> For the complete documentation index, see [llms.txt](https://docs.owkin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.owkin.com/connect-and-integrate/pathology-explorer-mcp-ai-powered-tissue-analysis/use-pathology-explorer-in-k-pro.md).

# Use Pathology Explorer in K-Pro

Pathology Explorer is built into K-Pro. There is nothing to connect or install: ask a question about H\&E slides in the chat, and K-Pro calls Pathology Explorer when your question needs it.

### What you can do

* **Find cohorts and slides:** list the available cohorts, then sort slides by any histomics feature, for example the slides with the highest lymphocyte density.
* **Look at slides:**
  * Slide thumbnails.
  * An interactive whole-slide viewer: pan, zoom, and go fullscreen. Tiles stream as you move, so large slides open in seconds.
  * Tile mosaics with the model's cell predictions overlaid.
* **Quantify the tissue:** slide-level histomics features (cell counts and densities, nuclear morphology, region-specific densities, cell–cell co-occurrence, TIL diffusivity) and summary statistics for a cohort. See Understanding Pathology Explorer's analysis capabilities for every feature.
* **Ask custom questions of the feature tables:** when no built-in tool fits your question, K-Pro can query the H\&E feature tables directly.
* **Run survival analyses:** interactive Kaplan-Meier curves with 95% confidence intervals, for overall or progression-free survival, stratified by a histomics feature. Survival times are reported in years.
* **Export the data:** download histomics features as a Parquet file for your own analyses.

Because Pathology Explorer runs in the same chat as K-Pro's other analyses, you can move from a slide-level finding to a follow-up question without switching tools.

### Available cohorts

| Cohort          | Slides | Notes                                                                                                                                           |
| --------------- | ------ | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| 26 TCGA cohorts | —      | See the full list. Both `TCGA_LUAD` and `TCGA-LUAD` work.                                                                                       |
| IBDColEpi       | 132    | Colon biopsies from patients with inflammatory bowel disease. There is no survival data, so survival analysis is not available for this cohort. |

To see what is available to you, ask:

```
List the available pathology cohorts.
```

### Example prompts

**Find a slide and open it**

```
In TCGA_LUAD, find the slide with the highest lymphocyte density and open it in the slide viewer.
```

**Look at the cells**

```
For that slide, show the tiles with the most cancer cells, with the cell predictions.
```

**Run a survival analysis**

```
In TCGA_BLCA, is plasmocyte density associated with overall survival?
```

**Describe a cohort**

```
Give me summary statistics of neutrophil density across TCGA_STAD slides.
```

**Explore inflammation**

```
In IBDColEpi, which slides have the highest neutrophil density? Show their thumbnails.
```

**Export the features**

```
Export the histomics features for TCGA_LUAD as a Parquet file.
```

{% hint style="info" %}
You can also use Pathology Explorer outside K-Pro, from Claude. See Use Pathology Explorer in Claude.
{% 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.owkin.com/connect-and-integrate/pathology-explorer-mcp-ai-powered-tissue-analysis/use-pathology-explorer-in-k-pro.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.