> For the complete documentation index, see [llms.txt](https://docs.biodock.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.biodock.ai/projects-and-models/measurement-reference.md).

# Measurement reference

*What you'll get: what each measurement (metric) a model can compute for an object means. To choose which ones your model computes, see* [*Configuring your model*](https://docs.biodock.ai/projects-and-models/configuring-your-model.md#measurements-metrics)*.*

Measurements are in pixels, unless the image file carried a pixel size when it was uploaded. Positions are in pixels of the whole image.

## Common measurements

* **X and Y Positions**: the X and Y pixel position of the object's centre (two measurements), in the whole image. On by default.
* **Area**: the number of pixels the object covers. Holes in the object are not counted. On by default.
* **Perimeter**: the number of pixels along the object's outer boundary.
* **Average Channel Intensities**: the average intensity of each channel over the object. An image with N channels gives N measurements, shown in your results as **Average Intensity (channel N)**.
* **Integrated Channel Intensities**: the total intensity of each channel over the object, one measurement per channel.
* **Solidity**: how convex the object is: its pixels divided by the pixels of its convex hull (the smallest convex shape around it). 1 means no dents.
* **Eccentricity**: how elongated the object is. A perfect circle has an eccentricity of 0.
* **Length of Major Axis**: the length of the long axis of the ellipse that best fits the object. A good stand-in for the object's longest width.
* **Length of Minor Axis**: the length of the short axis of that ellipse. A good stand-in for the object's shortest width.
* **Curved Length**: the length of a long, curved object (such as a worm or a neurite), measured along its skeleton. Not useful for round objects.
* **Model Score**: the model's confidence in the object, usually from 0 to 1. Object classes only.

## Less common measurements

* **Equivalent Diameter Area**: the diameter of a circle with the same area as the object.
* **Euler Number**: the number of objects minus the number of holes in them.
* **Extent**: the object's pixels divided by the pixels of its bounding box.
* **Feret Diameter Maximum**: the longest distance between two points on the object's convex hull.
* **Orientation**: the angle of the object's long axis.
* **Perimeter Crofton**: the perimeter estimated with the Crofton formula in 4 directions.
* **Area Bounding Box**: the number of pixels in the object's bounding box.
* **Area Convex**: the area of the object's convex hull.
* **Area Filled**: the area of the object with all its holes filled in.

## Measurements with settings

These need settings under **Parameters** before they are computed. See [Metrics with parameters](https://docs.biodock.ai/projects-and-models/configuring-your-model.md#metrics-with-parameters).

* **Colocalization: Pearson**: the correlation between two channels over the object, for each pair of channels you choose. Images with 2 or more channels only.
* **Colocalization: Manders**: the overlap between two channels over the object, for each pair of channels you choose. Images with 2 or more channels only.
* **Area threshold**: in one channel, after the brightness and contrast you set, how much of the object is above (or below) a threshold, as a percentage or in pixels. Use it to measure the positive area of a stain.

## Measurements added by hierarchies

A [class hierarchy](https://docs.biodock.ai/projects-and-models/configuring-your-model.md#class-hierarchy) can add:

* **Parent ID** on each child object: the object ID of the parent it sits in.
* **Number of&#x20;*****child*****&#x20;within&#x20;*****parent*** on each parent object: how many children overlap it by more than the overlap threshold.
* ***Child*****&#x20;overlap with&#x20;*****parent*** on each parent object: the share (0–1) of the parent's area covered by children.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.biodock.ai/projects-and-models/measurement-reference.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
