Segmentation of cell nuclei in fluorescence microscopy images: An integrated framework using level set segmentation and touching-cell splitting

Gharipour, Amin; Liew, Alan Wee‐Chung

doi:10.1016/j.patcog.2016.03.030

Cited by 41 publications

(19 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Morphological operations like ultimate erosion [24] and H-minima transform [25,26] have been used to locate centers. Radial symmetry was proposed as another seedpoint extraction approach in [4,9]. In [27], the centers of objects were interpreted in a physics perspective as particles dynamically reaching their steady states, with the distance transform mapping serving as a potential well.…”

Section: Related Workmentioning

confidence: 99%

“…Recognizing overlapping objects is a common problem in image analysis and arises in various real-world applications, such as splitting touching cells in medical images [1][2][3][4], bubble detection and recognition [5,6] and bloodstain pattern analysis in forensic science [7]. In cases where the individual objects have approximately oval shapes (cells, bubbles or bloodstains), one approach is to find a representation composed of multiple ellipses to approximate the overlapping objects.…”

Section: Introductionmentioning

confidence: 99%

“…There may be multiple arrangements of ellipses that all seem to produce a reasonable fit to the clump, yet there is no well-defined criterion to determine which is the best. The existing literature [1,3,4,6,9] relies on a variety of metrics of overall fit including Jaccard index, Hausdorff distance and mean absolute contour distance (MAD), or attempts to use concepts from classification (e.g., false positive and false negative counts). The former metrics assess the fit of the collection of ellipses but do not address the accuracy of individual ellipses, leading to optimistic evaluation.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recognition of overlapping elliptical objects in a binary image

Zou

Pan

Taylor

2021

Pattern Anal Applic

View full text Add to dashboard Cite

Recognition of overlapping objects is required in many applications in the field of computer vision. Examples include cell segmentation, bubble detection and bloodstain pattern analysis. This paper presents a method to identify overlapping objects by approximating them with ellipses. The method is intended to be applied to complex-shaped regions which are believed to be composed of one or more overlapping objects. The method has two primary steps. First, a pool of candidate ellipses are generated by applying the Euclidean distance transform on a compressed image and the pool is filtered by an overlaying method. Second, the concave points on the contour of the region of interest are extracted by polygon approximation to divide the contour into segments. Then, the optimal ellipses are selected from among the candidates by choosing a minimal subset that best fits the identified segments. We propose the use of the adjusted Rand index, commonly applied in clustering, to compare the fitting result with ground truth. Through a set of computational and optimization efficiencies, we are able to apply our approach in complex images comprised of a number of overlapped regions. Experimental results on a synthetic data set, two types of cell images and bloodstain patterns show superior accuracy and flexibility of our method in ellipse recognition, relative to other methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of overlapping elliptical objects in a binary image

Zou

Pan

Taylor

2021

Pattern Anal Applic

View full text Add to dashboard Cite

show abstract

“…A number of computational approaches have been developed for instance segmentation (e.g. (Thomas & John, 2017;Vu et al, 2019) , (Cremers, Rousson, & Deriche, 2007;Gharipour & Liew, 2016) (Bailoni et al, 2019) (Kallasi, Rizzini, Oleari, & Aleotti, 2015;Pal & Pal, 1993) ) such as for example the commonly used, watershed, graph partitioning and gradient based methods. In watershed approaches seed regions are first detected using criteria like local intensity minima or user provided markers .…”

Section: Introductionmentioning

confidence: 99%

Benchmarking of deep learning algorithms for 3D instance segmentation of confocal image datasets

Kar

Petit

Refahi

et al. 2021

Preprint

View full text Add to dashboard Cite

Segmenting three dimensional microscopy images is essential for understanding phenomena like morphogenesis, cell division, cellular growth and genetic expression patterns. Recently, deep learning (DL) pipelines have been developed which claim to provide high accuracy segmentation of cellular images and are increasingly considered as the state-of-the-art for image segmentation problems. However, it remains difficult to define their relative performance as the concurrent diversity and lack of uniform evaluation strategies makes it difficult to know how their results compare. In this paper, we first made an inventory of the available DL methods for 3D segmentation. We next implemented and quantitatively compared a number of representative DL pipelines, alongside a highly efficient non-DL method named MARS. The DL methods were trained on a common dataset of 3D cellular confocal microscopy images. Their segmentation accuracies were also tested in the presence of different image artefacts. A new method for segmentation quality evaluation was adopted which isolates segmentation errors due to under/over segmentation. This is complemented with new visualisation strategies that make interactive exploration of segmentation quality possible. Our analysis shows that the DL pipelines have very different levels of accuracy. Two of them show high performance, and offer clear advantages in terms of adaptability to new data.

show abstract

“…The methods used to segment clustered cells can be categorised into shaped‐based (Kumar et al ., ; Al‐Kofahi et al ., ; Kong et al ., ; Wienert et al ., ; Veta et al ., ; Chen et al ., ; Song et al ., ; Gharipour & Liew, ) and light intensity‐based approaches (Ali et al ., ; Wang et al ., ). Shape‐based approaches use distance transform (Al‐Kofahi et al ., ; Chen et al ., ; Song et al ., ), concave points along contours (Kumar et al ., ; Wienert et al ., ; Gharipour & Liew, ), and radial symmetry transform (Kong et al ., ; Veta et al ., ; Gharipour & Liew, ) to conduct cell segmentation, assuming cells have regular (elliptical, for example) and convex shapes. Light intensity‐based methods segment cells using the special distribution of light intensity over cell bodies, assuming the light intensity has direct correlation with cell height.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of clustered cells in negative phase contrast images with integrated light intensity and cell shape information

Yu-liang

Wang

Zhang

2017

Journal of Microscopy

View full text Add to dashboard Cite

Automated cell segmentation plays a key role in characterisations of cell behaviours for both biology research and clinical practices. Currently, the segmentation of clustered cells still remains as a challenge and is the main reason for false segmentation. In this study, the emphasis was put on the segmentation of clustered cells in negative phase contrast images. A new method was proposed to combine both light intensity and cell shape information through the construction of grey-weighted distance transform (GWDT) within preliminarily segmented areas. With the constructed GWDT, the clustered cells can be detected and then separated with a modified region skeleton-based method. Moreover, a contour expansion operation was applied to get optimised detection of cell boundaries. In this paper, the working principle and detailed procedure of the proposed method are described, followed by the evaluation of the method on clustered cell segmentation. Results show that the proposed method achieves an improved performance in clustered cell segmentation compared with other methods, with 85.8% and 97.16% accuracy rate for clustered cells and all cells, respectively.

show abstract

Segmentation of cell nuclei in fluorescence microscopy images: An integrated framework using level set segmentation and touching-cell splitting

Cited by 41 publications

References 63 publications

Recognition of overlapping elliptical objects in a binary image

Recognition of overlapping elliptical objects in a binary image

Benchmarking of deep learning algorithms for 3D instance segmentation of confocal image datasets

Segmentation of clustered cells in negative phase contrast images with integrated light intensity and cell shape information

Contact Info

Product

Resources

About