You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: PW45_2026_Boston/Projects/FineTuningSimcortexUsingManuallyCorrectedCorticalAnnotations/README.md
+25-28Lines changed: 25 additions & 28 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -25,58 +25,55 @@ key_investigators:
25
25
26
26
# Project Description
27
27
28
-
<!-- Add a short paragraph describing the project. -->
28
+
SimCortex v2 is a deep learning pipeline for cortical surface reconstruction from brain MRI. In this project, we will fine-tune the existing SimCortex v2 model using manually corrected segmentations and cortical surfaces.
29
29
30
+
The goal is to evaluate whether manual supervision can improve the reconstructed white and pial surfaces compared with the current SimCortex v2 baseline.
30
31
31
-
_No response_
32
-
32
+
As a practical outcome, we will also prepare a 3D Slicer extension for SimCortex. The extension runs SimCortex through Docker from a native T1-weighted MRI and loads the reconstructed cortical surfaces back into Slicer for visualization.
33
33
34
34
35
35
## Objective
36
36
37
-
<!-- Describe here WHAT you would like to achieve (what you will have as end result). -->
38
-
39
-
40
-
1. Objective A. Describe **what you plan to achieve** in 1-2 sentences.
41
-
42
-
37
+
1. Fine-tune SimCortex v2 using manually corrected segmentations and cortical surfaces, and evaluate the fine-tuned model on held-out test data.
43
38
39
+
2. Prepare the SimCortex 3D Slicer extension for public release, so users can run the pipeline and visualize the reconstructed surfaces directly in 3D Slicer.
44
40
45
41
## Approach and Plan
46
42
47
-
<!-- Describe here HOW you would like to achieve the objectives stated above. -->
48
-
49
-
50
-
1. Describe specific steps of **what you plan to do** to achieve the above described objectives.
51
-
52
-
43
+
1. Review the manually corrected segmentations and cortical surfaces.
44
+
2. Prepare the manual annotations in a format compatible with the SimCortex v2 training pipeline.
45
+
3. Fine-tune the relevant SimCortex v2 stages using the manual annotations.
46
+
4. Run inference with both the baseline and fine-tuned models on the same test data.
47
+
5. Compare the results using surface metrics, topology-related checks, and visual inspection.
48
+
6. Test the local SimCortex 3D Slicer extension and prepare the repository for public use.
53
49
54
50
55
51
## Progress and Next Steps
56
52
57
-
<!-- Update this section as you make progress, describing of what you have ACTUALLY DONE.
58
-
If there are specific steps that you could not complete then you can describe them here, too. -->
59
-
60
-
61
-
1. Describe specific steps you **have actually done**.
62
-
63
-
53
+
1. SimCortex v2 is already available as an open-source cortical surface reconstruction pipeline.
54
+
2. Manually corrected segmentations and cortical surfaces are available for fine-tuning.
55
+
3. A local prototype of the SimCortex 3D Slicer extension has been developed.
56
+
4. The extension can run SimCortex through Docker from a T1-weighted MRI and load the reconstructed white and pial surfaces back into Slicer.
57
+
5. Next steps are to finalize the fine-tuning workflow, run initial experiments, evaluate the results, and prepare the Slicer extension for public release.
64
58
65
59
66
60
# Illustrations
67
61
68
-
<!-- Add pictures and links to videos that demonstrate what has been accomplished. -->
69
62
63
+
The main illustration shows the SimCortex pipeline from brain MRI to segmentation, initial surfaces, deformation, and final predicted cortical surfaces.
0 commit comments