Difference between revisions of "Publications/xu.17.icip.inc"

From LRDE

 
(14 intermediate revisions by the same user not shown)
Line 4: Line 4:
   
 
Architecture of the proposed network. We fine tune it and combine linearly fine to coarse feature maps of the [http://www.robots.ox.ac.uk/~vgg/research/very_deep/ pre-trained VGG network]. The coarsest feature maps are discarded for the adult images.
 
Architecture of the proposed network. We fine tune it and combine linearly fine to coarse feature maps of the [http://www.robots.ox.ac.uk/~vgg/research/very_deep/ pre-trained VGG network]. The coarsest feature maps are discarded for the adult images.
  +
 
[[File:Xu.17.icip-pepeline.png|800 px]]
 
[[File:Xu.17.icip-pepeline.png|800 px]]
   
Line 15: Line 16:
   
 
== Materials ==
 
== Materials ==
  +
  +
=== Trained models ===
  +
The trained models and corresponding files for training for the proposed method on NeoBrainS12 and MRBrainS13 datasets are available in the following:
  +
* Training on Axial images at 40 weeks in NeoBrainS12 dataset are available in this [https://www.lrde.epita.fr/~xu/material/neobrains12_axial40_model.zip archive]
  +
* Training on coronal images at 30 weeks in NeoBrainS12 dataset are available in this [https://www.lrde.epita.fr/~xu/material/neobrains12_coronal30_model.zip archive]
  +
* Training on previous training sets for coronal images at 40 weeks in NeoBrainS12 dataset are available in this [https://www.lrde.epita.fr/~xu/material/neobrains12_coronal40_model.zip archive]
  +
* Training on MRBrainS13 dataset is available in this [https://www.lrde.epita.fr/~xu/material/mrbrains13_model.zip archive]
  +
  +
=== Segmentation results ===
  +
The pre-computed segmentation results of the proposed method on NeoBrainS12 and MRBrainS13 datasets are available in the following:
  +
* Results on Axial images at 40 weeks in NeoBrainS12 dataset are available in this [https://www.lrde.epita.fr/~xu/material/neobrains12_axial40_seg_results.zip archive]
  +
* Results on coronal images at 30 weeks in NeoBrainS12 dataset are available in this [https://www.lrde.epita.fr/~xu/material/neobrains12_coronal30_seg_results.zip archive]
  +
* Results on coronal images at 40 weeks in NeoBrainS12 dataset are available in this [https://www.lrde.epita.fr/~xu/material/neobrains12_coronal40_seg_results.zip archive]
  +
* Results on MRBrainS13 dataset are available in this [https://www.lrde.epita.fr/~xu/material/mrbrains_seg_results.zip archive]
   
 
== Illustrations ==
 
== Illustrations ==
Line 26: Line 41:
 
[[File:xu.17.icip-losoresults.jpg | 800 px]]
 
[[File:xu.17.icip-losoresults.jpg | 800 px]]
   
* Qualitative results on axial images at 40 weeks in NeoBrainS12 dataset
+
* Some results on axial images at 40 weeks in NeoBrainS12 dataset
   
 
<gallery>
 
<gallery>
Line 53: Line 68:
 
</gallery>
 
</gallery>
   
* Qualitative results on coronal at 30 weeks in NeoBrainS12 dataset
+
* Some results on coronal images at 30 weeks in NeoBrainS12 dataset
 
<gallery>
 
<gallery>
 
File:xu.17.icip-coronalTrain108Input.png
 
File:xu.17.icip-coronalTrain108Input.png
Line 79: Line 94:
 
</gallery>
 
</gallery>
   
* Qualitative results on aging adult at 70 ages in MRBrainS13 dataset
+
* Some results on axial images of aging adults at 70 ages in MRBrainS13 dataset
 
<gallery>
 
<gallery>
 
File:Xu.17.icip-mrbrainsTrain513Input.png
 
File:Xu.17.icip-mrbrainsTrain513Input.png
Line 110: Line 125:
 
[[File:Xu.17.icip-axial40results.jpg | 800 px]]
 
[[File:Xu.17.icip-axial40results.jpg | 800 px]]
   
Some qualitative results
+
Some result images
 
<gallery>
 
<gallery>
 
File:Xu.17.icip-axialTest408Input.png
 
File:Xu.17.icip-axialTest408Input.png
Line 128: Line 143:
 
[[File:Xu.17.icip-coronal30results.jpg | 800 px]]
 
[[File:Xu.17.icip-coronal30results.jpg | 800 px]]
   
  +
Some result images (some small errors inside the red circle)
Some qualitative results
 
 
<gallery>
 
<gallery>
 
File:Xu.17.icip-coronal30Test509Input.png
 
File:Xu.17.icip-coronal30Test509Input.png
Line 138: Line 153:
 
File:Xu.17.icip-coronal30Test509Seg.png
 
File:Xu.17.icip-coronal30Test509Seg.png
 
File:Xu.17.icip-coronal30Test517Seg.png
 
File:Xu.17.icip-coronal30Test517Seg.png
File:Xu.17.icip-coronal30Test529Seg.png
+
File:Xu.17.icip-coronal30Test529Seg_circles.png
 
File:Xu.17.icip-coronal30Test540Seg.png
 
File:Xu.17.icip-coronal30Test540Seg.png
 
</gallery>
 
</gallery>
Line 146: Line 161:
 
[[File:Xu.17.icip-coronal40results.jpg | 800 px]]
 
[[File:Xu.17.icip-coronal40results.jpg | 800 px]]
   
  +
Some result images (some small errors inside red circles)
Some qualitative results
 
 
<gallery>
 
<gallery>
 
File:Xu.17.icip-coronal40Test5021Input.png
 
File:Xu.17.icip-coronal40Test5021Input.png
Line 164: Line 179:
 
[[File:Xu.17.icip-adult70results.jpg | 800 px]]
 
[[File:Xu.17.icip-adult70results.jpg | 800 px]]
   
Some qualitative results
+
Some result images
 
<gallery>
 
<gallery>
 
File:Xu.17.icip-mrbrainsTest514Input.png
 
File:Xu.17.icip-mrbrainsTest514Input.png

Latest revision as of 22:04, 6 February 2017

Method and datasets

Method

Architecture of the proposed network. We fine tune it and combine linearly fine to coarse feature maps of the pre-trained VGG network. The coarsest feature maps are discarded for the adult images.

Xu.17.icip-pepeline.png

Datasets

  • Dataset of the MICCAI challenge of Neonatal Brain Segmentation 2012 (NeoBrainS12)
    • Axial images acquired at 40 weeks: 2 training images + 5 test images
    • Coronal images acquired at 30 weeks: 2 training images + 5 test images
    • Coronal images acquired at 40 weeks: 5 test images
  • Dataset of the MICCAI challenge of MR Brain Image Segmentation (MRBrainS13)
    • Axial images acquired at 70 years: 5 training images + 15 test images

Materials

Trained models

The trained models and corresponding files for training for the proposed method on NeoBrainS12 and MRBrainS13 datasets are available in the following:

  • Training on Axial images at 40 weeks in NeoBrainS12 dataset are available in this archive
  • Training on coronal images at 30 weeks in NeoBrainS12 dataset are available in this archive
  • Training on previous training sets for coronal images at 40 weeks in NeoBrainS12 dataset are available in this archive
  • Training on MRBrainS13 dataset is available in this archive

Segmentation results

The pre-computed segmentation results of the proposed method on NeoBrainS12 and MRBrainS13 datasets are available in the following:

  • Results on Axial images at 40 weeks in NeoBrainS12 dataset are available in this archive
  • Results on coronal images at 30 weeks in NeoBrainS12 dataset are available in this archive
  • Results on coronal images at 40 weeks in NeoBrainS12 dataset are available in this archive
  • Results on MRBrainS13 dataset are available in this archive

Illustrations

Experiments

Leave-One-Subject-Out (LOSO) cross-validation on N images + normal training/test experiments. Note that only one training image is used for LOSO 2. Xu.17.icip-experiments.jpg

LOSO experiments

Quantitative results of LOSO experiments in terms of Dice coefficient as compared to the state-of-the-art results. The last one is from P. Moeskops et al. on the 15 test images in MRBrainS13 dataset.

Xu.17.icip-losoresults.jpg

  • Some results on axial images at 40 weeks in NeoBrainS12 dataset
  • Some results on coronal images at 30 weeks in NeoBrainS12 dataset
  • Some results on axial images of aging adults at 70 ages in MRBrainS13 dataset

Neonatal brain MR image segmentation

  • Results on axial images at 40 weeks in NeoBrainS12 dataset. More details can be found Here

Xu.17.icip-axial40results.jpg

Some result images


  • Results on coronal images at 30 weeks in NeoBrainS12 dataset. More details can be found Here

Xu.17.icip-coronal30results.jpg

Some result images (some small errors inside the red circle)


  • Results on coronal images at 40 weeks in NeoBrainS12 dataset. More details can be found Here

Xu.17.icip-coronal40results.jpg

Some result images (some small errors inside red circles)

Adult brain MR image segmentation

  • Results on aging adult images at 70 years in MRBrainS13 dataset. Only top 10 methods among 38 submitted ones are shown. More results and details can be found Here

Xu.17.icip-adult70results.jpg

Some result images