Authors:
Jia Li
1
;
2
;
Junling He
3
;
Jingmin Long
1
;
Chenxu Wang
2
;
Jesper Kers
3
and
Fons Verbeek
1
Affiliations:
1
Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands
;
2
School of Computer Science, Xi’an Jiaotong University, Beilin, Xi’an, China
;
3
Leiden University Medical Center, Leiden, The Netherlands
Keyword(s):
Tissue Segmentation, Foreground Extraction, U-Net, Whole Slide Image.
Abstract:
In recent years, computational pathology is rapidly developing. This resulted in various artificial intelligence
approaches that have been proposed and applied to images common to the pathology practice, i.e. Whole Slide
Images. It is very important to pre-process these images for a deep learning classifier because they are simply
too large to feed into such a network. In order to get useful information from these images, we propose a new
background removal method for the extracted Regions Of Interest in these images. We combine traditional
morphology image operators and a U-Net framework. Firstly, we pre-process the images by using Contrast
Limited Adaptive Histogram Equalization and thresholding. Then we predict the mask by using pre-trained
U-Net weights. Finally, we use morphological opening and propagation operators on the predicted mask to
refine the masks. The experiments based on different types of staining (H&E, PAS, and JONES silver) show
the effectiveness of our method com
pared to 3 state-of-the-art models.
(More)