Unsupervised Deep Learning Method for Bias Correction

Maria Perez-Caballero; Sergio Morell-Ortega; Marina Ruiz Perez; Pierrick Coupe; Jose V Manjon

Unsupervised Deep Learning Method for Bias Correction

Maria Perez-Caballero, Sergio Morell-Ortega, Marina Ruiz Perez, Pierrick Coupe, Jose V Manjon

Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1098-1106, 2024.

Abstract

In this paper, a new method for automatic MR image inhomogeneity correction is proposed. This method, based on deep learning, uses unsupervised learning to estimate the bias corrected images minimizing a cost function based on the entropy of the corrupted image, the derivative of the estimated bias field and corrected image statistics. The proposed method has been compared with the state-of-the-art method N4 providing improved results.

Cite this Paper

BibTeX

@InProceedings{pmlr-v250-perez-caballero24a,
  title = 	 {Unsupervised Deep Learning Method for Bias Correction},
  author =       {Perez-Caballero, Maria and Morell-Ortega, Sergio and Perez, Marina Ruiz and Coupe, Pierrick and Manjon, Jose V},
  booktitle = 	 {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning},
  pages = 	 {1098--1106},
  year = 	 {2024},
  editor = 	 {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana},
  volume = 	 {250},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {03--05 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://raw.githubusercontent.com/mlresearch/v250/main/assets/perez-caballero24a/perez-caballero24a.pdf},
  url = 	 {https://proceedings.mlr.press/v250/perez-caballero24a.html},
  abstract = 	 {In this paper, a new method for automatic MR image inhomogeneity correction is proposed. This method, based on deep learning, uses unsupervised learning to estimate the bias corrected images minimizing a cost function based on the entropy of the corrupted image, the derivative of the estimated bias field and corrected image statistics. The proposed method has been compared with the state-of-the-art method N4 providing improved results.}
}

Endnote

%0 Conference Paper
%T Unsupervised Deep Learning Method for Bias Correction
%A Maria Perez-Caballero
%A Sergio Morell-Ortega
%A Marina Ruiz Perez
%A Pierrick Coupe
%A Jose V Manjon
%B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning
%C Proceedings of Machine Learning Research
%D 2024
%E Ninon Burgos
%E Caroline Petitjean
%E Maria Vakalopoulou
%E Stergios Christodoulidis
%E Pierrick Coupe
%E Hervé Delingette
%E Carole Lartizien
%E Diana Mateus	
%F pmlr-v250-perez-caballero24a
%I PMLR
%P 1098--1106
%U https://proceedings.mlr.press/v250/perez-caballero24a.html
%V 250
%X In this paper, a new method for automatic MR image inhomogeneity correction is proposed. This method, based on deep learning, uses unsupervised learning to estimate the bias corrected images minimizing a cost function based on the entropy of the corrupted image, the derivative of the estimated bias field and corrected image statistics. The proposed method has been compared with the state-of-the-art method N4 providing improved results.

APA

Perez-Caballero, M., Morell-Ortega, S., Perez, M.R., Coupe, P. & Manjon, J.V.. (2024). Unsupervised Deep Learning Method for Bias Correction. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1098-1106 Available from https://proceedings.mlr.press/v250/perez-caballero24a.html.

Related Material

Download PDF