ANTsX/ANTsRNet

Name: ANTsRNet

Owner: Advanced Normalization Tools Ecosystem

Description: Medical image analysis framework merging ANTsR and deep learning

Created: 2018-04-26 21:03:52.0

Updated: 2018-05-22 22:51:13.0

Pushed: 2018-05-22 22:51:12.0

Homepage: null

Size: 180

Language: R

GitHub Committers

User	Most Recent Commit	# Commits

Other Committers

User	Email	Most Recent Commit	# Commits

README

ANTsRNet

A collection of well-known deep learning architectures ported to the R language.

And tools for basic medical image processing.

Examples avaiable at ANTsRNetExamples.

Image segmentation

• U-Net (2-D) or V-Net (3-D) with a multi-label Dice loss function
  • O. Ronneberger, P. Fischer, and T. Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation.
  • Fausto Milletari, Nassir Navab, Seyed-Ahmad Ahmadi. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation.

Image classification

• AlexNet (2-D, 3-D)
  • A. Krizhevsky, and I. Sutskever, and G. Hinton. ImageNet Classification with Deep Convolutional Neural Networks.
• Vgg16/Vgg19 (2-D, 3-D)
  • K. Simonyan and A. Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition.
• ResNet/ResNeXt (2-D, 3-D)
  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep Residual Learning for Image Recognition.
  • Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He. Aggregated Residual Transformations for Deep Neural Networks.
• GoogLeNet (Inception v3) (2-D)
  • C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going Deeper with Convolutions.
• DenseNet (2-D, 3-D)
  • G. Huang, Z. Liu, K. Weinberger, and L. van der Maaten. Densely Connected Convolutional Networks Networks.

Object detection

• Single Shot MultiBox Detector (SSD) (2-D, 3-D)
  • W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C-Y. Fu, and A. Berg. SSD: Single Shot MultiBox Detector.
  • SSD7: small 7-layer architecture
  • SSD300/SSD512: porting of original architectures

Image super-resolution

• Super-resolution convolutional neural network (SRCNN) (2-D, 3-D)
  • Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image Super-Resolution Using Deep Convolutional Networks.
• Expanded super-resolution (ESRCNN) (2-D, 3-D)
  • Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image Super-Resolution Using Deep Convolutional Networks.
• Denoising auto encoder super-resolution (DSRCNN) (2-D, 3-D)
• Deep denoise super-resolution (DDSRCNN) (2-D, 3-D)
• ResNet super-resolution (SRResNet) (2-D, 3-D)
  • Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.
• Python implementations