examinations. An initial slice with a seed is firstly chosen by the operator for the first examination. The system then performs automatically the tumor volume measure that allows the clinician to evaluate the therapeutic treatment. Our system is validated by comparing with hand tracking of the expert. It is also performed with success for following a patient during more than one year (three MRI examinations per year).
Keywords :
biomedical MRI; cancer; image segmentation; medical image processing; patient treatment; tumours; MRI images; automatic segmentation system; hand tracking; level set method; magnetic resonance imaging; therapeutic treatment; tumor tracking; Active contours; Brain; Fuzzy logic; Graphics; Image segmentation; Level set; Magnetic resonance imaging; Neoplasms; Topology; Volume measurement; Humans; Magnetic Resonance Imaging; Monitoring, Physiologic; Neoplasms; Time Factors; Tumor Burden;
Conference_Titel :
Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE
Conference_Location :
Lyon
Print_ISBN :
978-1-4244-0787-3
DOI :
10.1109/IEMBS.2007.4352413