Skip to content

Commit 4c35883

Browse files
Update and rename using-clairvoy to using-clairvoy.md
@dlevitas
1 parent 9056605 commit 4c35883

File tree

2 files changed

+64
-38
lines changed

2 files changed

+64
-38
lines changed

docs/tutorial/using-clairvoy

-38
This file was deleted.

docs/tutorial/using-clairvoy.md

+64
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
1+
# Clairvoy Tutorial
2+
3+
## Welcome to Clairvoy.
4+
5+
Clairvoy is an experimental [brainlife.io](https://brainlife.io) App.
6+
The Clairvoy App utilizes a machine learning, prognostic model to predict whether someone who has experienced a concussion is at risk for slow recovery (defined as not cleared for full return to sport at greater than 28 days).
7+
The diffusion-weighted and T1-weighted MRI should be collected 24-48 hours after a diagnosed concussion.
8+
This experimental tool is entirely based on the publication of Bertó et al. 2024 (Neuroimage: Clinical, In Press).
9+
Clairvoy was funded by the U.S. Department of Defense, award W81XWH-20-1-0717, PI: Nicholas L Port.
10+
The dataset analyzed by Bertó et al. is from the NCAA/DOD CARE Consortium and was jointly funded by the NCAA and DOD, award W81XWH-14-2-0151, PI: Thomas W McAllister.
11+
12+
We encourage clinicians and scientists to try Clairvoy and appreciate any feedback on how to refine the app.
13+
Drs. [Port](mailto:[email protected]) and [Pestilli](mailto:[email protected]) are actively seeking funding to conduct a clinical trial to validate Clairvoy, but, at present, Clairvoy has not been validated for clinical use.
14+
Thank you for trying Clairvoy and helping us refine the application.
15+
16+
## Directions
17+
18+
The Clairvoy App lives inside the [brainlife.io](https://brainlife.io) platform, an easy-to-use, web-based, Open Science data analysis platform focused on neuroimaging.
19+
Free and open to anyone in the world, Brainlife has over 1,000 users across dozens of countries. Brainlife offers free access to the super-computer built into the platform.
20+
If you become a regular user, you can connect your (super-)computer to BrainLife, which may significantly speed up your analyses.
21+
Before using Cairvoy, you will need a free Brainlife login. We recommend reading the [brainlife.io getting started guide](https://brainlife.io/docs/user/started/).
22+
There are also many helpful videos on the [brainlife.io YouTube channel](https://www.youtube.com/@brainlifeio/videos).
23+
24+
Clairvoy uses the web-based ezBIDS tool (built into Brainlife) to import Dicom files, convert them automatically to NIfTI format, and then create a BIDS project (Brain Imaging Data Structure).
25+
You can learn more about ezBIDs at [this link](https://brainlife.io/docs/using_ezBIDS/) and watch a video at [this link](https://www.youtube.com/watch?v=KvhIHxzHsl4).
26+
The dMRI and T1 protocols can be found in Berto, et al. (Neuroimage: Clinical, In Press) 2024 and Nencka, et al. 2018 (Brain Imaging Behav 12:1121-1140).
27+
28+
### Step-by-step directions for Clairvoy:
29+
30+
A narrated video of how to use Clairvoy is available at [this link](https://youtu.be/TvVmsXITP_0).
31+
32+
### Step 1. Upload files into a BIDS project
33+
1. Login into ezBIDS with your free Brainlife account. The homepage will now open to the `Upload Imaging Data` on the left side Tab.
34+
2. Drag and drop, or browse, for the files you wish to upload. Zip’ing the files may increase upload speed.
35+
3. Fill in the relevant details of the Dataset Description: Dataset Name (e.g., “DWI_workflow”, Authors (eg. your name). Some elements will be extracted from the DICOM, eg. Subject and Session.
36+
4. If the data is not deidentified, you may wish to change the subject name to a private subject ID number.
37+
5. In `BIDS Datatype`, choose `IntendedFor` to `dwi/dwi`. It is also best to deface at this stage, allowing the data to be shared in the future.
38+
6. Choose `QuickShear` method and run defacing (this will remove any recognizable face and ear features). When finished, visually confirm the brain is still in the image and select `Use Defaced`.
39+
7. In `Participants Info`, you may want to choose the sex and age of the subject (this is not HIPAA-protected information), then select `Finalize` to convert to BIDS.[^1]
40+
8. Next, click `Send to Brainlife.io` and select `Run DWI Pipeline`.
41+
9. Finally, click `Submit`, this will automatically create a Project on [brainlife.io](https://brainlife.io), and the pipeline will start processing the data inside the project.
42+
43+
### Step 2. Switch to Brainlife
44+
1. Navigate to [brainlife.io/projects](https://brainlife.io/projects).
45+
2. In `Projects`, search for and choose your Project using the name selected in Step 1 (e.g., DWI_workflow).
46+
3. The `Pipeline` tab should show the pipeline is “active” and “processing.” Wait for process completion[^2].
47+
48+
### Step 3. Run the Clairvoy App
49+
After pipeline completion:
50+
1. Choose the `Archive` tab in your project,
51+
2. Select `tractmeasures`, and
52+
3. Choose `Stage to process`. Give the process the name “Clairvoy” and click `Submit`.
53+
4. In the `Preprocess` tab, choose `Clairvoy` and click `Submit App`.
54+
5. Choose the `Clairvoy App` from the list of Apps suggested by [brainlife.io](https://brainlife.io) and click submit. This should only take a minute or so to complete.
55+
6. When finished, the `Clairvoy App` output will state either: **This injury is at high risk of developing PPCS** in red letters, or **This injury is predicted to recover in under 28 days** in green letters.
56+
57+
**[Here is a narrated YouTube video about how to run Clairvoy](https://youtu.be/TvVmsXITP_0)**
58+
59+
[^1]: It is best practice to save the download `configuration/template` to your computer, which can be reused later for other similar datasets.
60+
61+
[^2]: Time to completion depends on the currently available computing resources on [brainlife.io](https://brainlife.io).
62+
If you have access to a (super-)computer, time to completion may be reduced to less than an hour.
63+
If you use a free, public [brainlife.io](https://brainlife.io) supercomputer, the pipeline may take over 24 hours to complete.
64+

0 commit comments

Comments
 (0)