Back

Volumetric Segmentation of Cell Cycle Markers in Confocal Images

Khan, F. A.; Voss, U.; Pound, M. P.; French, A. P.

2019-07-23 plant biology
10.1101/707257 bioRxiv
Show abstract

I.AO_SCPCAPBSTRACTC_SCPCAPUnderstanding plant growth processes is important for many aspects of biology and food security. Automating the observations of plant development - a process referred to as plant phenotyping - is increasingly important in the plant sciences, and is often a bottleneck. Automated tools are required to analyse the data in images depicting plant growth. In this paper, a deep learning approach is developed to locate fluorescent markers in 3D timeseries microscopy images. The approach is not dependant on marker morphology; only simple 3D point location annotations are required for training. The approach is evaluated on an unseen timeseries comprising several volumes, capturing growth of plants. Results are encouraging, with an average recall of 0.97 and average F-score of 0.78, despite only a very limited number of simple training annotations. In addition, an in-depth analysis of appropriate loss functions is conducted. To accompany [the finally-published] paper we are releasing the 4D point annotation tool used to generate the annotations, in the form of a plugin for the popular ImageJ (Fiji) software. Network models will be released online.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.