1
|
|
2
|
Macaque neuron instance segmentation only with point annotations based on multiscale fully convolutional regression neural network. Neural Comput Appl 2021. [DOI: 10.1007/s00521-021-06574-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
3
|
Vicar T, Balvan J, Jaros J, Jug F, Kolar R, Masarik M, Gumulec J. Cell segmentation methods for label-free contrast microscopy: review and comprehensive comparison. BMC Bioinformatics 2019; 20:360. [PMID: 31253078 PMCID: PMC6599268 DOI: 10.1186/s12859-019-2880-8] [Citation(s) in RCA: 85] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2019] [Accepted: 05/07/2019] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Because of its non-destructive nature, label-free imaging is an important strategy for studying biological processes. However, routine microscopic techniques like phase contrast or DIC suffer from shadow-cast artifacts making automatic segmentation challenging. The aim of this study was to compare the segmentation efficacy of published steps of segmentation work-flow (image reconstruction, foreground segmentation, cell detection (seed-point extraction) and cell (instance) segmentation) on a dataset of the same cells from multiple contrast microscopic modalities. RESULTS We built a collection of routines aimed at image segmentation of viable adherent cells grown on the culture dish acquired by phase contrast, differential interference contrast, Hoffman modulation contrast and quantitative phase imaging, and we performed a comprehensive comparison of available segmentation methods applicable for label-free data. We demonstrated that it is crucial to perform the image reconstruction step, enabling the use of segmentation methods originally not applicable on label-free images. Further we compared foreground segmentation methods (thresholding, feature-extraction, level-set, graph-cut, learning-based), seed-point extraction methods (Laplacian of Gaussians, radial symmetry and distance transform, iterative radial voting, maximally stable extremal region and learning-based) and single cell segmentation methods. We validated suitable set of methods for each microscopy modality and published them online. CONCLUSIONS We demonstrate that image reconstruction step allows the use of segmentation methods not originally intended for label-free imaging. In addition to the comprehensive comparison of methods, raw and reconstructed annotated data and Matlab codes are provided.
Collapse
Affiliation(s)
- Tomas Vicar
- Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3058/10, Brno, CZ-61600 Czech Republic
- Department of Physiology, Faculty of Medicine, Masaryk University, Kamenice 5, Brno, CZ-62500 Czech Republic
| | - Jan Balvan
- Department of Pathological Physiology, Faculty of Medicine, Masaryk University, Kamenice 5, Brno, CZ-62500 Czech Republic
- Central European Institute of Technology, Brno University of Technology, Purkynova 656/123, Brno, CZ-612 00 Czech Republic
| | - Josef Jaros
- Department of Histology and Embryology, Faculty of Medicine, Masaryk University, Kamenice 5, Brno, CZ-62500 Czech Republic
- International Clinical Research Center, St. Anne’s University Hospital, Pekarska 664/53, Brno, CZ-65691 Czech Republic
| | - Florian Jug
- Max Planck Institute of Molecular Cell Biology and Genetics, Pfotenhauerstr. 108, Dresden, DE-01307 Germany
| | - Radim Kolar
- Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3058/10, Brno, CZ-61600 Czech Republic
| | - Michal Masarik
- Department of Pathological Physiology, Faculty of Medicine, Masaryk University, Kamenice 5, Brno, CZ-62500 Czech Republic
- Central European Institute of Technology, Brno University of Technology, Purkynova 656/123, Brno, CZ-612 00 Czech Republic
| | - Jaromir Gumulec
- Department of Physiology, Faculty of Medicine, Masaryk University, Kamenice 5, Brno, CZ-62500 Czech Republic
- Department of Pathological Physiology, Faculty of Medicine, Masaryk University, Kamenice 5, Brno, CZ-62500 Czech Republic
- Central European Institute of Technology, Brno University of Technology, Purkynova 656/123, Brno, CZ-612 00 Czech Republic
| |
Collapse
|
4
|
Winter M, Mankowski W, Wait E, De La Hoz EC, Aguinaldo A, Cohen AR. Separating Touching Cells Using Pixel Replicated Elliptical Shape Models. IEEE TRANSACTIONS ON MEDICAL IMAGING 2019; 38:883-893. [PMID: 30296216 PMCID: PMC6450753 DOI: 10.1109/tmi.2018.2874104] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
One of the most important and error-prone tasks in biological image analysis is the segmentation of touching or overlapping cells. Particularly for optical microscopy, including transmitted light and confocal fluorescence microscopy, there is often no consistent discriminative information to separate cells that touch or overlap. It is desired to partition touching foreground pixels into cells using the binary threshold image information only, and optionally incorporating gradient information. The most common approaches for segmenting touching and overlapping cells in these scenarios are based on the watershed transform. We describe a new approach called pixel replication for the task of segmenting elliptical objects that touch or overlap. Pixel replication uses the image Euclidean distance transform in combination with Gaussian mixture models to better exploit practically effective optimization for delineating objects with elliptical decision boundaries. Pixel replication improves significantly on commonly used methods based on watershed transforms, or based on fitting Gaussian mixtures directly to the thresholded image data. Pixel replication works equivalently on both 2-D and 3-D image data, and naturally combines information from multi-channel images. The accuracy of the proposed technique is measured using both the segmentation accuracy on simulated ellipse data and the tracking accuracy on validated stem cell tracking results extracted from hundreds of live-cell microscopy image sequences. Pixel replication is shown to be significantly more accurate compared with other approaches. Variance relationships are derived, allowing a more practically effective Gaussian mixture model to extract cell boundaries for data generated from the threshold image using the uniform elliptical distribution and from the distance transform image using the triangular elliptical distribution.
Collapse
|
5
|
Microscopic malaria parasitemia diagnosis and grading on benchmark datasets. Microsc Res Tech 2018; 81:1042-1058. [DOI: 10.1002/jemt.23071] [Citation(s) in RCA: 38] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2017] [Revised: 04/23/2018] [Accepted: 05/10/2018] [Indexed: 12/16/2022]
|
6
|
Yan Z, Chen F, Wu F, Kong D. Inferior vena cava segmentation with parameter propagation and graph cut. Int J Comput Assist Radiol Surg 2017; 12:1481-1499. [PMID: 28421319 DOI: 10.1007/s11548-017-1582-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2016] [Accepted: 03/29/2017] [Indexed: 11/29/2022]
Abstract
PURPOSE The inferior vena cava (IVC) is one of the vital veins inside the human body. Accurate segmentation of the IVC from contrast-enhanced CT images is of great importance. This extraction not only helps the physician understand its quantitative features such as blood flow and volume, but also it is helpful during the hepatic preoperative planning. However, manual delineation of the IVC is time-consuming and poorly reproducible. METHODS In this paper, we propose a novel method to segment the IVC with minimal user interaction. The proposed method performs the segmentation block by block between user-specified beginning and end masks. At each stage, the proposed method builds the segmentation model based on information from image regional appearances, image boundaries, and a prior shape. The intensity range and the prior shape for this segmentation model are estimated based on the segmentation result from the last block, or from user- specified beginning mask if at first stage. Then, the proposed method minimizes the energy function and generates the segmentation result for current block using graph cut. Finally, a backward tracking step from the end of the IVC is performed if necessary. RESULTS We have tested our method on 20 clinical datasets and compared our method to three other vessel extraction approaches. The evaluation was performed using three quantitative metrics: the Dice coefficient (Dice), the mean symmetric distance (MSD), and the Hausdorff distance (MaxD). The proposed method has achieved a Dice of [Formula: see text], an MSD of [Formula: see text] mm, and a MaxD of [Formula: see text] mm, respectively, in our experiments. CONCLUSION The proposed approach can achieve a sound performance with a relatively low computational cost and a minimal user interaction. The proposed algorithm has high potential to be applied for the clinical applications in the future.
Collapse
Affiliation(s)
- Zixu Yan
- School of Mathematical Sciences, Zhejiang University, Hangzhou, 310027, China
| | - Feng Chen
- Department of Radiology, First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, 310003, China
| | - Fa Wu
- School of Mathematical Sciences, Zhejiang University, Hangzhou, 310027, China
| | - Dexing Kong
- School of Mathematical Sciences, Zhejiang University, Hangzhou, 310027, China.
| |
Collapse
|
7
|
Yi F, Huang J, Yang L, Xie Y, Xiao G. Automatic extraction of cell nuclei from H&E-stained histopathological images. J Med Imaging (Bellingham) 2017; 4:027502. [PMID: 28653017 PMCID: PMC5478972 DOI: 10.1117/1.jmi.4.2.027502] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2017] [Accepted: 05/31/2017] [Indexed: 12/15/2022] Open
Abstract
Extraction of cell nuclei from hematoxylin and eosin (H&E)-stained histopathological images is an essential preprocessing step in computerized image analysis for disease detection, diagnosis, and prognosis. We present an automated cell nuclei segmentation approach that works with H&E-stained images. A color deconvolution algorithm was first applied to the image to get the hematoxylin channel. Using a morphological operation and thresholding technique on the hematoxylin channel image, candidate target nuclei and background regions were detected, which were then used as markers for a marker-controlled watershed transform segmentation algorithm. Moreover, postprocessing was conducted to split the touching nuclei. For each segmented region from the previous steps, the regional maximum value positions were identified as potential nuclei centers. These maximum values were further grouped into [Formula: see text]-clusters, and the locations within each cluster were connected with the minimum spanning tree technique. Then, these connected positions were utilized as new markers for a watershed segmentation approach. The final number of nuclei at each region was determined by minimizing an objective function that iterated all of the possible [Formula: see text]-values. The proposed method was applied to the pathological images of the tumor tissues from The Cancer Genome Atlas study. Experimental results show that the proposed method can lead to promising results in terms of segmentation accuracy and separation of touching nuclei.
Collapse
Affiliation(s)
- Faliu Yi
- University of Texas Southwestern Medical Center, Quantitative Biomedical Research Center, Department of Clinical Science, Dallas, Texas, United States
| | - Junzhou Huang
- University of Texas at Arlington, Department of Computer Science and Engineering, Arlington, Texas, United States
| | - Lin Yang
- University of Texas Southwestern Medical Center, Quantitative Biomedical Research Center, Department of Clinical Science, Dallas, Texas, United States
- Chinese Academy of Medical Science and Peking Union Medical College, National Cancer Center/Cancer Hospital, Department of Pathology, Chaoyang District, Beijing, China
| | - Yang Xie
- University of Texas Southwestern Medical Center, Quantitative Biomedical Research Center, Department of Clinical Science, Dallas, Texas, United States
- University of Texas Southwestern Medical Center, Department of Bioinformatics, Dallas, Texas, United States
- University of Texas Southwestern Medical Center, Harold C. Simmons Comprehensive Cancer Center, Dallas, Texas, United States
| | - Guanghua Xiao
- University of Texas Southwestern Medical Center, Quantitative Biomedical Research Center, Department of Clinical Science, Dallas, Texas, United States
- University of Texas Southwestern Medical Center, Department of Bioinformatics, Dallas, Texas, United States
- University of Texas Southwestern Medical Center, Harold C. Simmons Comprehensive Cancer Center, Dallas, Texas, United States
| |
Collapse
|
8
|
Scherzinger A, Kleene F, Dierkes C, Kiefer F, Hinrichs KH, Jiang X. Automated Segmentation of Immunostained Cell Nuclei in 3D Ultramicroscopy Images. LECTURE NOTES IN COMPUTER SCIENCE 2016. [DOI: 10.1007/978-3-319-45886-1_9] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/22/2023]
|
9
|
An Object Splitting Model Using Higher-Order Active Contours for Single-Cell Segmentation. ADVANCES IN VISUAL COMPUTING 2016. [DOI: 10.1007/978-3-319-50835-1_3] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
|
10
|
Robinson S, Guyon L, Nevalainen J, Toriseva M, Åkerfelt M, Nees M. Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields. PLoS One 2015; 10:e0143798. [PMID: 26630674 PMCID: PMC4668034 DOI: 10.1371/journal.pone.0143798] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2015] [Accepted: 11/10/2015] [Indexed: 11/22/2022] Open
Abstract
Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.
Collapse
Affiliation(s)
- Sean Robinson
- Department of Mathematics and Statistics, University of Turku, Turku, Finland
- Industrial Biotechnology, VTT Technical Research Centre of Finland, Turku, Finland
- Université Grenoble-Alpes, F-38000 Grenoble, France
- CEA, iRTSV, Biologie à Grande Echelle, F-38054 Grenoble, France
- INSERM, U1038, F-38054 Grenoble, France
- * E-mail:
| | - Laurent Guyon
- Université Grenoble-Alpes, F-38000 Grenoble, France
- CEA, iRTSV, Biologie à Grande Echelle, F-38054 Grenoble, France
- INSERM, U1038, F-38054 Grenoble, France
| | - Jaakko Nevalainen
- Department of Mathematics and Statistics, University of Turku, Turku, Finland
- School of Health Sciences, University of Tampere, Tampere, Finland
| | - Mervi Toriseva
- Industrial Biotechnology, VTT Technical Research Centre of Finland, Turku, Finland
- Institute of Biomedicine, University of Turku, Turku, Finland
- Turku Centre for Biotechnology, University of Turku, Turku, Finland
| | - Malin Åkerfelt
- Industrial Biotechnology, VTT Technical Research Centre of Finland, Turku, Finland
- Institute of Biomedicine, University of Turku, Turku, Finland
- Turku Centre for Biotechnology, University of Turku, Turku, Finland
| | - Matthias Nees
- Industrial Biotechnology, VTT Technical Research Centre of Finland, Turku, Finland
- Institute of Biomedicine, University of Turku, Turku, Finland
- Turku Centre for Biotechnology, University of Turku, Turku, Finland
| |
Collapse
|
11
|
Zafari S, Eerola T, Sampo J, Kälviäinen H, Haario H. Segmentation of Overlapping Elliptical Objects in Silhouette Images. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2015; 24:5942-5952. [PMID: 26513788 DOI: 10.1109/tip.2015.2492828] [Citation(s) in RCA: 27] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
Segmentation of partially overlapping objects with a known shape is needed in an increasing amount of various machine vision applications. This paper presents a method for segmentation of clustered partially overlapping objects with a shape that can be approximated using an ellipse. The method utilizes silhouette images, which means that it requires only that the foreground (objects) and background can be distinguished from each other. The method starts with seedpoint extraction using bounded erosion and fast radial symmetry transform. Extracted seedpoints are then utilized to associate edge points to objects in order to create contour evidence. Finally, contours of the objects are estimated by fitting ellipses to the contour evidence. The experiments on one synthetic and two different real data sets showed that the proposed method outperforms two current state-of-art approaches in overlapping objects segmentation.
Collapse
|
12
|
Qi J, Wang B, Pelaez N, Rebay I, Carthew RW, Katsaggelos AK, Nunes Amaral LA. Drosophila Eye Nuclei Segmentation Based on Graph Cut and Convex Shape Prior. INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS. INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING 2013:670-674. [PMID: 25089515 DOI: 10.1109/icip.2013.6738138] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
The rapid advance in three-dimensional (3D) confocal imaging technologies is rapidly increasing the availability of 3D cellular images. However, the lack of robust automated methods for the extraction of cell or organelle shapes from the images is hindering researchers ability to take full advantage of the increase in experimental output. The lack of appropriate methods is particularly significant when the density of the features of interest in high, such as in the developing eye of the fruit fly. Here, we present a novel and efficient nuclei segmentation algorithm based on the combination of graph cut and convex shape prior. The main characteristic of the algorithm is that it segments nuclei foreground using a graph cut algorithm and splits overlapping or touching cell nuclei by simple convex and concavity analysis, using a convex shape assumption for nuclei contour. We evaluate the performance of our method by applying it to a library of publicly-available two-dimensional (2D) images that were hand-labeled by experts. Our algorithm yields a substantial quantitative improvement over other methods for this benchmark. For example, our method achieves a decrease of 3.2 in the Hausdorff distance and an decrease of 1.8 per slice in the merged nuclei error.
Collapse
Affiliation(s)
- Jin Qi
- Department of Electrical Engineering and Computer Science, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
| | - B Wang
- Molecular Biosciences, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
| | - N Pelaez
- NICO and Dept. Chemical & Biological Engineering, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
| | - I Rebay
- HHMI, Northwestern University, 2145 Sheridan Road, Evanston, IL 60208, USA
| | - R W Carthew
- Department of Electrical Engineering, University of Electronic Science & Technology of China, 2006 Xiyuan Avenue, Gaoxin District, Chengdu, Sichuan Province 611731, China
| | - A K Katsaggelos
- Ben May Center for Cancer Research, University of Chicago, Chicago, IL 60637, USA
| | | |
Collapse
|
13
|
Zimmer C. From microbes to numbers: extracting meaningful quantities from images. Cell Microbiol 2012; 14:1828-35. [DOI: 10.1111/cmi.12032] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2012] [Revised: 08/29/2012] [Accepted: 08/30/2012] [Indexed: 11/26/2022]
|
14
|
Massoudi A, Sowmya A, Mele K, Semenovich D. Employing temporal information for cell segmentation using max-flow/min-cut in phase-contrast video microscopy. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2011; 2011:5985-5988. [PMID: 22255703 DOI: 10.1109/iembs.2011.6091479] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/31/2023]
Abstract
Cell segmentation is a crucial step in many bio-medical image analysis applications and it can be considered as an important part of a tracking system. Segmentation in phase-contrast images is a challenging task since in this imaging technique, the background intensity is approximately similar to the cell pixel intensity. In this paper we propose an interactive automatic pixel level segmentation algorithm, that uses temporal information to improve the segmentation result. This algorithm is based on the max-flow/min-cut algorithm and can be solved in polynomial time. This method is not restricted to any specific cell shape and segments cells of various shapes and sizes. The results of the proposed algorithm show that using the temporal information does improve segmentation considerably.
Collapse
Affiliation(s)
- Amir Massoudi
- Department of Computer Science and Engineering, University of New South Wales, Sydney, New South Wales 2052, Australia
| | | | | | | |
Collapse
|
15
|
Quelhas P, Marcuzzo M, Mendonça AM, Campilho A. Cell nuclei and cytoplasm joint segmentation using the sliding band filter. IEEE TRANSACTIONS ON MEDICAL IMAGING 2010; 29:1463-1473. [PMID: 20525532 DOI: 10.1109/tmi.2010.2048253] [Citation(s) in RCA: 41] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/29/2023]
Abstract
Microscopy cell image analysis is a fundamental tool for biological research. In particular, multivariate fluorescence microscopy is used to observe different aspects of cells in cultures. It is still common practice to perform analysis tasks by visual inspection of individual cells which is time consuming, exhausting and prone to induce subjective bias. This makes automatic cell image analysis essential for large scale, objective studies of cell cultures. Traditionally the task of automatic cell analysis is approached through the use of image segmentation methods for extraction of cells' locations and shapes. Image segmentation, although fundamental, is neither an easy task in computer vision nor is it robust to image quality changes. This makes image segmentation for cell detection semi-automated requiring frequent tuning of parameters. We introduce a new approach for cell detection and shape estimation in multivariate images based on the sliding band filter (SBF). This filter's design makes it adequate to detect overall convex shapes and as such it performs well for cell detection. Furthermore, the parameters involved are intuitive as they are directly related to the expected cell size. Using the SBF filter we detect cells' nucleus and cytoplasm location and shapes. Based on the assumption that each cell has the same approximate shape center in both nuclei and cytoplasm fluorescence channels, we guide cytoplasm shape estimation by the nuclear detections improving performance and reducing errors. Then we validate cell detection by gathering evidence from nuclei and cytoplasm channels. Additionally, we include overlap correction and shape regularization steps which further improve the estimated cell shapes. The approach is evaluated using two datasets with different types of data: a 20 images benchmark set of simulated cell culture images, containing 1000 simulated cells; a 16 images Drosophila melanogaster Kc167 dataset containing 1255 cells, stained for DNA and actin. Both image datasets present a difficult problem due to the high variability of cell shapes and frequent cluster overlap between cells. On the Drosophila dataset our approach achieved a precision/recall of 95%/69% and 82%/90% for nuclei and cytoplasm detection respectively and an overall accuracy of 76%.
Collapse
Affiliation(s)
- Pedro Quelhas
- Instituto de Engenharia Biomédica (INEB), 4200-465 Porto, Portugal.
| | | | | | | |
Collapse
|