FIGURE SUMMARY
Title

EmbryoMiner: A new framework for interactive knowledge discovery in large-scale cell tracking data of developing embryos

Authors
Schott, B., Traub, M., Schlagenhauf, C., Takamiya, M., Antritter, T., Bartschat, A., Löffler, K., Blessing, D., Otte, J.C., Kobitski, A.Y., Nienhaus, G.U., Strähle, U., Mikut, R., Stegmaier, J.
Source
Full text @ PLoS Comput. Biol.

Different possibilities to visualize 3D+t cell tracking data.

(A) Temporally scrollable maximum intensity projection with superimposed centroids of detected cell nuclei (red dots) allows following development over time. (B) Similar to the maximum intensity projections, detected nuclei can be superimposed on interactive 3D volume rendering of the original data. (C) Tracks of all cells can be analyzed from arbitrary orientations in an interactive and highly responsive 3D visualization using plain colors (C1) or quantitative trajectory features (C2, color-code indicates time). The panels show neural crest cells of a zebrafish embryo at 20 hpf (A, B) and the trajectories spanning the entire experimental duration from 12.5 − 28 hpf (C). Scale bar: 100 μm.

Feature-based extraction of groups of interest.

(A) Quantitative features associated with each of the cell tracks allows feature-based selections. The left and right part of an embryo was separated along the anteroposterior axis using the end point coordinates of each track. (A1) and (A2) show the identified groups of ∼1400 neural crest cells as a scatter plot (x coordinate of the trajectory end points versus the unique track ID) and a 3D rendering of all trajectories. (B) Cluster algorithms can be used to automatically group the data. The example shows four identified clusters using the end point locations in the XY-plane at a selected time point as a 3D rendering (B1) and a scatter plot (B2). (C) Special trajectory features can be used to characterize particular cell movements in the early embryo. (C1) schematically illustrates the ratio of effective displacement (distance between start and end point) versus the spatial length (integrated path length) that was used to automatically identify two clusters corresponding to hypoblast cells (magenta) and epiblast cells (green) visualized as scatter plot (C2) and 3D rendering (C3). Panels (A) and (B) show neural crest cells of a zebrafish embryo (12.5 − 28 hpf) and panel (C) is based on a slice cut from a whole-embryo zebrafish data set (5 − 7.25 hpf). Scale bar: 100 μm.

Interactive selection possibilities complement the automatic feature-based group selections.

Tracking data from cranial neural crest cells of a zebrafish embryo during 14-20 hpf are shown. (A) All visualization windows allow selecting groups of interest using freehand selection tools. From the left: maximum intensity projection overlay of the raw images and cell centroids for two time points of the neural crest data set at 12.5 hpf and 14 hpf (A1, A2); tracks of all cells in 3D (A3); subset of selected tracks in 3D (A4); scatter plot of track-based features (A5). All visualization windows (A1-A5) are synchronized to obtain consistent selections in all views (see corresponding color-code of panels A1-A5). (B) Exemplary manual selection of a group of interest. Freehand selection tools allow intuitive and interactive selection/deselection of groups of interest. (C) All performed selection steps can be recorded in a hierarchical selection tree view and arbitrary nodes of the tree can be combined to new groups of interest. The hierarchical selection tree view serves as a template to reproduce a particular selection on other data sets including the possibility of refinements to adapt to biological variation of different data sets. The panels show neural crest cells of a zebrafish embryo (12.5 − 28 hpf). Scale bar: 100 μm.

Steps that were performed for extracting hypoblast cells in four different wild-type zebrafish embryos with developmental time ranging from 2–14 hpf (A).

The knowledge discovery process was designed interactively on Embryo 01. First, the embryo was filtered temporally (5–7.25 hpf) and spatially (region around the blastoderm margin) to focus on the region of interest (B, C). The two groups of cells were separated using a feature-based clustering approach (D-F). The whole analysis pipeline was then applied to Embryos 02-04 resulting in the extraction of the same internalizing cells in all embryos. The color code in panels (A-E) indicates time from 2–14 hpf and the group association to hypoblast (magenta) or epiblast (green) in panel (F).

Interactive tracking correction of neural crest cells of a zebrafish embryo.

(A) To analyze the precursors of the olfactory epithelium, a particular subgroup of neural crest cells of a zebrafish embryo, a set of about 100 cells was interactively selected at 23 hpf (blue). The corrected tracks are shown in the global context (B) as well as in isolation using time for coloring (C). Scale bar: 100 μm.

Preprocessing steps to automatically detect, segment and track fluorescently labeled nuclei in light-sheet microscopy images of a zebrafish embryo.

(A) Maximum intensity projection of a single time point of an entire zebrafish embryo at early somitogenesis stages [11, 66]. (B) Maximum intensity projection of a 3D light-sheet microscopy image with superimposed centroids of detected cell nuclei in red. (C) Volume rendering of segmented cell nuclei using a random color code. (D) Exemplary movement paths for 25 arbitrarily selected neural crest nuclei of a zebrafish embryo that were automatically tracked using a nearest neighbor algorithm [58, 59]. Dorsal view of the anterior half of the embryo (anterior up). All data sets were aligned prior to the analysis, to obtain a common reference orientation. (E) Whole-embryo data sets were oriented such that the animal-vegetal axis was aligned with the y-axis (animal pole on the positive y-axis) and the dorsoventral axis was aligned with the x-axis (dorsal part on the positive x-axis). (F) The embryos highlighting neural crest cells were oriented such that the anteroposterior axis formed a left-right symmetry axis with the head region on the positive y-axis (dorsal view, anterior up). Circled regions in (F) indicate the positions of the prospective eyes and the olfactory epithelium of the embryo, respectively. The green rectangle in panels (A) and (E) indicates the neural crest cell region visualized in (F). Panels (A)-(D) were adapted from [67] and panel (E) was adapted from [11]. Scale bar: 100 μm.

Interactive and semi-automatic strategies to correct and analyze fragmented cell tracks.

(A) Erroneous tracks can be interactively repaired to obtain a set of corrected full-length tracks. The curation mode features interactive maximum intensity projections and 3D volume rendering with superimposed cell tracks. Moreover, link candidate predictions and different curation modes like breadth-first or depth-first curation strategies minimize the required manual correction effort. (B-F) As an alternative to manually correcting the entire tracking database, we propose to select only a subset of sufficiently long tracks (B, e.g., select only tracks spanning over 70% of the time interval of interest), to perform the region of interest selection on these corrected tracks (C-E) and to finally assign all unlabeled tracks to the predominating group of their spatiotemporally nearest neighbors (F). Panel (A) shows a C. elegans embryo of the Cell Tracking Challenge that was imported to EmbryoMiner (data set by the Waterston lab, The George Washington University, Washington D.C., USA) [24, 36] and panels (B-F) show cropped regions of a whole-embryo zebrafish data set (S2 Note).

Acknowledgments
This image is the copyrighted work of the attributed author or publisher, and ZFIN has permission only to display this image to its users. Additional permissions should be obtained from the applicable author or publisher of the image. Full text @ PLoS Comput. Biol.