> 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/analysis-and-results/results-dashboard-overview.md).

# Results dashboard overview

*What you'll get: a tour of a result page: its tabs, the filter bar, the plot and image viewer, and the comparison chart.*

Every analysis has its own result page. To open it, go to **Analysis** in the sidebar and click the result, or choose **Open** from the row's **⋯** menu. A finished result opens on its **Dashboard** tab.

## The tabs

* **Label**: only for AI-assisted analyses. This is where you label the objects.
* **Dashboard**: the interactive data view described on this page.
* **Export data**: downloads of your results. See [Download results and reports](https://docs.biodock.ai/analysis-and-results/download-results-and-reports.md).
* **Edit objects**: the object editor. See [Editing objects (QC)](https://docs.biodock.ai/analysis-and-results/editing-objects-qc.md). Not every result has it, and AI-assisted analyses don't.
* **Job details**: the model and parameters the job ran with, the progress of each image, and when it started and finished. Not shown for AI-assisted analyses.
* **Share**: shown if you can share the result.

While a job is still running, and for an archived result, only **Job details** and **Share** are shown.

{% hint style="info" %}
Results from jobs that ran before 2023, and classification results, open the classic dashboard inside the same page. Their **Export data** tab offers the older whole-job downloads.
{% endhint %}

The **Dashboard** tab has a header with the number of objects, images and classes, the start date and the status. Below it are the filter bar, the **Segmentation data** card (a plot and an image viewer) and the **Comparison data** card.

## Filter bar

The filter bar decides which objects the rest of the dashboard shows.

![The result page tabs, summary and filter bar](https://3806122466-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fk3DfNQKoMy1JXdaDLvpG%2Fuploads%2Fgit-blob-c95eaaf874ab72ba91644294ace2bce7717908c4%2Fv2-results-top.png?alt=media)

1. **View** groups the results:
   * **Group**: by image group, which means the folders you picked when you ran the analysis. Pick the groups to include; each shows how many files it holds.
   * **Image**: one image at a time.
   * **Parent obj.**: one parent object at a time, such as one organoid and the cells inside it. Only offered when the results have parent objects (see [Class hierarchy](https://docs.biodock.ai/projects-and-models/configuring-your-model.md#class-hierarchy)).
2. **Classes**: click a class to show or hide its objects.
3. **Populations**: **Create population** makes a gated population, and the populations button (for example **All populations selected**) opens the population tree, where you choose which populations to show. See [Populations (gating)](https://docs.biodock.ai/analysis-and-results/filters-like-flow-cytometry.md).

## Segmentation data card

This card holds the plot on the left and the image viewer on the right. Below them, it shows the measurements of the object you selected.

![The Segmentation data card: scatter plot and image viewer](https://3806122466-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fk3DfNQKoMy1JXdaDLvpG%2Fuploads%2Fgit-blob-1bd854d849c2011c822da4c31342dddbe69d02cc%2Fv2-results-segmentation-card.png?alt=media)

### Plot

* Choose **Scatter** or **Histogram**.
* Below the plot, change the **X** and **Y** axes (and a **Color** axis) of the scatter plot, or the **X** axis of the histogram. The **Selection** row shows how many objects are in view.
* Click any dot to select that object. Biodock opens its image in the viewer and shows the object's measurements. **Copy data** copies them.

<figure><img src="https://3806122466-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fk3DfNQKoMy1JXdaDLvpG%2Fuploads%2Fgit-blob-603e10a4b3401708f8c441da4b01bd02930db57d%2Fdocs-results-click-a-dot.gif?alt=media" alt="Set X to Area on the scatter plot, click a dot far to the right, the image viewer jumps to that object and the Object card shows its Area"><figcaption><p>Set <strong>X</strong> to <strong>Area</strong>, then click an outlying dot to see that object in the viewer.</p></figcaption></figure>

Setting **X** to **Area** and clicking the largest objects is a quick way to find debris and objects that were merged by mistake.

### Image viewer

The viewer shows the images with an outline around each object. Scroll to zoom and drag to move. Click an object to select it and see its measurements.

* **Outlines** shows or hides the outlines. Holding **Shift** hides them for a moment.
* **Channels** shows or hides channels and changes brightness and contrast. This only changes the view, not the results.
* **Download** saves the image you are viewing, with its outlines. See [Download results and reports](https://docs.biodock.ai/analysis-and-results/download-results-and-reports.md#overlay-images).
* The **⋯** (More actions) menu has **Import to project**, which adds this image's predictions to a project as labels. See [Correcting results to improve your model](https://docs.biodock.ai/analysis-and-results/correcting-results-to-improve-your-model.md).
* The **On-demand** row offers **Enter viewer**, then **Generate for viewport**, to draw the outlines for just the area you are looking at. It is useful on very large images. **Exit** leaves it.

To change objects, use the **Edit objects** tab.

## Comparison data card

This card shows bar charts that compare image groups, images or parent objects, depending on the **View** you picked. Choose the measurement with the **Y** dropdown: object count, area, shape and intensity measurements, and any others the model computes. Tick **Show std. dev** to add standard deviation bars.

![The Comparison data card](https://3806122466-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fk3DfNQKoMy1JXdaDLvpG%2Fuploads%2Fgit-blob-91df7469209327d00be8235e23f53df703574db8%2Fv2-results-comparison-card.png?alt=media)

Check the **Image** view as well as the **Group** view. An image with far fewer objects than its neighbours may be out of focus, and you want to know that before you trust a group average.

If your images were set up as a well plate, the dashboard also shows the results on the plate.

## Large results

* Above 250,000 objects, the plots show a random sample of 250,000 objects, and a message says so.
* Above 10 million objects, only the comparison data is shown. Download the full results from **Export data**.
* Above 250,000 objects in one image, the viewer may only outline a few classes. Zoom in and use the on-demand viewer to see every object.

Exports always include every object.

{% hint style="info" %}
Measurements such as area are in pixels, unless the image file carried a pixel size when it was uploaded. A pixel size cannot be entered afterwards.
{% endhint %}


---

# 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/analysis-and-results/results-dashboard-overview.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.
