MaMedIS

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

StainGAN?: Stain style transfer for digital histological images

Supervision: Prof. Dr. Nassir Navab, Shadi Albarqouni, Christoph Baur

Abstract

Digitized Histopathological diagnosis is in increasing demand, but stain color variations due to stain preparation, differences in raw materials, manufacturing techniques of stain vendors and use of different scanner manufacturers are imposing obstacles to the diagnosis process. The problem of stain variations is a well-defined problem with many proposed methods to overcome it each depending on the reference slide image to be chosen by a pathologist expert. We propose a deep-learning solution to that problem based on the Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks eliminating the need for an expert to pick a representative reference image. Our approach showed promising results that we compare quantitatively and quantitatively against the state of the art methods.

Tasks:

  • Understand GANs
  • Transfer the knowledge to Medical Image Synthesis
  • Validate the proposed algorithm on clinical data

Requirements:

  • Good understanding of medical physics
  • Good understanding of statistics and machine learning methods.
  • Very good programming skills in Python & TensorFlow? / pyTorch

Location:

  • Garching

Literature

[1] Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y., 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems (pp. 2672-2680).
[2] Denton, E.L., Chintala, S. and Fergus, R., 2015. Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks. In Advances in neural information processing systems (pp. 1486-1494).
[3] Nie, D., Trullo, R., Petitjean, C., Ruan, S. and Shen, D., 2016. Medical Image Synthesis with Context-Aware Generative Adversarial Networks. arXiv preprint arXiv:1612.05362.
[4] Havaei, M., Guizard, N., Chapados, N. and Bengio, Y., 2016, October. HeMIS: Hetero-Modal Image Segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) (pp. 469-477).
[5] Wiggermann, V., Hernández-Torres, E., Traboulsee, A., Li, D.K.B. and Rauscher, A., 2016. FLAIR2: A combination of FLAIR and T2 for improved MS lesion detection. American Journal of Neuroradiology, 37(2), pp.259-265.

Resultant Paper


ProjectForm
Title: StainGAN?: Stain style transfer for digital histological images
Abstract: Digitized Histopathological diagnosis is in increasing demand, but stain color variations due to stain preparation, differences in raw materials, manufacturing techniques of stain vendors and use of different scanner manufacturers are imposing obstacles to the diagnosis process. The problem of stain variations is a well-defined problem with many proposed methods to overcome it each depending on the reference slide image to be chosen by a pathologist expert. We propose a deep-learning solution to that problem based on the Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks eliminating the need for an expert to pick a representative reference image. Our approach showed promising results that we compare quantitatively and quantitatively against the state of the art methods.
Student: M. Tarek Shaban
Director: Prof. Dr. Nassir Navab
Supervisor: Shadi Albarqouni, Christoph Baur
Type: Master Thesis
Area: Machine Learning, Medical Imaging
Status: running
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.9 - 19 Feb 2018 - 16:41 - ShadiAlbarqouni