需要读的论文
最先进的模块
模块：skip connections
Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J., 2018b. Unet++: A nested u-net architecture for medical image segmentation, in: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Springer, pp. 3–11.
论文：https://arxiv.org/pdf/1807.10165.pdf
GitHub：https://github.com/MrGiovanni/UNetPlusPlus
pytorch：https://github.com/4uiiurz1/pytorch-nested-unet
模块：residual convolution blocks
Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., Asari, V.K., 2018. Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv preprint arXiv:1802.06955 .
论文：https://arxiv.org/ftp/arxiv/papers/1802/1802.06955.pdf
pytorch: https://github.com/LeeJunHyun/Image_Segmentation
论文翻译：R2U-Net for medical image segmentation
RCL: 递归卷积神经网络(RCNN)
模块：稠密卷积块
Li, X., Chen, H., Qi, X., Dou, Q., Fu, C.W., Heng, P.A., 2018. H-denseunet:hybrid densely connected unet for liver and tumor segmentation from ct volumes. IEEE transactions on medical imaging 37, 2663–2674.
论文：https://arxiv.org/pdf/1709.07330.pdf
Github:https://github.com/xmengli999/H-DenseUNet
论文解读: 多任务分割(器官、病变)——H-DenseUNet
论文翻译：https://blog.csdn.net/qq_38565134/article/details/90266969
Denset
论文翻译:https://www.cnblogs.com/zhhfan/p/10187634.html
模块：注意力机制
Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K.,Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., Glocker, B., Rueckert, D., 2018. Attention U-Net: Learning Where to Look for the Pancreas.2018 CVPR
论文：https://arxiv.org/pdf/1804.03999.pdf
论文解读：https://www.jianshu.com/p/3c920bc316f9
GitHub-PyTorch：：https://github.com/ozan-oktay/Attention-Gated-Networks
模块：混合挤压激励模块
Roy, A.G., Navab, N., Wachinger, C., 2018. Concurrent spatial and channel squeeze & excitationin fully convolutional networks, in: International Conference on Medical Image Computing and Computer-Assisted Intervention,Springer. pp. 421–429.2018 CVPR
论文：https://arxiv.org/pdf/1803.02579.pdf
论文解读：https://www.jianshu.com/p/b0cc2b73f515
综述
GANs在医学影像中的应用
Yi, X., Walia, E., Babyn, P., 2018. Generative adversarial network in medical imaging: A review. arXiv preprint arXiv:1809.07294
医学图像分割的架构改进
Hesamian, M.H., Jia, W., He, X., Kennedy, P., 2019. Deep learning techniques for medical image segmentation: Achievements and challenges. Journal of digital imaging , 1–15.
医学图像分割中的小样本问题
Zhang, P., Zhong, Y., Deng, Y., Tang, X., Li, X., 2019b. A survey on deep learning of small sample in biomedical image analysis. arXiv preprint arXiv:1908.00473 .
数据增强
传统增强
医学成像中使用的数据增强方法可以按照他们打算操纵的图像属性进行分组
Zhang, L., Wang, X., Yang, D., Sanford, T., Harmon, S., Turkbey, B., Roth,H., Myronenko, A., Xu, D., Xu, Z., 2019a. When unseen domain generalization is unnecessary? rethinking data augmentation. arXiv preprint arXiv:1906.03347
图像属性：图像质量、图像外观和图像布局。
图像质量：与二维自然图像的数据增强类似，图像质量也会受到锐度、模糊度和噪声的影响。
将高斯噪声应用于CT扫描，作为数据增强的一部分
Christ, P.F., Elshaer, M.E.A., Ettlinger, F., Tatavarty, S., Bickel, M., Bilic, P.,Rempfler, M., Armbruster, M., Hofmann, F., D’Anastasi, M., et al., 2016.Automatic liver and lesion segmentation in ct using cascaded fully convolutional neural networks and 3d conditional random fields, in: MICCAI, Springer. pp. 415–423.
采用高斯模糊对结肠组织图像进行腺体分割
Sirinukunwattana, K., Pluim, J.P., Chen, H., Qi, X., Heng, P.A., Guo, Y.B.,Wang, L.Y., Matuszewski, B.J., Bruni, E., Sanchez, U., et al., 2017. Gland segmentation in colon histology images: The glas challenge contest. Medical image analysis 35, 489–502.
通过调整图像质量进行数据增强，可以使得MR图像中的性能增益最大，而最大的性能提升来自于通过应用非锐化掩模进行图像锐化。
Zhang, L., Wang, X., Yang, D., Sanford, T., Harmon, S., Turkbey, B., Roth,H., Myronenko, A., Xu, D., Xu, Z., 2019a. When unseen domain generalization is unnecessary? rethinking data augmentation. arXiv preprint arXiv:1906.03347 .
图像外观：通过调整图像外观实现的数据增强是指操纵图像亮度、饱和度和对比度等强度的统计特征。
在视网膜血管分割之前，对HSV颜色空间的饱和度和值进行伽玛校正。
Liskowski, P., Krawiec, K., 2016. Segmenting retinal blood vessels with deep neural networks. IEEE transactions on medical imaging 35, 2369–2380.
在3D磁共振体积中随机增强亮度--大脑
Dong, H., Yang, G., Liu, F., Mo, Y., Guo, Y., 2017. Automatic brain tumor detection and segmentation using u-net based fully convolutional networks, in:annual conference on medical image understanding and analysis, Springer.pp. 506–517.
当图像显示出不均匀的强度时，对比度增强通常是有帮助的
对荧光显微图像应用对比度变换函数来丰富数据集，以丰富细胞核分割任务的数据集
Fu, C., Ho, D.J., Han, S., Salama, P., Dunn, K.W., Delp, E.J., 2017. Nuclei segmentation of fluorescence microscopy images using convolutional neural networks, in: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), IEEE. pp. 704–708.
将直方图匹配作为一种预处理形式，将3D MR图像与训练数据中任意选择的参考图像进行匹配。--大脑
Alex, V., Vaidhya, K., Thirunavukkarasu, S., Kesavadas, C., Krishnamurthi,G., 2017. Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation. Journal of Medical Imaging 4, 041311.
图像布局：改变图像布局的数据扩充由旋转、缩放和变形等空间变换组成。
增加随机弹性变形的训练集是训练很少带注释图像的分割网络的关键。
Ronneberger, O., Fischer, P., Brox, T., 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 [cs] URL: http://arxiv.org/abs/1505.04597. a
通过2x2x2的控制点网格和b样条插值对训练图像应用了密集变形场。
Milletari, F., Navab, N., Ahmadi, S.A., 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation, in: 2016 Fourth International Conference on 3D Vision (3DV), IEEE. pp. 565–571.
首先从一个正态分布的网格中抽取随机向量，每个方向的间距为32个体素，然后应用b样条插值。
C¸ ic¸ek, O., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O., 2016. 3d u-net: learning dense volumetric segmentation from sparse annotation,in: International conference on medical image computing and computerassisted intervention, Springer. pp. 424–432.
