PixN2N-HD: Image Synthesis for Multiplexed Immunofluorescence Imaging

This is the official implementation for Image Synthesis for Multiplexed Immunofluorescence Imaging using paired data to deal with missing stain and missing tissue.

Missing stain: PixN2N-HD

Missing tissue: PixNto1-MT

Source code repository

https://github.com/MASILab/MXIF_MARKER_Synthesis

Get our docker image

To do

Run Code

To do

Description

Multiplex immunofluorescence (MxIF) is an emerging imaging technique that produces the high sensitivity and specificity of single-cell mapping. With a tenet of “seeing is believing”, MxIF enables iterative staining and imaging extensive antibodies, which provides comprehensive biomarkers to segment and group different cells on a single tissue section. However, considerable depletion of the scarce tissue is inevitable from extensive rounds of staining and bleaching (“missing tissue”). Moreover, the immunofluorescence (IF) imaging can globally fail for particular rounds (“missing stain”).

For missing stain: we propose a novel multi-channel high-resolution image synthesis approach, called pixN2N-HD, to tackle any possible combinations of missing stain scenarios in MxIF. Our contribution is three-fold: (1) A single deep network is proposed to tackle missing stain synthesis task in MxIF; (2) The proposed “N-to-N” method saves 2,000-fold computational time (from four years to only 20 hours) compared with training missing stain specific models (e.g., “(N-1)-to-1”), without sacrificing the performance; (3) To our knowledge, this is the first comprehensive experimental study of tackling the missing stain challenge in MxIF via deep synthetic learning.

For missing tissue: we integrate a multi-channel high-resolution image synthesis approach, called PixNto1-MT, to synthesize the missing tissue from the remaining markers. The performance of different methods is quantitatively evaluated via the downstream cell membrane segmentation task. Our contribution is that we, for the first time, assess the feasibility of synthesizing missing tissues in MxIF via quantitative segmentation. 

Reference

Random Multi-Channel Image Synthesis for Multiplexed Immunofluorescence Imaging
Shunxing Bao, Yucheng Tang, Ho Hin Lee, Riqiang Gao, Sophie Chiron, Ilwoo Lyu, Lori A. Coburn, Keith T. Wilson, Joseph T. Roland, Bennett A. Landman, and Yuankai Huo
MICCAI Workshop on Computational Pathology (COMPAY 2021)

Inpainting Missing Tissue in Multiplexed Immunofluorescence Imaging
Shunxing Bao, Yucheng Tang, Ho Hin Lee, Riqiang Gao, Qi Yang, Xin Yu, Sophie Chiron, Lori A Coburn, Keith T Wilson, Joseph T Roland, Bennett A Landman, Yuankai Huo
SPIE Medical Imaging 2022