The automatic detection and extraction of tumor area in Magnetic Resonance Imaging (MRI) is an important and challenging task. This paper presents a fully automatic and unsupervised method for fast and accurate extraction of brain tumor area from MR images. The proposed method named as Saliency Based Segmentation (SBS) is based on visual saliency. The saliency model detects the pathologically important area and then fuzzy thresholding is used for extraction of the detected region. The performance of SBS is compared with Adaptively Regularized Kernel-Based Fuzzy C-Means Clustering, Mean Shift and Fuzzy C-Means clustering with Level Set Method. The experimental evaluation validated on BRATS database using Jaccard index (0.84 ± 0.04), Dice Index (0.91 ± 0.02), Execution time (2.99 ± 0.29), Precision (0.82 ± 0.16), Recall (0.97 ± 0.03) and F-measure (0.88 ± 0.10) demonstrates that SBS achieves better segmentation results even in the presence of noise and uneven illumination in images.

在磁共振成像（MRI）中自动检测和提取肿瘤区域是一项重要且具有挑战性的任务。本文提出了一种全自动，无监督的方法，可以快速准确地从MR图像中提取脑肿瘤区域。所提出的名为基于显着性的分割（SBS）的方法是基于视觉显着性的。显着性模型检测到病理上重要的区域，然后使用模糊阈值提取检测到的区域。将SBS的性能与基于水平集方法的自适应正则核模糊C均值聚类，均值平移和模糊C均值聚类进行了比较。在BRATS数据库上使用Jaccard指数（0.84±0.04），骰子指数（0.91±0.02），执行时间（2.99±0.29），精度（0.82±0.16），召回率（0.97±0）验证了实验评估。