二维码（扫一下试试看！） | | 基于生成对抗网络的海马子区图像分割 | | Image Segmentation of Hippocampal Subfields with Generative Adversarial Networks | | 投稿时间：2018-10-20 | | DOI：10.15918/j.tbit1001-0645.2019.s1.029 | | 中文关键词:海马子区分割生成对抗网络卷积神经网络图像分割 | | English Keywords:hippocampal subfields segmentationgenerative adversarial networks (GAN)convolution neural network (CNN)image segmentation | | 基金项目:国家自然科学基金资助项目（60971133，61271112） | | | 摘要点击次数:4114 | | 全文下载次数:371 | | 中文摘要: | | 海马子区体积很小且结构复杂，传统分割方法无法达到理想分割效果，为此引入生成对抗网络模型用于海马子区图像分割.该方法构建一个生成对抗网络模型，通过构建生成网络和对抗网络并对其进行交替对抗训练实现对脑部海马子区图像的像素级精确分割.实验选取美国旧金山CIND中心的32位实验者的脑部MRI图像进行海马子区分割测试，在定性和定量方面分别对比了所提方法基于稀疏表示与字典学习方法和传统CNN的分割结果.实验结果表明，该方法优于基于稀疏表示与字典学习和CNN方法，海马子区分割准确率有较大提升.该方法提升了海马子区的分割准确率，可用于大脑核磁图像中海马子区的分割，为诸多神经退行性疾病的临床诊断与治疗提供依据. | | English Summary: | | Attribute to the small structures and the morphological complexity of the hippocampal subfields, it is hard to obtain desirable segmentation results with the traditional segmentation methods. Therefore,we introduce generative adversarial networks into image segmentation of hippocampal subfields. The introduced method can achieve the pixel-level segmentation of brain MR images. The generative model and the adversarial model are trained alternately. The approach was tested based on the brain MRI images of 32 volunteers from the CIND Center in San Francisco, USA. It was compared quantitatively and qualitatively with methods based on the sparse representation and dictionary learning and CNN. The results showed that the proposed method, which achieved a significant improvement in the segmentation accuracy of the hippocampal subfields, outperforms the existing methods based on the dictionary learning and sparse representation and CNN. The results reveal that the introduced method can effectively improve the segmentation accuracy of hippocampal subfields in the brain MRI images, which will provide the basis for the clinical diagnosis and treatment of neurodegenerative diseases. | | 查看全文查看/发表评论下载PDF阅读器 | |
胡东海,何仁,徐晓明,衣丰艳.电子液压制动系统耗能特性影响因素分析[J].北京理工大学学报（自然科学版）,2018,38(3):261~266.HUDong-hai,HERen,XUXiao-ming,YIFeng-yan.AnalysisonInfluencingFactorsofEnergyCo ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21宁志刚,郝光鹏,程雄,沈文斌,丁德馨.基于图像分析的堆浸铀矿石颗粒参数辨识[J].北京理工大学学报（自然科学版）,2018,38(3):300~304,312.NINGZhi-gang,HAOGuang-peng,CHENGXiong,SHENWen-bin,DINGDe-xin.Parameter ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21邬春明,郑宏阔,王艳娇,付饶,于明,孙勇.基于多节点协作的WMSNs图像压缩算法[J].北京理工大学学报（自然科学版）,2018,38(5):545~550.WUChun-ming,ZHENGHong-kuo,WANGYan-jiao,FURao,YUMing,SUNYong.AImageCompr ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21高绍姝,张晓东,金伟其.可见光与红外灰度融合图像感知对比度客观评价[J].北京理工大学学报（自然科学版）,2018,38(7):715~720.GAOShao-shu,ZHANGXiao-dong,JINWei-qi.PerceptualContrastMetricforVisibleandInfr ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21刘帅奇,扈琪,李喆,安彦玲,李鹏飞,赵杰.基于相似性验证与子块排序的NSST域SAR图像去噪[J].北京理工大学学报（自然科学版）,2018,38(7):744~751.LIUShuai-qi,HUQi,LIZhe,ANYan-ling,LIPeng-fei,ZHAOJie.SARImageDeno ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21.北京理工大学学报2018年总目次（第38卷）[J].北京理工大学学报（自然科学版）,2018,38(12):1321~1338..[J].TransactionsofBeijingInstituteofTechnology,2018,38(12):1321-1338.二维码（扫一下试试看！）北京理 ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21王晓华,许雪,王卫江,高东红.一种稀疏度拟合的图像自适应压缩感知算法[J].北京理工大学学报（自然科学版）,2017,37(1):88~92.WANGXiao-hua,XUXue,WANGWei-jiang,GAODong-hong.ANovelAlgorithmonAdaptiveImageCom ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21郑凤,陈艺戬.基于多径的双极化信道信息反馈方法[J].北京理工大学学报（自然科学版）,2017,37(4):365~370.ZHENGFeng,CHENYi-jian.CSIFeedbackBasedonMulti-PathsInformationinDual-PolarizedMIMOSystem ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21强彦,张晓慧.车载手势识别中基于小波变换和双边滤波的图像去噪方法[J].北京理工大学学报（自然科学版）,2017,37(4):376~380.QIANGYan,ZHANGXiao-hui.ImageDenoisingMethodBasedonWaveletTransformandBilateralF ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21张真宁,孙华飞,韩希武,曹丽梅.晶粒直径的信息几何结构[J].北京理工大学学报（自然科学版）,2017,37(4):436~440.ZHANGZhen-ning,SUNHua-fei,HANXi-wu,CAOLi-mei.TheInformationGeometricStructuresoftheS ... 北京理工大学科研学术 本站小编 Free考研考试 2021-12-21
| |
