A CAD system for cerebral glioma in Magnetic Resonance Diffusion Tensor Images: semiautomatic segmentation and therapy follow up

Abstract

Tumor cells in cerebral glioma invade sur-rounding tissues preferentially along white matter tracts, spreading beyond the abnormal area seen on conventional Magnetic Resonance Images (MRI). Diffusion tensor imaging (DTI) can reveal larger peritumoral abnormalities in gliomas that are not ap-parent on MRI. Our aim was the characterization of pathological vs healthy tissue in DTI datasets by 3D statistical texture analysis, developing a semi automatic segmentation technique (CAD, Computer Assisted Detection sys-tem) for cerebral glioma, especially useful in patient follow-up during chemotherapy and for preoperative assessment of tumor extension.