A deep learning model integrating FCNNs and CRFs for brain tumor segmentation

Accurate brain tumor segmentation is of great importance in cancer diagnosis, treatment planning, and treatment outcome evaluation. Since manual segmentation of brain tumors is laborious (Bauer  et al., 2013), an enormous effort has devoted to the development of semi-automatic or automatic brain tumor segmentation methods. Most of the existing brain tumor segmentation studies are focusing on gliomas that are the most common brain tumors in adults and can be measured by Magnetic Resonance Imaging (MRI) with multiple sequences, such as T2-weighted fluid attenuated inversion recovery (Flair), T1-weighted (T1), T1-weighted contrast-enhanced (T1c), and T2-weighted (T2).

Source: Medical Image Analysis - October 5, 2017 Category: Radiology Authors: Xiaomei Zhao, Yihong Wu, Guidong Song, Zhenye Li, Yazhuo Zhang, Yong Fan Source Type: research