A Fully Automatic Approach for Multimodal PET and MR Image Segmentation in Gamma Knife Treatment Planning

Highlights • The aim of this study is to combine Biological Target Volume (BTV) segmentation and Gross Target Volume (GTV) segmentation in stereotactic neurosurgery. • Our goal is to enhance Clinical Target Volume (CTV) definition, including metabolic and morphologic information, for treatment planning and patient follow-up. • We propose a fully automatic approach for multimodal PET and MR image segmentation. • The proposed approach is based on Random Walker (RW) and Fuzzy C-Means clustering (FCM) algorithms. • A total of 19 brain metastatic tumors, undergone stereotactic neuro-radiosurgery, were retrospectively considered in the present study. • A framework for the evaluation of multimodal PET/MRI segmentation is also presented, considering volume-based, overlap-based and spatial distance-based metrics. Statistics was also included to measure correlation. • A five-point Likert scale was used to provide a qualitative evaluation about the clinical value of the proposed multimodal approach.