Difference between revisions of "Publications/xu.17.icip.inc"
From LRDE
Yongchao Xu (talk | contribs) |
Yongchao Xu (talk | contribs) |
||
Line 97: | Line 97: | ||
=== Neonatal brain MR image segmentation === |
=== Neonatal brain MR image segmentation === |
||
+ | * Results on axial images at 40 weeks in NeoBrainS12 dataset. More results can be found [http://neobrains12.isi.uu.nl/mainResults_Set1.php Here] |
||
− | |||
[[File:Xu.17.icip-axial40results.jpg | 800 px]] |
[[File:Xu.17.icip-axial40results.jpg | 800 px]] |
||
+ | Qualitative results |
||
− | |||
− | |||
⚫ | |||
− | |||
− | |||
− | |||
⚫ | |||
− | |||
− | |||
<gallery> |
<gallery> |
||
File:Xu.17.icip-axialTest408Input.png |
File:Xu.17.icip-axialTest408Input.png |
||
Line 121: | Line 113: | ||
</gallery> |
</gallery> |
||
+ | |||
+ | * Results on coronal images at 30 weeks in NeoBrainS12 dataset. More results can be found [http://neobrains12.isi.uu.nl/mainResults_Set2.php Here] |
||
⚫ | |||
+ | |||
+ | Qualitative results |
||
<gallery> |
<gallery> |
||
File:Xu.17.icip-coronal30Test509Input.png |
File:Xu.17.icip-coronal30Test509Input.png |
||
Line 133: | Line 130: | ||
</gallery> |
</gallery> |
||
+ | |||
+ | * Results on coronal images at 40 weeks in NeoBrainS12 dataset. More results can be found [http://neobrains12.isi.uu.nl/mainResults_Set3.php Here] |
||
⚫ | |||
+ | |||
+ | Qualitative results |
||
<gallery> |
<gallery> |
||
File:Xu.17.icip-coronal40Test5021Input.png |
File:Xu.17.icip-coronal40Test5021Input.png |
Revision as of 12:00, 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.
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
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.
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.
- Qualitative results on axial images at 40 weeks in NeoBrainS12 dataset
- Qualitative results on coronal at 30 weeks in NeoBrainS12 dataset
- Qualitative results on aging adult at 70 ages in MRBrainS13 dataset
Neonatal brain MR image segmentation
- Results on axial images at 40 weeks in NeoBrainS12 dataset. More results can be found Here
Qualitative results
- Results on coronal images at 30 weeks in NeoBrainS12 dataset. More results can be found Here
Qualitative results
- Results on coronal images at 40 weeks in NeoBrainS12 dataset. More results can be found Here
Qualitative results
Adult brain MR image segmentation