During the prediction, IKOSA AI applications will assign an ID to each and every found object that is listed in the analysis job results. These The IDs not only determine the order in which the instance are listed of objects in the CSV or XLSX output , they can also help finding the instance but also aid in locating objects within the visualization.

This page documents explains the peculiarities of instance numbering within unique aspects of the way object numbering works in the visualizations.

Order of the

...

objects on small images

The instances objects on small images (smaller than a “tile“, “tile” more on this under in the next pointfollowing section) are ordered by a line-dominant scheme. This means the image is read line by line and from left to right when numbering the instancesobjects. The object’s relevant point for the instance is the upper left corner of its bounding box. Simplified, this can be imagined like this:

...

Object order on large images

Large images are split into “tiles“ within the application . On into tiles (dashed line on the image below). The numbering on each of those tiles the numbering is follows a line-dominant as described abovepattern (described in the previous section). However, neighbouring neighboring tiles are numbered in sequence from left to right and top to bottom. This can result in a pattern like the one below.

...

The default tile size for IKOSA AI Applications is 2048 x 2048 Pixels. So, if your image is larger more significant than 2048 Pixels in any direction, expect your instance object numbering to follow this presented pattern.

Numbers are omitted on small

...

objects

When labelling labeling small instancesobjects, at some point the instance id overlaps with too much of the instance - basically hiding the instance behind its own , their IDs hide them behind their index visualization. To avoid this, a visualization threshold for the instance object number exists. By default, Numbers will not be displayed if the numbers' bounding box is more than over 5 times larger than the instance area, the number is not displayedobject area.

Limit

...

the number of

...

objects to be numbered at all

When predicting instances objects on very large images or whole slide images (WSI), the predicted number of instances can be more than can exceed what can be reasonably analyzed visually. And as the instances with very large indices would need to be very large to actually have a displayed number (see previous point) there There is a maximum number of instances objects until when which the instance object numbers for all instances are displayed.of them will be displayed. The reason for this is that objects with high indices would require a large size to display their value.

By default, this number threshold is 100.000 instancesobjects. So, if your prediction contains more than 100k instancesthat, no instance object number will be shown in the visualization at all..

...

If you still have questions regarding your application training, feel free to send us an email at support@ikosa.ai. Copy-paste your training ID in the subject line of your email.

...

📚 Related articles