Volumetric Semantic Instance Segmentation of the Plasma Membrane of HeLa Cells

Abstract

In this work, an unsupervised volumetric semantic instance segmentation of the plasma membrane of HeLa cells as observed with serial block face scanning electron microscopy is described. The resin background of the images was segmented at different slices of a 3D stack of 518 slices with 8192 × 8192 pixels each. The background was used to create a distance map, which helped identify and rank the cells by their size at each slice. The centroids of the cells detected at different slices were linked to identify them as a single cell that spanned a number of slices. A subset of these cells, i.e., the largest ones and those not close to the edges were selected for further processing. The selected cells were then automatically cropped to smaller regions of interest of 2000 × 2000 × 300 voxels that were treated as cell instances. Then, for each of these volumes, the nucleus was segmented, and the cell was separated from any neighbouring cells through a series of traditional image processing steps that followed the plasma membrane. The segmentation process was repeated for all the regions of interest previously selected. For one cell for which the ground truth was available, the algorithm provided excellent results in Accuracy (AC) and the Jaccard similarity Index (JI): nucleus: JI =0.9665, AC =0.9975, cell including nucleus JI =0.8711, AC =0.9655, cell excluding nucleus JI =0.8094, AC =0.9629. A limitation of the algorithm for the plasma membrane segmentation was the presence of background. In samples with tightly packed cells, this may not be available. When tested for these conditions, the segmentation of the nuclear envelope was still possible. All the code and data were released openly through GitHub, Zenodo and EMPIAR.

Impact of Training Data, Ground Truth and Shape Variability in the Deep Learning-Based Semantic Segmentation of HeLa Cells Observed with Electron Microscopy

“…Details regarding the preparation of the HeLa cells have been previously described [ 75 ]. For completeness, these are briefly described here.…”

“…The aggregated segmentations were then used to train a U-Net and segment 20 cells from the data. The image processing algorithm was further developed in [ 73 , 75 ] to segment the plasma membrane in addition to the nuclear envelope. Further, whilst the previous papers had worked with a region of interest, Ref.…”

“…Further, whilst the previous papers had worked with a region of interest, Ref. [ 75 ] expanded the scope to a larger dataset and performed an instance segmentation of 25 cells. It is important to highlight that a limitation of the algorithm is that the cells were detected separately and then segmented in an iterative manner.…”

Evaluation of training data, ground truth and shape variability in the semantic segmentation of HeLa cells observed with electron microscopy

“…Details regarding the preparation of the HeLa cells have been previously described [11]. For completeness these are briefly described.…”

“…At higher resolutions and in three dimensions, such as those provided by electron microscopy, the problem is challenging [15,16]. Segmentation with traditional image processing algorithms and deep learning approaches [13] are widely used in tasks of segmentation, and have previously been compared for the segmentation of nuclear envelope and plasma membranes of HeLa cells as observed with electron microscopes [7,10,11,22]. In this work, the impact that the training data can have on the outcome of a segmentation was evaluated, and a comparison of the segmentations of HeLa plasma membranes and nuclear envelope with a U-Net [20] was performed.…”