Data

Tools

Indexes

Applications

Experiments

Open Source Science

spark_bts_kifaru

MICCA_BRATS_Africa_2023 Kifaru Team: Generative Style Transfer for MR Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa

https://github.com/btskifaru/spark_bts_kifaru

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

MICCA_BRATS_Africa_2023 Kifaru Team: Generative Style Transfer for MR Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa

Basic Info
  • Host: GitHub
  • Owner: BTSKifaru
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 17.5 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Generative Style Transfer for MR Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa

Abstract. In Sub-SaharanAfrica (SSA), the utilization of lower-quality Magnetic Resonance Imaging (MRI) technology raises questions about the applicability of machine learning (ML) methods for clinical tasks. This study aims to provide a robust deep learning-based brain tumor segmentation (BraTS) method tailored for the SSA population using a threefold approach. Firstly, the impact of domain shift from the SSA training data on model efficacy was examined, revealing no significant effect.Secondly, a comparative analysis of 3D and 2D full-resolution models using the nnU-Net framework indicates similar performance of both the models trained for 300 epochs achieving a five-fold cross-validation score of 0.93. Lastly, addressing the performance gap observed in SSA validation as opposed to the relatively larger BraTS glioma (GLI) validation set, two strategies are proposed: fine-tuning SSA cases using the GLI + SSA best-pretrained 2D fullres model at 300 epochs, and introducing a novel neural style transfer-based data augmentation technique for the SSA cases. This investigation underscores the potential of enhancing brain tumor prediction within SSA’s unique healthcare landscape.

Keywords: Brain Tumor Segmentation · Neural style transfer · nnU-Net

Alt text

Citation

If you use this research and/or software, please cite it using the following:

```bibtex @article{Chepchirchir2025GenerativeStyleTransfer, author = {Chepchirchir, Rancy and Sunday, Jill and Confidence, Raymond and Zhang, Dong and Chaudhry, Talha and Annazodo, Udunna and Muchungi, Kendi and Zou, Yujing}, title = {Generative Style Transfer for MR Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa}, year = {2025}, month = {January}, version = {1.0.0}, doi = {XXX}, url = {https://github.com/BTSKifaru/SPARKBTSKIFARU.git}, }

Owner

  • Name: BTSKifaru
  • Login: BTSKifaru
  • Kind: organization

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software or research work, please consider citing it as below."
authors:
- family-names: "Chepchirchir"
  given-names: "Rancy"
- family-names: "Sunday"
  given-names: "Jill"
- family-names: "Confidence"
  given-names: "Raymond"
- family-names: "Zhang"
  given-names: "Dong"
- family-names: "Chaudhry"
  given-names: "Talha"
- family-names: "Annazodo"
  given-names: "Udunna"
- family-names: "Muchungi"
  given-names: "Kendi"
- family-names: "Zou"
  given-names: "Yujing"
title: "Generative Style Transfer for MR Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa"
version: 1.0.0
date-released: 2025-01-02
doi: "XXX"
url: "https://github.com/BTSKifaru/SPARK_BTS_KIFARU.git"

GitHub Events

Total
  • Member event: 1
  • Public event: 1
  • Push event: 3
Last Year
  • Member event: 1
  • Public event: 1
  • Push event: 3

Dependencies

Optimized U-Net_BTS/Dockerfile docker
  • ${FROM_IMAGE_NAME} latest build
Optimized U-Net_BTS/requirements.txt pypi
  • joblib ==1.0.1
  • nibabel ==3.2.1
  • pytorch-lightning ==1.7.7
  • rich ==12.5.0
  • scikit-image ==0.18.3
  • scikit-learn ==1.0
  • scipy ==1.8.1
Optimized U-Net_BTS/triton/requirements.txt pypi
  • PyYAML >=5.2
  • natsort >=7.0.0
  • networkx ==2.5
  • onnx ==1.8.0
  • onnxruntime ==1.5.2
  • pycuda >=2019.1.2
  • tabulate >=0.8.7
  • tqdm >=4.44.1