Active Graph Matching for Automatic Joint Segmentation and Annotation of C. elegans

Kainmueller, Dagmar; Jug, Florian; Rother, Carsten; Myers, Gene

doi:10.1007/978-3-319-10404-1_11

Cited by 33 publications

(38 citation statements)

References 9 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to annotate the neurons based on their positions, the information of the positions and their variations will be required. Long et al (Long et al 2008(Long et al , 2009) produced 3D digital atlas for 357 out of 558 cells from several tens of L1 animals, and related works also used the atlas (Qu et al 2011;Kainmueller et al 2014). The atlas consists of positions and their deviations of the cell nuclei of body wall muscles, intestine, pharyngeal neurons, and neurons posterior to the retrovesicular ganglion, as well as some other cell types.…”

Section: Introductionmentioning

confidence: 99%

An annotation dataset facilitates automatic annotation of whole-brain activity imaging ofC. elegans

Toyoshima

Kanamori

et al. 2019

Preprint

View full text Add to dashboard Cite

Annotation of cell identity is an essential process in neuroscience that allows for comparing neural activities across different animals. In C. elegans, although unique identities have been assigned to all neurons, the number of annotatable neurons in an intact animal is limited in practice and comprehensive methods for cell annotation are required. Here we propose an efficient annotation method that can be integrated with the whole-brain imaging technique. We systematically identified neurons in the head region of 311 adult worms using 35 cell-specific promoters and created a dataset of the expression patterns and the positions of the neurons. The large positional variations illustrated the difficulty of the annotation task. We investigated multiple combinations of cell-specific promoters to tackle this problem. We also developed an automatic annotation method with human interaction functionality that facilitates annotation for whole-brain imaging. (137 words)

show abstract

Section: Introductionmentioning

confidence: 99%

An annotation dataset facilitates automatic annotation of whole-brain activity imaging ofC. elegans

Toyoshima

Kanamori

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Instances are densely connected graphs with 20 -60 nodes. The third one is the novel worms datasets [38], containing 30 problem instances coming from bioimaging. The problems are made of sparsely connected graphs with up to 600 nodes and up to 1500 labels.…”

Section: Graph Matchingmentioning

confidence: 99%

A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems

Swoboda

Kuske

Savchynskyy

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a general dual ascent framework for Lagrangean decomposition of combinatorial problems. Although methods of this type have shown their efficiency for a number of problems, so far there was no general algorithm applicable to multiple problem types. In this work, we propose such a general algorithm. It depends on several parameters, which can be used to optimize its performance in each particular setting. We demonstrate efficacy of our method on graph matching and multicut problems, where it outperforms state-of-the-art solvers including those based on subgradient optimization and off-the-shelf linear programming solvers.

show abstract

“…There are many works addressing the task of nuclei segmentation in bio-image analysis. Methods based on classical computer vision include automatic thresholding [17,19] combined with morphological operations, marker-controlled watershed [16,27], active contours and level sets [9,14], and model-based approaches such as the generalized hough transform [12,3]. More recently, Deep Learning has dominated the field of semantic segmentation [15,20], including instance segmentation [7,2], whenever a large amount of annotated training data is available.…”

Section: Related Workmentioning

confidence: 99%

Bots for Software-Assisted Analysis of Image-Based Transcriptomics

Cicconet

Hochbaum

Richmond

et al. 2017

Preprint

View full text Add to dashboard Cite

We introduce software assistants -bots -for the task of analyzing image-based transcriptomic data. The key steps in this process are detecting nuclei, and counting associated puncta corresponding to labeled RNA. Our main release offers two algorithms for nuclei segmentation, and two for spot detection, to handle data of different complexities. For challenging nuclei segmentation cases, we enable the user to train a stacked Random Forest, which includes novel circularity features that leverage prior knowledge regarding nuclei shape for better instance segmentation. This machine learning model can be trained on a modern CPUonly computer, yet performs comparably with respect to a more hardware-demanding state-of-the-art deep learning approach, as demonstrated through experiments. While the primary motivation for the bots was image-based transcriptomics, we also demonstrate their applicability to the more general problem of scoring "spots" in nuclei.

show abstract

Active Graph Matching for Automatic Joint Segmentation and Annotation of C. elegans

Cited by 33 publications

References 9 publications

An annotation dataset facilitates automatic annotation of whole-brain activity imaging ofC. elegans

An annotation dataset facilitates automatic annotation of whole-brain activity imaging ofC. elegans

A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems

Bots for Software-Assisted Analysis of Image-Based Transcriptomics

Contact Info

Product

Resources

About