Generalising multistain immunohistochemistry tissue segmentation using end‐to‐end colour deconvolution deep neural networks

Abstract

A key challenge in cancer immunotherapy biomarker research is quantification of pattern changes in microscopic whole slide images of tumor biopsies. Different cell types tend to migrate into various tissue compartments and form variable distribution patterns. Drug development requires correlative analysis of various biomarkers in and between the tissue compartments. To enable that, tissue slides are manually annotated by expert pathologists. Manual annotation of tissue slides is a labor intensive, tedious and error-prone task. Automation of this annotation process can improve accuracy and consistency while reducing workload and cost in a way that will positively influence drug development efforts. In this paper we present a novel one-shot color deconvolution deep learning method to automatically segment and annotate digitized slide images with multiple stainings into compartments of tumor, healthy tissue, and necrosis. We address the task in the context of drug development where multiple stains, tissue and tumor types exist and look into solutions for generalizations over these image populations.

Color Deconvolution as a Simple and Rapid Tool in Quantitative Biomedical Research

“…This simple and rapid technique to analyze the absorbance of different dyes in a quantitative manner has the potential to increase the flow of analysis in biomedical research. To corroborate with our presented toolkit, color deconvolution was previously used by researchers to study, e.g., hepatocellular carcinoma, 4 atherosclerotic lesions, 5 deep neural networks, 6 and skin layers. 7 These studies showed the versatility of this technique in both histochemistry and IHC as the brown color generated by 3,3′-diaminobenzidine from IHC can be separate from the original image and quantitatively analyzed to show the percentage of its stained structure.…”

Translational AI and Deep Learning in Diagnostic Pathology

“…High accuracy results are obtained with substantial improvement in generalization. The added deconvolution segment layer learns to differentiate stain channels for different types of stains (104). Garcia et al used CNNs for detection of lymphocytes in IHC images and have used augmentation to increase the data for analysis.…”

A Multi-Scale Conditional Deep Model for Tumor Cell Ratio Counting

“…Deep learning methods have been shown to produce excellent results on general image segmentation tasks 19 and have recently been applied to histology images for nuclei segmentation [20][21][22] and tumor area segmentation. 23,24 The general principle is the same as for nuclei detection. A model is trained to map an input image to a density map representing the tumor area.…”