Deep Convolutional Gaussian Mixture Model for Stain-Color Normalization in Histopathological H&E Images. The TensorFlow GPU implementation.
Stain-color variation degrades the performance of the computer-aided diagnosis (CAD) systems. In the presence of severe color variarion between training set and test set in histopathological images, current CAD systems including deep learning models suffer from such an undesirable effect. Stain-color normalization is known as a remedy.
Stain-color normalization model can be defined as a generative models that by applying on input image can create different color copies of input image to somehow the converted image contain specific chromatic distribution. Our proposed method contains two stage: (1) Fitting a Gaussian mixture model (GMM) by considering the shape and apearance of image content structures. To do so the visual representation and modeling of convolutional neyral networks (CNNs) are exploited. (2) transforming the estimated distribution to any arbitary distribution that computed from a secondary (template) image.
*The tissue class membership, computed by the standard GMM algorithm (middle) and the DCGMM (right); Clusters include nuclei (red), surrounding tissues (green) and the background(blue).*
Template image
Stain-color conversion
==> ==> ==>
For evaluating the algorithm, CAMELYON17 dataset can be used.
If you find DCGMM useful in your research, please consider citing:
Stian-color normalization by using DCGMM is released under the free GNU license.
This work was done as a part of 3DPathology project and has been funded by ITEA3 (Grant number: ITEA151003).