arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.01239eess.IVcs.CV
收藏

一种性能一致且计算高效的CNN高质量脑肿瘤自动分割系统

A Performance-Consistent and Computation-Efficient CNN System for High-Quality Automated Brain Tumor Segmentation

Concordia University(康考迪亚大学)

Juncheng Tong, Chunyan Wang

摘要:

基于CNN的全自动脑肿瘤分割系统的研究进展迅速。为了使系统能够应用于实际,开发基于CNN的全自动脑肿瘤分割系统的研究进展迅速。为了使系统在实际中得到应用,必须具有良好的加工质量和可靠性。此外,对于这样的系统的广泛应用,期望计算复杂性的最小化,这也可以导致计算中的随机性的最小化,并且因此导致更好的性能一致性。为此,所提出的系统中的CNN具有独特的结构,具有2个区别字符。首先,设计了特征提取模块的三条路径,分别从多模态输入中提取单模态、双模态和跨模态数据的综合特征信息。此外,它有一个特定的三分支分类块来识别4类像素。每个分支被单独训练,使得参数具体地用目标肿瘤区域的对应地面实况数据来更新。系统的卷积层是根据特定目的定制设计的,总共有61,843个参数,非常简单。所提出的系统使用BraTS 2018和BraTS 2019数据集进行了广泛测试。从BrTS 2018验证样本的10次实验中获得的平均Dice评分分别为0.787 ± 0.003、0.886 ± 0.002、0.801 ± 0.007(增强肿瘤、整个肿瘤和肿瘤核心)和0.751 ± 0.007、0.885 ± 0.002、0.776 ± 0.004(BrTS 2019)。测试结果表明,该系统能够以一致的方式执行高质量的分割。此外,其极低的计算复杂度将有助于其在各种环境中的实现/应用。

英文摘要:

The research on developing CNN-based fully-automated Brain-Tumor-Segmentation systems has been progressed rapidly. For the systems to be applicable in practice, a good The research on developing CNN-based fully-automated Brain-Tumor-Segmentation systems has been progressed rapidly. For the systems to be applicable in practice, a good processing quality and reliability are the must. Moreover, for wide applications of such systems, a minimization of computation complexity is desirable, which can also result in a minimization of randomness in computation and, consequently, a better performance consistency. To this end, the CNN in the proposed system has a unique structure with 2 distinguished characters. Firstly, the three paths of its feature extraction block are designed to extract, from the multi-modality input, comprehensive feature information of mono-modality, paired-modality and cross-modality data, respectively. Also, it has a particular three-branch classification block to identify the pixels of 4 classes. Each branch is trained separately so that the parameters are updated specifically with the corresponding ground truth data of a target tumor areas. The convolution layers of the system are custom-designed with specific purposes, resulting in a very simple config of 61,843 parameters in total. The proposed system is tested extensively with BraTS2018 and BraTS2019 datasets. The mean Dice scores, obtained from the ten experiments on BraTS2018 validation samples, are 0.787+0.003, 0.886+0.002, 0.801+0.007, for enhancing tumor, whole tumor and tumor core, respectively, and 0.751+0.007, 0.885+0.002, 0.776+0.004 on BraTS2019. The test results demonstrate that the proposed system is able to perform high-quality segmentation in a consistent manner. Furthermore, its extremely low computation complexity will facilitate its implementation/application in various environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑