ImPartial: Partial Annotations for Cell Instance Segmentation
Authors:
Preprint
Abstract
Segmenting noisy multiplex spatial tissue images constitutes a challenging task, since the characteristics of both the noise and the biology being imaged differs significantly across tissues and modalities; this is compounded by the high monetary and time costs associated with manual annotations. It is therefore imperative to build algorithms that can accurately segment the noisy images based on a small number of annotations. Recently techniques to derive such an algorithm from a few scribbled annotations have been proposed, mostly relying on the refinement and estimation of pseudo-labels. Other techniques leverage the success of self-supervised denoising as a parallel task to potentially improve the segmentation objective when few annotations are available. In this paper, we propose a method that augments the segmentation objective via self-supervised multi-channel quantized imputation, meaning that each class of the segmentation objective can be characterized by a mixture of distributions. This approach leverages the observation that perfect pixel-wise reconstruction or denoising of the image is not needed for accurate segmentation, and introduces a self-supervised classification objective that better aligns with the overall segmentation goal. We demonstrate the superior performance of our approach for a variety of cancer datasets acquired with different highly-multiplexed imaging modalities in real clinical settings. Code for our method along with a benchmarking dataset is available at https://github.com/natalialmg/ImPartial .Keywords
This publication has 25 references indexed in Scilit:
- Scribble2Label: Scribble-Supervised Cell Segmentation via Self-generating Pseudo-Labels with Consistency2020
- Nucleus segmentation across imaging experiments: the 2018 Data Science BowlNature Methods, 2019
- Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response2019
- PseudoEdgeNet: Nuclei Segmentation only with Point Annotations2019
- Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence ImagesCytometry Part A, 2019
- Deep learning for cellular image analysisNature Methods, 2019
- Content-aware image restoration: pushing the limits of fluorescence microscopyNature Methods, 2018
- A Structured Tumor-Immune Microenvironment in Triple Negative Breast Cancer Revealed by Multiplexed Ion Beam ImagingCell, 2018
- CDeep3M—Plug-and-Play cloud-based deep learning for image segmentationNature Methods, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015