Computer vision applied to biological microscopy images

The number of neurons of the brain is not fixed at birth. Neurons keep being produced throughout life in some regions of the brain: among which the dentate gyrus of the hippocampus. Adult neurogenesis has a physiological relevance, newborn neurons are integrated in circuits and this plasticity of circuits seems to be important for forgetting memories. It is however unclear how new neurons are produced in the adult hippocampus. Biologists are setting up experimental techniques to follow the production of neurons by time-lapse microscopy in living mice and can now directly address the genealogy of newborn neurons and their function (images kindly provided by Gregor Pilz and Sara Bottes).

One challenge is the image analysis of these datasets. This workgroup is aimed at gaining image analysis experience by working with real biological images. We will try out standard computer vision and image analysis methods to automatically segment cells in microscopy images and in a second time extract relevant features for cell classification in different types. Depending on these first results we might also try deep neural networks. Previous knowledge in biology / computer vision image processing is not required and people willing to learn more about these topics are encouraged to join.

If you have any question, do not hesitate to contact me.
Successful participation in this workgroup will be rewarded with Margaritas ;)

Login to become a member send


Day Time Location
Tue, 26.04.2016 21:00 - 22:00 Lecture room
Thu, 28.04.2016 21:00 - 22:00 Sala Panorama
Mon, 02.05.2016 21:00 - 22:00 Sala Panorama
Tue, 03.05.2016 14:00 - 15:00 Sala Panorama
Thu, 05.05.2016 14:00 - 15:00 Terrasse
Fri, 06.05.2016 15:00 - 17:00 Terrasse


How is the pool of adult Neural Stem cells maintained thoughrout life to keep producing neurons that will be integrated in the hippocampus? These newborn neurons are important for learning new memories, forgetting. Neurogenesis is activated by physical activity, espacially running in mice and inhibited in the case of depression or stress (antidepressor drugs promote neurogenesis).

Biologist have developped 2-photon microscopy methods to follow the fate of neural stem cells and their progeny in vivo. The bottleneck of the pipline is the image processing, We worked on developing image processing methods to automatically segment cells from the pictures.


Session1_1.jpgSession 1

In the first session I told you about the experimental paradigm biologist are setting up to directly address the production of neurons in the adult hippocampus. They are using two photon microscopy to directly image neural stem cells and their progeny in living mice. From previous indirect experiments we have an idea about the rough genealogical relationships between Neural Stem cells, astrocytes, neuronal precursors, neuroblasts and neurons. The dataset of images allow us to directly address the question by observing the transitions (cf image of the first session).

The image dataset is composed of 63 time series (called spots) with dimensions x,y,z,t. Pictures are composed of 512x512 pixels (corrsponding to 0.5x0.5microns), 30 to 60 z (number variables betweens spots and also between time points within a spot, black frames have been added so that every time point of a serie has the same number of z), 4 to approximatively 18 time points, which makes a total number of cells of about 10 000 pictures all taken together.


- segments cells from the background, on the 3D stack or on a smart projection of the z images

- classify cells based on their morphology to identify different types (cf Bonaguidi et al, review). First try some simple clustering methods (k-mean...)

- try to automatize the cell tracking in time

We agreed on first trying simple method of image processing. Someone pointed to the Point Cloud Library that might be useful to visualize the data in 3D and try out some algorithms already implemented.

We can also try some convolution neural networks.

Montage_519_Spot3.jpgImage sample

Example of a movie (Here all z planes have been collapsed). Images kindly provided by Gregor Pilz and Sara Bottes (HIFO, Zurich).

Icon Review cell morphology (2.4 MB)

Icon Clonal analysis initial paper (2.4 MB)


Methods for 3D segmentation:

- 1st method: simple method taking advantage of the image properties: high contrast. Uses exponential filter.

Drawback: uses K-mean clustering, so one needs to define beforehand how many cells we expect in the picture.


- 2nd method: gradient based (central difference gradient), find centroids in 3D



- improve the segmentation of the dendrites

- define a metric to compare the quality of the different methods compared to a human expert ground truth.


Next steps:

Train an SVN or a CNN to learn features specific for each cell type (Neural Stem Cells, precursors, neuroblasts, neurons)

Develop a GUI for the biologists to easily correct the automatically segmented cells





Original picture (maximum projection)


Method 1 : 3D segmentation only by thresholding



Method 2: gradient based segmentation


Segmented cells on the original picture


Segmented cells, edges are shown.


Individual segmented cells


Marion betizeau
Manu Nair


Adam Arany
Marion betizeau
Enrico Calabrese
Lukas Cavigelli
Richard George
siohoi ieng
Marina Ignatov
vincent lorrain
Gabriela Michel
Manu Nair
Felix Neumärker
Guido Novati
Francesca Puppo
Jaak Simm
Valentina Vasco
Nikolaos Vasileiadis
Borys Wrobel
Qi Xu