Topology‐based fluorescence image analysis for automated cell identification and segmentation

Abstract

Cell segmentation refers to the body of techniques used to identify cells in images and extract biologically relevant information from them; however, manual segmentation is laborious and subjective. We present Topological Boundary Line Estimation using Recurrence Of Neighbouring Emissions (TOBLERONE), a topological image analysis tool which identifies persistent homological image features as opposed to the geometric analysis commonly employed. We demonstrate that topological data analysis can provide accurate segmentation of arbitrarily‐shaped cells, offering a means for automatic and objective data extraction. One cellular feature of particular interest in biology is the plasma membrane, which has been shown to present varying degrees of lipid packing, or membrane order, depending on the function and morphology of the cell type. With the use of environmentally‐sensitive dyes, images derived from confocal microscopy can be used to quantify the degree of membrane order. We demonstrate that TOBLERONE is capable of automating this task.

Three-dimensional topology-based analysis segments volumetric and spatiotemporal fluorescence microscopy

“…That said, topological features are inherently robust to variations in intensity in both 2D and 3D data, so a range of persistence thresholds will typically suffice ( 58 , 59 ) . It has been shown that topological segmentation is consistently accurate across varied intensity conditions provided there is sufficient contrast between the foreground and background ( 28 ) . As discussed, TOBLERONE is invariant of object morphology, which makes the algorithm extremely generalizable, but can lead to difficulties when separating densely-packed structures ( 57 , 59 ) .…”

“…Here, we devise complete algorithms for volumetric segmentation in 3D data and dynamic tracking of live-cell data. As topological methodologies, the TOBLERONE family of algorithms require no training data, are robust to imaging artifacts, can be extended to an arbitrary number of dimensions, and are invariant to variations in geometry, allowing them to function regardless of cell or organelle morphologies (28,(31)(32)(33) . Furthermore, the algorithms automatically extract statistics of the volumetric properties of the underlying objects, such as size and position, and dynamic processes, such as change in the number of objects identified over time.…”

“…In this work, we introduce two new algorithms, built on the existing topological data analysis (TDA) technique TOBLERONE, for segmentation and quantification of 3D volumetric (3DTOB) and spatiotemporal (tempTOB) data sets ( 28 ) . Topological decomposition of image intensity variation across imposed gradient fields has shown promise in both 2D and 3D segmentation of cells and organelles, especially in fluorescence microscopy ( 29 , 30 ) .…”