Combining intensity, edge and shape information for 2D and 3D segmentation of cell nuclei in tissue sections

By Carolina Wählby, Ida-Maria Sintorn, F. Erlandsson, Gunilla Borgefors, Ewert Bengtsson. 2004

372 citations recorded by the source corpus.

We present a region‐based segmentation method in which seeds representing both object and background pixels are created by combining morphological filtering of both the original image and the gradient magnitude of the image. The seeds are then used as starting points for watershed segmentation of the gradient magnitude image. The fully automatic seeding is done in a generous fashion, so that at least one seed will be set in each foreground object. If more than one seed is placed in a single object, the watershed segmentation will lead to an initial over‐segmentation, i.e. a boundary is created where there is no strong edge. Thus, the result of the initial segmentation is further refined by merging based on the gradient magnitude along the boundary separating neighbouring objects. This step also makes it easy to remove objects with poor contrast. As a final step, clusters of nuclei are separated, based on the shape of the cluster. The number of input parameters to the full segmentation procedure is only five. These parameters can be set manually using a test image and thereafter be used on a large number of images created under similar imaging conditions. This automated system was verified by comparison with manual counts from the same image fields. About 90% correct segmentation was achieved for two‐ as well as three‐dimensional images.

Subfields: Artificial Intelligence, Biophysics, Computer Vision and Pattern Recognition, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biophysics

In Computer Vision and Pattern Recognition

In Medical Imaging

Citations in the corpus

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images (2018, methodology): “One of the most commonly used strategies for nucleus segmentation is Otsu’s thresholding method (7) followed by seeded watershed (8,9), because of its effectiveness, simplicity of use and computational efficiency.”
On the digital trail of mobile cells (2006, methodology): “CELL CONTACTS A recurrent problem when tracking multiple cells is posed by cells that touch or overlap each other, because the boundary between cells in contact is often difficult to identify automatically as well as by eye [1], [9], [11], [14], [22].”
Histopathological Image Analysis: A Review (2009, methodology): “[71], where the accuracy here is calculated based on manual cell counts (i.”
Machine learning and computer vision approaches for phenotypic profiling (2017, methodology): “For example, bright-field or differential interference contrast images typically require edge detection–based algorithms (Chen et al., 2006), whereas fluorescent images can rely on thresholding and region-growing techniques (Wählby et al., 2004).”
Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review (2016, methodology): “For nucleus segmentation in 2-D prostate carcinoma images [43], [62], the mean intensity along the border”
Automated Cell Lineage Construction: A Rapid Method to Analyze Clonal Development Established with Murine Neural Progenitor Cells (2006, methodology): “The first approach involves segmenting cells in each image frame independently based on properties such as intensity, texture and gradient, 15,16 followed by an association of cells between consecutive image frames.”
CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging (2010, methodology): “, followed by a watershed split-and-merge segmentation error correctio”
Digital Topology and Geometry in Medical Imaging: A Survey (2015, background): “Another approach to reduce the number of regions is using a seeded watershed [186], [187], where the flooding starts from labeled seed points instead of local minima and barriers are built when two basins meet.”
Computer vision for high content screening (2016, methodology): “In many cases, thresholding methods are used to identify regions within cells, such as nuclei, and region growing methods, such as seeded watershed, are used to identify cell boundaries (Bengtsson et al ., 2004; Wa¨hlby et al ., 2004).”
An investigation of single sand particle fracture using X-ray micro-tomography (2015, methodology): “An approach based on the concept of markers was therefore used to control the over-segmentation (Wählby et al., 2004).”