Accurate brain tumor segmentation plays a significant role in the area of radiotherapy diagnosis and in the proper treatment for brain tumor detection. Typically, the brain tumor has poor boundary and low contrast between normal and lesion soft tissues that makes segmentation of brain tumor in the CT images a challenging task. This paper presents a novel approach to brain image segmentation using pulse-coupled neural network (PCNN) and zero level set (ZL) with Sobolev gradient (SG) method. In this article, PCNN is designed to use as an edge mapper to provide a regional description for the ZL to segregate the CT images based on contour maps. The PCNN is used to estimate the exact threshold to obtain the prominent edges of the images. Resulting edges are utilized in the ZL to extract image contour from the source image. Due to the over-sensitivity of the ZL method on the initial contour, a level set with the SG has been equipped to overcome the limitation of the ZL method. The experimental results show satisfactory segmentation outcomes with excellent accuracy and acceleration in comparison with the state-of-the-art methods.

中文翻译：

---

在GPU框架中使用PCNN和Sobolev梯度方法的CT图像分割新算法

准确的脑肿瘤分割在放射治疗诊断和脑肿瘤检测的正确治疗方面起着重要作用。通常，脑肿瘤边界差，正常和病变软组织之间的对比度低，这使得在CT图像中分割脑肿瘤成为一项艰巨的任务。本文提出了一种使用脉冲耦合神经网络（PCNN）和零水平集（ZL）和Sobolev梯度（SG）方法进行脑图像分割的新方法。在本文中，PCNN被设计为用作边缘映射器，以为ZL提供区域描述，以基于轮廓图分离CT图像。PCNN用于估计确切阈值以获得图像的突出边缘。在ZL中使用所得边缘从源图像中提取图像轮廓。由于ZL方法在初始轮廓上的灵敏度过高，因此配备了SG设定的水平可以克服ZL方法的局限性。实验结果表明，与最新方法相比，分割结果令人满意，准确度和加速度都非​​常出色。