论著摘要 |【AI-CT】用于骨肉瘤的CT图像分割的MSFCN多重监督全卷积网络(双语版)

2018-01-19 11:10:53 admin 0
标签:   人工智能 CT 卷积神经网络 CNN 骨肉瘤 多重监督网络 图像分割

MSFCN-multiple supervised fully convolutional networks for the osteosarcoma segmentation of CT images.

发表日期: 2017.05.01   来源:Comput Methods Programs Biomed. 2017 May;143:67-74.

作者:

Huang L1, Xia W2, Zhang B3, Qiu B4, Gao X2.

作者介绍:

1. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China; University of Science and Technology of China, Hefei, China.

2. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China.

3. Second Affiliated Hospital of Soochow University, Suzhou, China.

4. University of Science and Technology of China, Hefei, China.

摘要

Abstact

背景与目的

骨肉瘤的计算机断层扫描(CT)图像上的自动肿瘤分割是一个具有挑战性的问题,因为肿瘤具有较大的空间和结构可变性。在这项研究中,提出了一种基于具有多个监督侧输出层(MSFCN)的完全卷积网络的自动肿瘤分割方法。

Background and Objective

Automatic osteosarcoma tumor segmentation on computed tomography (CT) images is a challenging problem, as tumors have large spatial and structural variabilities. In this study, an automatic tumor segmentation method, which was based on a fully convolutional networks with multiple supervised side output layers (MSFCN), was presented.

方法

应用图像归一化作为减少图像之间的差异的预处理步骤。在完全卷积网络的框架中,将监督侧输出层添加到三层,以引导多尺度特征学习作为契约结构,从而能够捕捉局部和全局图像特征。在上采样部分使用多特征通道来捕获更多的背景信息,以确保肿瘤的准确分割,并且在软组织周围对比度较低。将所有侧面输出的结果融合以确定肿瘤的最终边界。

Methods

Image normalization is applied as a pre-processing step for decreasing the differences among images. In the frame of the fully convolutional networks, supervised side output layers were added to three layers in order to guide the multi-scale feature learning as a contracting structure, which was then able to capture both the local and global image features. Multiple feature channels were used in the up-sampling portion to capture more context information, for the assurance of accurate segmentation of the tumor, with low contrast around the soft tissue. The results of all the side outputs were fused to determine the final boundaries of the tumors.

结果

对405例骨肉瘤手工分割结果进行定量比较,平均Dice相似性系数(DSC),平均敏感度,平均Hammoude距离(HM)和F1-measure分别为87.80%,86.88%,19.81%和0.908。与其他学习算法(如全卷积网络(FCN),U-Net方法和整体嵌套边缘检测(HED)方法)相比,MSFCN在DSC,灵敏度,HM和F1-measure方面有着最好的性能。

Results

A quantitative comparison of the 405 osteosarcoma manual segmentation results from the CT images showed that the average Dice similarity coefficient (DSC), average sensitivity, average Hammoude distance (HM) and F1-measure were 87.80%, 86.88%, 19.81% and 0.908, respectively. It was determined that, when compared with the other learning-based algorithms (for example, the fully convolution networks (FCN), U-Net method, and holistically-nested edge detection(HED) method), the MSFCN had the best performances in terms of DSC, sensitivity, HM and F1-measure.

结论

结果表明,该算法有助于快速,准确地描绘肿瘤边界,有助于医生制定更精确的治疗方案。

Conclusions

The results indicated that the proposed algorithm contributed to the fast and accurate delineation of tumor boundaries, which could potentially assist doctors in making more precise treatment plans.

关键词:

卷积神经网络;多重监督网络;骨肉瘤分割

Keywords:

Convolutional neural networks; Multiple supervised networks; Osteosarcoma segmentation

阅读原文:PMID: 28391820  DOI: 10.1016/j.cmpb.2017.02.013


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片