MICCAI-iseg2017挑战赛小结与婴儿脑组织分割总结

按照数据集进行划分:

关于自动分割工具,婴儿脑MR图像来自单个时间点,其中纵向数据集不可用,因此必须开发不针对纵向数据集的分割工具,目前提出了一些机器学习方法,但这些方法的效果并不令人满意。

iseg-2017:

竞赛结果一共评估了两次,第一次评估中的TOP-1为MSL_SKKU,第二次评估中降为了第二名,但由于第二次评估的时间较晚,因此已发表的论文大多与第一次评估中的冠军作对比,在以下的总结中,把第一次评估的第一名作为挑战赛的冠军。

第二次评估结果入下:

第二次评估结果

MICCAI iseg-2017挑战赛结果:  第一名为MSL_SKKU

DICE、MHD、ASD

 

DICE结果排名如下:

三项分割标签各自的DICE排名

 

MHD排名结果如下: 

3项分割标签各自的MHD排名

 

ASD排名结果如下:

3项分割标签各自的ASD排名

 

 

前五名的结果为:

top-5

 

与数据集相关的论文:

Bui T D, Shin J, Moon T. 3d densely convolution networks for volumetric segmentation[J]. arXiv preprint arXiv:1709.03199, 2017. 

 ---10引用   采用DenseNet    挑战赛中排名第一   队伍名:MSL-SKKU

取小数点后3位的情况下9项指标6项第一


Dolz J, Desrosiers C, Wang L, et al. Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation[J]. arXiv preprint arXiv:1712.05319, 2017.       

  ---6引用   采用SemiDenseNet   在某些指标中排名第一或者第二,结果如下:

 


Dolz J, Ayed I B, Yuan J, et al. Isointense infant brain segmentation with a hyper-dense connected convolutional neural network[C]//Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on. IEEE, 2018: 616-620. 

  ---3引用   采用DenseNet   9个指标中6个排名前三

该文章基于另外两篇文章:

 Konstantinos Kamnitsas et al., "Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation", Medical image analysis, vol. 36, pp. 61-78, 2017. 

Jose Dolz et al., "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study", NeuroImage, 2017.

 


Dolz J, Gopinath K, Yuan J, et al. HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation[J]. arXiv preprint arXiv:1804.02967, 2018.

 

iseg-2017

 

取小数点后两位的情况下,都为9项指标7项第一

对于MRBrainS2013:

MRBrainS2013

提交时间为18.02.16,提交时为第一名,目前排名第6,对比结果如下:

HyperDenseNet(top-6)0.86331.346.190.89461.786.030.83422.267.31
XMU_SmartDSP2(top-1)0.8651.295.750.8991.735.4784.81.846.83

Dolz J, Ayed I B, Yuan J, et al. HyperDense-Net: A hyper-densely connected CNN for multi-modal image semantic segmentation[J]. arXiv preprint arXiv:1710.05956, 2017.

  ---未了解(上一篇的效果较好)


Fonov V, Doyle A, Evans A C, et al. NeuroMTL iSEG challenge methods[J]. bioRxiv, 2018: 278465.

  ---排名较靠前   队伍名:NeuroMTL


Sanroma G, Benkarim O M, Piella G, et al. Learning to combine complementary segmentation methods for fetal and 6-month infant brain MRI segmentation[J]. Computerized Medical Imaging and Graphics, 2018, 69: 52-59.   

  ---非顶会,效果不好但拿不到数据集


Zeng G, Zheng G. Multi-stream 3D FCN with multi-scale deep supervision for multi-modality isointense infant brain MR image segmentation[C]//Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on. IEEE, 2018: 136-140.  

  ---排名第三 队伍名:Bern_IPMI  采用FCN 


Wang Z, Zou N, Shen D, et al. Global Deep Learning Methods for Multimodality Isointense Infant Brain Image Segmentation[J]. arXiv preprint arXiv:1812.04103, 2018.

-----预印本,目前最新效果最好的的论文(WM与GM为最佳性能,CSF具有可比性),提交时间为2018.12.10,未参与挑战赛排名,实验结果为:

 WMGMCSF
top-10.9010.9190.958
论文0.90440.92190.9557

Li T, Zhou F, Zhu Z, et al. A label-fusion-aided convolutional neural network for isointense infant brain tissue segmentation[C]//Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on. IEEE, 2018: 692-695. 

使用的数据集为 iseg-2017,使用的网络为FCNN,实验结果接近第一名,实验结果如下:

CSF指标相同

Kumar S, Conjeti S, Roy A G, et al. InfiNet: Fully convolutional networks for infant brain MRI segmentation[C]//Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on. IEEE, 2018: 145-148. 

数据集来源于BCP项目,该数据集作为iseg-2017挑战赛数据集的一部分(总数,训练测试集数一样),结果比挑战赛TOP-1低2%,但参数减半。

3D-DenseNet为挑战赛第一名的结果

推荐的文章为:但3篇文章都为预印本

1.Bui T D, Shin J, Moon T. 3d densely convolution networks for volumetric segmentation[J]. arXiv preprint arXiv:1709.03199, 2017. 

 ---10引用   采用DenseNet    挑战赛中排名第一   队伍名:MSL-SKKU

取小数点后3位的情况下9项指标6项第一

2.Dolz J, Gopinath K, Yuan J, et al. HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation[J]. arXiv preprint arXiv:1804.02967, 2018.

--取小数点后2为的情况下都为9项指标7项第一

3.Wang Z, Zou N, Shen D, et al. Global Deep Learning Methods for Multimodality Isointense Infant Brain Image Segmentation[J]. arXiv preprint arXiv:1812.04103, 2018.

-----预印本,目前最新效果最好的的论文(WM与GM为最佳性能,CSF具有可比性),提交时间为2018.12.10,未参与挑战赛排名


 

NDAR数据集

Wang L, Li G, Shi F, et al. Volume-based analysis of 6-month-old infant brain MRI for autism biomarker identification and early diagnosis[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2018: 411-419.

采用U-Net,数据集来源于NDAR,包含18名受试者,分割结果很好------未找到数据集

分割结果

 


neobrains(类别较多)--相关文章较少

第一名排名结果如下(在大多数指标中排名第一)提交时间为2018.09

在40周矫正年龄时获得轴向扫描

 CoGMUMWCSFVentCBBSBGTMWMUWM+MWMCSF+Vent
DC0.890.940.850.900.950.860.940.53(2)0.93(3)0.85
MSD0.10.090.160.140.260.240.300.600.100.16
HD18.7910.578.6613.7616.407.1319.849.197.838.27

在30周矫正年龄时获得冠状位扫描

 CoGMUWMCSFVentCBBSBGTMWMUMW+MWMSCF+Vent
DC0.790.950.890.870.910.840.89-0.950.91
MSD0.140.140.130.330.300.370.42-0.140.10
HD13.819.166.4313.697.097.547.98-9.994,96

在40周矫正年龄时获得冠状位扫描

 CoGMUWMCSFVentCBBSBGTMWMUWM+MWMCSF+Vent
DC0.790.910.820.820.890.680.860.040.910.83
MSD0.210.180.300.410.651.130.987.070.220.28
HD27.2024.0012.8615.4226.1815.1525.9127.9213.7512.52

使用了该数据集的部分文章:

 

 


 

其他

1.Nie D, Wang L, Adeli E, et al. 3-D fully convolutional networks for multimodal isointense infant brain image segmentation[J]. IEEE Transactions on Cybernetics, 2018.    1区

2.Bernal J, Kushibar K, Cabezas M, et al. Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging[J]. arXiv preprint arXiv:1801.06457, 2018.

 3.Chen J, Zhang H, Nie D, et al. Automatic accurate infant cerebellar tissue segmentation with densely connected convolutional network[C]//International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 2018: 233-240.

MICCAI挑战赛底部文章:

[1]. Li Wang, Yaozong Gao, Feng Shi, Gang Li, John H. Gilmore, Weili Lin, Dinggang Shen. LINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images, Neuroimage, 108, 160-172, 2015.
[2]. Li Wang, Feng Shi, Yaozong Gao, Gang Li, John H. Gilmore, Weili Lin, Dinggang Shen. Integration of Sparse Multi-modality Representation and Anatomical Constraint for Isointense Infant Brain MR Image Segmentation, Neuroimage, 89, 152-164, 2014.
[3]. Wenlu Zhang, Rongjian Li, Houtao Deng, Li Wang, Weili Lin, Shuiwang Ji, Dinggang Shen. Deep Convolutional Neural Networks for Multi-Modality Isointense Infant Brain Image Segmentation, Neuroimage, 108, 214–224, 2015.

综述文章:

Li G, Wang L, Yap P T, et al. Computational neuroanatomy of baby brains: A review[J]. Neuroimage, 2018.    

  ---引用9    综述文章

A review on automatic fetal and neonatal brain MRI segmentation

  ---综述文章

Convolutional Neural Networks for Rapid and Simultaneous Brain Extraction and Tissue Segmentation   书籍

 

 

 

 

 

 

 

 

 

 

 

 

 

 

吃鸡加我:360258904

  • 3
    点赞
  • 14
    收藏
    觉得还不错? 一键收藏
  • 14
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 14
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值