Object‐Oriented Segmentation of Cell Nuclei in Fluorescence Microscopy Images

Abstract

Cell nucleus segmentation remains an open and challenging problem especially to segment nuclei in cell clumps. Splitting a cell clump would be straightforward if the gradients of boundary pixels in-between the nuclei were always higher than the others. However, imperfections may exist: inhomogeneities of pixel intensities in a nucleus may cause to define spurious boundaries whereas insufficient pixel intensity differences at the border of overlapping nuclei may cause to miss some true boundary pixels. In contrast, these imperfections are typically observed at the pixel-level, causing local changes in pixel values without changing the semantics on a large scale. In response to these issues, this article introduces a new nucleus segmentation method that relies on using gradient information not at the pixel level but at the object level. To this end, it proposes to decompose an image into smaller homogeneous subregions, define edge-objects at four different orientations to encode the gradient information at the object level, and devise a merging algorithm, in which the edge-objects vote for subregion pairs along their orientations and the pairs are iteratively merged if they get sufficient votes from multiple orientations. Our experiments on fluorescence microscopy images reveal that this high-level representation and the design of a merging algorithm using edge-objects (gradients at the object level) improve the segmentation results.

Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl

“…The most challenging aspect of the competition was that the holdout set included microscopy images from 15 different biological experiments, including various 2D light microscopy types, acquisition equipment and biological conditions. This is in contrast to previous research studies that optimize nucleus segmentation methods individually for each image set or type 12,18,22,[25][26][27][28] . From a visual standpoint, we identified five groups of images comprising nuclei of very different appearances, including two major types of light microscopy (…”

Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning

“…As a result of the scalability of our human-in-the-loop approach to data labeling, TissueNet is larger than the sum total of all previously published datasets 26,27,[32][33][34][35][36][37][38] (Figure 1b), with 1.3 million whole-cell annotations and 1.2 million nuclear annotations. TissueNet contains data from six imaging platforms (Figure 1c), nine organs (Figure 1d), and includes both histologically normal and diseased tissue (e.g., tumor resections).…”

Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning

“…Existing annotated datasets for cell segmentation are limited in scope and scale ( Figure 1b) 26,27,[32][33][34][35][36][37][38] . This limitation is largely due to the linear, time-intensive approach used to construct them, which requires the border of every cell in an image to be manually demarcated.…”

“…e, The number of hours of annotation time required to create TissueNet. As a result of the scalability of our human-in-the-loop approach to data labeling, TissueNet is larger than the sum total of all previously published datasets 26,27,[32][33][34][35][36][37][38] (Figure 1b), with 1.3 million whole-cell annotations and 1.2 million nuclear annotations. TissueNet contains data from six imaging platforms (Figure 1c), nine organs (Figure 1d), and includes both histologically normal and diseased tissue (e.g., tumor resections).…”

“…Generating ground-truth data for cell segmentation is time intensive due to the need to generate pixel-level labels; as a result, existing datasets are of modest size (10 4 -10 5 annotations). Moreover, most public datasets 26,27,[32][33][34][35][36][37][38] annotate the location of cell nuclei rather than the whole cell. Deploying pre-trained models to the life science community is also difficult, and has been the focus of a number of recent works [39][40][41][42] .…”