> For the complete documentation index, see [llms.txt](https://docs.imerit.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.imerit.net/data/importing-assets/importing-reference-medical-data-during-asset-import.md).
# Importing Reference Medical Data During Asset Import
You may upload reference medical data (.nrrd, .nifti) which users will be able to switch to during annotation.
## How to Import Reference Medical Data
Prepare a JSON like the following, where the URL in the `data` property points to the main medical asset to annotate, and the URLs in the `overlay` list point to the assets to use as reference. The order of the URLs will determine the order in which references will be presented to the annotator in the dropdown.
The following JSON will import one asset with three references:
```json
[
{
"data": "https://example.com/assets/medical/nrrds/0522c0419.nrrd",
"overlay": [
"https://example.com/assets/medical/nrrds/CT-chest.nrrd",
"https://example.com/assets/medical/nrrds/RegLib_C01_1.nrrd",
"https://example.com/assets/medical/nrrds/TCGA-CV-7236.nrrd"
],
"externalId": "patient-study"
}
]
```
From your project dashboard, go to the *Assets* tab and click on *Add Data*. Then, enter the *Cloud Storage* section and drag and drop your JSON on the file upload field. Then, press on *Upload*. Your multi-image asset(s) will be uploaded.
If your assets are located in a private storage, please ensure you select the correct storage from the *Storage Method* dropdown on the left-hand side of the screen.
Assets uploaded this way will have a dropdown, allowing annotators to navigate between the volumes in the dataset.
---
# 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.imerit.net/data/importing-assets/importing-reference-medical-data-during-asset-import.md?ask=&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.
