Abstract
Pathological examination has been done manually by visual in-spection of hematoxylin and eosin (H&E)-stained images. However, this pro-cess is labor intensive, prone to large variations, and lacking reproducibility in the diagnosis of a tumor. We aim to develop an automatic workflow to extract different cell nuclei found in cancerous tumors portrayed in digital renderings of the H&E-stained images. For a given image, we propose a semantic pixel-wise segmentation technique using dilated convolutions. The architecture of our dilated convolutional network (DCN) is based on SegNet, a deep convolutional encoder-decoder architecture. For the encoder, all the max pooling layers in the SegNet are removed and the convolutional layers are replaced by dilated convolution layers with increased dilation factors to preserve image resolution. For the decoder, all max unpooling layers are removed and the convolutional layers are replaced by dilated convolution layers with decreased dilation factors to remove gridding artifacts. We show that dilated convolutions are superior in extracting information from textured images. We test our DCN network on both synthetic data sets and a public available data set of H&E-stained images and achieve better results than the state of the art.
Original language | English (US) |
---|---|
Pages (from-to) | 27-40 |
Number of pages | 14 |
Journal | Inverse Problems and Imaging |
Volume | 15 |
Issue number | 1 |
DOIs | |
State | Published - 2021 |
Keywords
- Convolution
- Deep learning
- Dilated convolution
- Histopathology image
- Semantic segmentation
ASJC Scopus subject areas
- Analysis
- Modeling and Simulation
- Discrete Mathematics and Combinatorics
- Control and Optimization