Dice-XMBD: Deep learning-based cell segmentation for imaging mass cytometry

Abstract

Highly multiplexed imaging technology is a powerful tool to facilitate understanding cells composition and interaction in tumor microenvironment at subcellular resolution, which is crucial for both basic research and clinical applications. Imaging mass cytometry (IMC), a multiplex imaging method recently introduced, can measure up to 40 markers simultaneously in one tissue section by using a high-resolution laser with a mass cytometer. However, due to its high resolution and large number of channels, how to process and interpret the image data from IMC remains a key challenge for its further applications. Accurate and reliable single cell segmentation is the first and a critical step to process IMC image data. Unfortunately, existing segmentation pipelines either produce inaccurate cell segmentation results, or require manual annotation which is very time-consuming. Here, we developed Dice-XMBD, a Deep learnIng-based Cell sEgmentation algorithm for tissue multiplexed imaging data. In comparison with other state-of-the-art cell segmentation methods currently used in IMC, Dice-XMBD generates more accurate single cell masks efficiently on IMC images produced with different nuclear, membrane and cytoplasm markers. All codes and datasets are available at https://github.com/xmuyulab/Dice-XMBD.

An end-to-end workflow for multiplexed image processing and analysis

“…For example, a two-channel nuclear/cytoplasm image can be constructed from a multichannel image by averaging all nuclear and all cytoplasmic channels. Such channel-aggregated images can then be used to train panel-agnostic pixel classifiers to imitate classifiers previously trained on specific sets of markers [12], or to directly apply generalist cell segmentation algorithms [13][14][15]. The latter methodologies include deep learning-enabled algorithms achieving human-level performance across various tissue types and imaging platforms [15].…”