> For the complete documentation index, see [llms.txt](https://medomicslab.gitbook.io/medomics-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://medomicslab.gitbook.io/medomics-docs/v1-fr/tutorials/design/extraction-modules.md).

# Module d'extraction

{% hint style="warning" %}
Tous les composants du module d'extraction sont actuellement désactivés car ils n'ont pas passé tous les contrôles de stabilité.
{% endhint %}

Le *Module d'extraction* est divisé en quatre composants. Les trois premiers sont des pages consacrées à des processus d'extraction simples sur différents types de données (images, notes textuelles et séries temporelles) utilisant des modèles pré-entraînés et/ou *bibliothèques* Python [*Le quatrième composant est*](https://medimage.readthedocs.io/en/latest/index.html)MEDimage *bibliothèques* , qui est l'implémentation d'un

{% hint style="info" %}
package open-source conçu pour le traitement d'images médicales et l'extraction de caractéristiques radiomiques. [Dans la vidéo ci-dessous, l'étude "HAIM" fait référence à](https://www.nature.com/articles/s41746-022-00689-4)
{% endhint %}

{% embed url="<https://youtu.be/eNKN7H9nwjc?si=zzTJjwQgApcLwKxu>" %}
<https://www.nature.com/articles/s41746-022-00689-4https://github.com/mlmed/torchxrayvisionhttps://physionet.org/content/mimic-iv-demo/2.2/>
{% endembed %}

**Tutoriel vidéo du module d'extraction**

* [00:00](https://www.youtube.com/watch?v=eNKN7H9nwjc\&t=0s) Contenu&#x20;
* [00:50](https://www.youtube.com/watch?v=eNKN7H9nwjc\&t=50s) Aperçu&#x20;
* [04:24](https://www.youtube.com/watch?v=eNKN7H9nwjc\&t=264s) Extraction d'images
* [08:29](https://www.youtube.com/watch?v=eNKN7H9nwjc\&t=509s) Extraction de séries temporelles&#x20;
* [10:48](https://www.youtube.com/watch?v=eNKN7H9nwjc\&t=648s) Extraction de texte

**Dernier mot**

* Données [Physionet :](https://physionet.org/)&#x20;
* <https://physionet.org/> [Base de données de démonstration MIMIC-IV :](https://physionet.org/content/mimic-iv-demo/2.2/)&#x20;
* <https://physionet.org/content/mimic-iv-demo/2.2/> [MIMIC-IV-Note :](https://physionet.org/content/mimic-iv-note/2.2/)&#x20;
* <https://physionet.org/content/mimic-iv-note/2.2/> [MIMIC-IV-CXR :](https://physionet.org/content/mimic-cxr-jpg/2.0.0/)&#x20;
* <https://physionet.org/content/mimic-cxr-jpg/2.0.0/> [Étude de Soenksen et al. :](https://www.nature.com/articles/s41746-022-00689-4)&#x20;

**<https://www.nature.com/articles/s41746-022-00689-4>**

* Outils d'extraction [TorchXRayVision :](https://github.com/mlmed/torchxrayvision)
* <https://github.com/mlmed/torchxrayvision> [TSfresh :](https://tsfresh.readthedocs.io)&#x20;
* <https://tsfresh.readthedocs.io> [BioBERT :](https://arxiv.org/abs/1901.08746)
* <https://arxiv.org/abs/1901.08746> [Poids BioBERT :](https://github.com/EmilyAlsentzer/clinicalBERT)&#x20;

***

{% content-ref url="/pages/5f492f073cdf3920642fe47ed7539c2addf80d8a" %}
[Page d'extraction d'images](/medomics-docs/v1-fr/tutorials/design/extraction-modules/image-extraction-page.md)
{% endcontent-ref %}

{% content-ref url="/pages/5e146cd052979069c33cba31638194c60bda6697" %}
[Page d'extraction de texte](/medomics-docs/v1-fr/tutorials/design/extraction-modules/text-extraction-page.md)
{% endcontent-ref %}

{% content-ref url="/pages/052021c719b73ccfe2843d368c6d7a50d9f95f68" %}
[Page d'extraction de séries temporelles](/medomics-docs/v1-fr/tutorials/design/extraction-modules/time-series-extraction-page.md)
{% endcontent-ref %}

{% content-ref url="/pages/732c01f649704d3796a516e18d723bbb3c0d0376" %}
[MEDimage](/medomics-docs/v1-fr/tutorials/design/extraction-modules/medimage.md)
{% endcontent-ref %}


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://medomicslab.gitbook.io/medomics-docs/v1-fr/tutorials/design/extraction-modules.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.