Skip to content
master
Switch branches/tags
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 

SIMBA: Specific Identity Markers for Bone Age Assessment

¡We released a new version of the Bone Age Assessment Resources!

Follow this link to find the updated webpage with new methods, curated datasets and an evaluation server with a public leaderboard for fair comparison of Bone Age Assessment algorithms.

This repository provides a PyTorch implementation of SIMBA, presented in the paper SIMBA: Specific Identity Markers for Bone Age Assessment. Presented at MICCAI,2020. SIMBA is a novel approach for the task of BAA based on the use of identity markers. For this purpose, we build upon the state-of-the-art model, fusing the information present in the identity markers with the visual features created from the original hand radiograph. We then use this robust representation to estimate the patient’s relative bone age: the difference between chronological age and bone age.

Paper

SIMBA: Specific Identity Markers for Bone Age Assessment
Cristina González 1* , María Escobar 1* ,Laura Daza1,Felipe Torres 1, Gustavo Triana2, Pablo Arbeláez1
*Equal contribution.
1 Center for Research and Formation in Artificial Intelligence (CINFONIA) , Universidad de Los Andes.
2 Radiology department, Fundación Santa Fe de Bogotá.

Dependencies

  • Pytorch 1.3.1
  • Pandas 1.0.1
  • Horovod 0.19.1
  • Tqdm 4.42.1
  • Scipy 1.3.2

Usage

Cloning the repository

$ git clone https://github.com/BCV-Uniandes/SIMBA.git
$ cd simba

Train setup:

Modify the routes in train_net.sh according to your local paths. Use the flags for training the different versions of SIMBA.

bash train_net.sh

Test setup:

Modify the routes in test_net.sh according to your local paths. Use the flags for evaluating the different versions of SIMBA.

bash test_net.sh

Pretrained models

Gender multiplier Chronological age multiplier Relative bone age Subset MAD Pretrained model
x x Validation 6.50 model1
x x Validation 8.72 model2
x x Validation 7.33 model3
x x x Validation 6.34 model4
x x x Test 5.47 model5

Citation

@inproceedings{gonzalez2020simba,
  title={SIMBA: Specific Identity Markers for Bone Age Assessment},
  author={Gonz{\'a}lez, Cristina and Escobar, Mar{\'\i}a and Daza, Laura and Torres, Felipe and Triana, Gustavo and Arbel{\'a}ez, Pablo},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
  pages={753--763},
  year={2020},
  organization={Springer}
}

About

Pytorch implementation of the MICCAI 2020 paper SIMBA: Specific Identity Markers for Bone Age Assessment

Topics

Resources

License

Releases

No releases published

Packages

No packages published