Institute of Microbiology

T - Frequently Asked Questions


When training (clicking on the objects) the object borders should be visible before the click, otherwise it is just a guess what will be included in the object that I click.

Such an option indeed exists. If one navigates in the "Main Window" to the drop down menu "Display" selects and "Show all cells", one can select of four existing options how all objects within that image could be displayed: as shadows, as white outlines, as white rectangles or not at all. The "shadow" option can also be activated by pressing CTRL-V.


Is a "Save data" click necessary after each image?

Yes, only after pressing "Save data" any objects are memorized. With the other existing options to navigate through images no object data are saved.


In SVM training, the "Objects from current session" buttons don't work.

In this part of the graphical user interface (upper left part of SVM-window) the objects trained by the user are divided into a training part and a validation part. This can be done either by moving the slider or by typing a number into the box "Number objects training". The remaining objects will automatically be part of the validation data set. The other boxes just show numbers and cannot be modified.

Defining and Generating the Output

Can you explain clearly what is meant by a vector?

Vectors are important for summarizing and integrating data. They are defined in the "Adjust Output" window. A Enhanced CellClassifier vector is always binary (contains only the values zero or one). Vectors are calculated image wise and belong to a parent object. A vector contains as many elements as objects of this kind exist on a given image. The number of vectors that can be defined is not limited.

One example might make this clearer: If an image contains 10 nuclei. The user could define a vector "mitotic_nuclei". This vector would have as its parent CellProfiler object "nuclei", and would look initially as follows: 1; 1; 1; 1; 1; 1; 1; 1; 1; 1. One could now use the information from a classifier trained to distinguish mitotic nuclei. If nuclei 2, 6 and 10 would be mitotic, the resulting vector "mitotic_nuclei" would be 0; 1; 0; 0; 0; 1; 0; 0; 0; 1.


Wichtiger Hinweis:
Diese Website wird in älteren Versionen von Netscape ohne graphische Elemente dargestellt. Die Funktionalität der Website ist aber trotzdem gewährleistet. Wenn Sie diese Website regelmässig benutzen, empfehlen wir Ihnen, auf Ihrem Computer einen aktuellen Browser zu installieren. Weitere Informationen finden Sie auf
folgender Seite.

Important Note:
The content in this site is accessible to any browser or Internet device, however, some graphics will display correctly only in the newer versions of Netscape. To get the most out of our site we suggest you upgrade to a newer browser.
More information

© 2015 Microbiology ETH Zürich | Imprint | Disclaimer | 23 December 2009