Skip to content

Commit e1bc695

Browse files
tomDag25Thomas Dagonneaulunebellec
authored
Thomas Dagonneau Poject (#402)
* added my project * Added the photo for the README * Update README.md * Rename README.md to index.md * Update content/en/project/Multimodal-ms-lesions-segmentation/index.md --------- Co-authored-by: Thomas Dagonneau <thdaga@romane> Co-authored-by: Lune Bellec <[email protected]>
1 parent be290cd commit e1bc695

File tree

3 files changed

+245
-0
lines changed

3 files changed

+245
-0
lines changed

‎content/en/project/Multimodal-ms-lesions-segmentation/LICENSE.txt‎

Lines changed: 121 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,121 @@
1+
Creative Commons Legal Code
2+
3+
CC0 1.0 Universal
4+
5+
CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
6+
LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
7+
ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
8+
INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
9+
REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
10+
PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
11+
THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
12+
HEREUNDER.
13+
14+
Statement of Purpose
15+
16+
The laws of most jurisdictions throughout the world automatically confer
17+
exclusive Copyright and Related Rights (defined below) upon the creator
18+
and subsequent owner(s) (each and all, an "owner") of an original work of
19+
authorship and/or a database (each, a "Work").
20+
21+
Certain owners wish to permanently relinquish those rights to a Work for
22+
the purpose of contributing to a commons of creative, cultural and
23+
scientific works ("Commons") that the public can reliably and without fear
24+
of later claims of infringement build upon, modify, incorporate in other
25+
works, reuse and redistribute as freely as possible in any form whatsoever
26+
and for any purposes, including without limitation commercial purposes.
27+
These owners may contribute to the Commons to promote the ideal of a free
28+
culture and the further production of creative, cultural and scientific
29+
works, or to gain reputation or greater distribution for their Work in
30+
part through the use and efforts of others.
31+
32+
For these and/or other purposes and motivations, and without any
33+
expectation of additional consideration or compensation, the person
34+
associating CC0 with a Work (the "Affirmer"), to the extent that he or she
35+
is an owner of Copyright and Related Rights in the Work, voluntarily
36+
elects to apply CC0 to the Work and publicly distribute the Work under its
37+
terms, with knowledge of his or her Copyright and Related Rights in the
38+
Work and the meaning and intended legal effect of CC0 on those rights.
39+
40+
1. Copyright and Related Rights. A Work made available under CC0 may be
41+
protected by copyright and related or neighboring rights ("Copyright and
42+
Related Rights"). Copyright and Related Rights include, but are not
43+
limited to, the following:
44+
45+
i. the right to reproduce, adapt, distribute, perform, display,
46+
communicate, and translate a Work;
47+
ii. moral rights retained by the original author(s) and/or performer(s);
48+
iii. publicity and privacy rights pertaining to a person's image or
49+
likeness depicted in a Work;
50+
iv. rights protecting against unfair competition in regards to a Work,
51+
subject to the limitations in paragraph 4(a), below;
52+
v. rights protecting the extraction, dissemination, use and reuse of data
53+
in a Work;
54+
vi. database rights (such as those arising under Directive 96/9/EC of the
55+
European Parliament and of the Council of 11 March 1996 on the legal
56+
protection of databases, and under any national implementation
57+
thereof, including any amended or successor version of such
58+
directive); and
59+
vii. other similar, equivalent or corresponding rights throughout the
60+
world based on applicable law or treaty, and any national
61+
implementations thereof.
62+
63+
2. Waiver. To the greatest extent permitted by, but not in contravention
64+
of, applicable law, Affirmer hereby overtly, fully, permanently,
65+
irrevocably and unconditionally waives, abandons, and surrenders all of
66+
Affirmer's Copyright and Related Rights and associated claims and causes
67+
of action, whether now known or unknown (including existing as well as
68+
future claims and causes of action), in the Work (i) in all territories
69+
worldwide, (ii) for the maximum duration provided by applicable law or
70+
treaty (including future time extensions), (iii) in any current or future
71+
medium and for any number of copies, and (iv) for any purpose whatsoever,
72+
including without limitation commercial, advertising or promotional
73+
purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
74+
member of the public at large and to the detriment of Affirmer's heirs and
75+
successors, fully intending that such Waiver shall not be subject to
76+
revocation, rescission, cancellation, termination, or any other legal or
77+
equitable action to disrupt the quiet enjoyment of the Work by the public
78+
as contemplated by Affirmer's express Statement of Purpose.
79+
80+
3. Public License Fallback. Should any part of the Waiver for any reason
81+
be judged legally invalid or ineffective under applicable law, then the
82+
Waiver shall be preserved to the maximum extent permitted taking into
83+
account Affirmer's express Statement of Purpose. In addition, to the
84+
extent the Waiver is so judged Affirmer hereby grants to each affected
85+
person a royalty-free, non transferable, non sublicensable, non exclusive,
86+
irrevocable and unconditional license to exercise Affirmer's Copyright and
87+
Related Rights in the Work (i) in all territories worldwide, (ii) for the
88+
maximum duration provided by applicable law or treaty (including future
89+
time extensions), (iii) in any current or future medium and for any number
90+
of copies, and (iv) for any purpose whatsoever, including without
91+
limitation commercial, advertising or promotional purposes (the
92+
"License"). The License shall be deemed effective as of the date CC0 was
93+
applied by Affirmer to the Work. Should any part of the License for any
94+
reason be judged legally invalid or ineffective under applicable law, such
95+
partial invalidity or ineffectiveness shall not invalidate the remainder
96+
of the License, and in such case Affirmer hereby affirms that he or she
97+
will not (i) exercise any of his or her remaining Copyright and Related
98+
Rights in the Work or (ii) assert any associated claims and causes of
99+
action with respect to the Work, in either case contrary to Affirmer's
100+
express Statement of Purpose.
101+
102+
4. Limitations and Disclaimers.
103+
104+
a. No trademark or patent rights held by Affirmer are waived, abandoned,
105+
surrendered, licensed or otherwise affected by this document.
106+
b. Affirmer offers the Work as-is and makes no representations or
107+
warranties of any kind concerning the Work, express, implied,
108+
statutory or otherwise, including without limitation warranties of
109+
title, merchantability, fitness for a particular purpose, non
110+
infringement, or the absence of latent or other defects, accuracy, or
111+
the present or absence of errors, whether or not discoverable, all to
112+
the greatest extent permissible under applicable law.
113+
c. Affirmer disclaims responsibility for clearing rights of other persons
114+
that may apply to the Work or any use thereof, including without
115+
limitation any person's Copyright and Related Rights in the Work.
116+
Further, Affirmer disclaims responsibility for obtaining any necessary
117+
consents, permissions or other rights required for any use of the
118+
Work.
119+
d. Affirmer understands and acknowledges that Creative Commons is not a
120+
party to this document and has no duty or obligation with respect to
121+
this CC0 or use of the Work.

‎content/en/project/Multimodal-ms-lesions-segmentation/index.md‎

Lines changed: 124 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,124 @@
1+
---
2+
type: "project" # DON'T TOUCH THIS ! :)
3+
date: "2025-05-16" # Date you first upload your project.
4+
# Title of your project (we like creative title)
5+
title: "Multimodal spine multiple sclerosis segmentation"
6+
7+
# List the names of the collaborators within the [ ]. If alone, simple put your name within []
8+
names: [Thomas Dagonneau]
9+
10+
# Your project GitHub repository URL
11+
github_repo: https://github.com/brainhack-school2025/Dagonneau_project
12+
13+
# If you are working on a project that has website, indicate the full url including "https://" below or leave it empty.
14+
website:
15+
16+
# List +- 4 keywords that best describe your project within []. Note that the project summary also involves a number of key words. Those are listed on top of the [github repository](https://github.com/PSY6983-2021/project_template), click `manage topics`.
17+
# Please only lowercase letters
18+
tags: [project, github, segmentation, brainhack]
19+
20+
# Summarize your project in < ~75 words. This description will appear at the top of your page and on the list page with other projects..
21+
22+
summary: "This project presents an open-source pipeline for segmenting multiple sclerosis lesions in the spinal cord using multimodal MRI data. Built for the MS-Multi-Spine Challenge, it combines nnUNet, the Spinal Cord Toolbox, Docker, and Boutiques for reproducibility and ease of use. The pipeline includes preprocessing, inference, and post-processing steps, and is packaged with full documentation and containerization to support future research and clinical applications in spinal cord imaging."
23+
24+
# If you want to add a cover image (listpage and image in the right), add it to your directory and indicate the name
25+
# below with the extension.
26+
image: "ms_segmentation.png"
27+
---
28+
<!-- This is an html comment and this won't appear in the rendered page. You are now editing the "content" area, the core of your description. Everything that you can do in markdown is allowed below. We added a couple of comments to guide your through documenting your progress. -->
29+
30+
31+
## Project definition
32+
33+
### Background
34+
35+
Multiple sclerosis (MS) is a chronic disease of the central nervous system, with spinal cord involvement playing a critical role in clinical outcomes. Although MRI is essential for MS diagnosis and disease monitoring [1], spinal cord imaging remains challenging due to anatomical complexity and variability in acquisition protocols. Existing automated lesion segmentation tools have focused primarily on the brain [2–4], and very few methods were designed for spinal cord lesions, particularly across heterogeneous and multimodal MRI data. Additionally, high inter- and intra-rater variability in manual annotations [5] highlights the need for reliable, automated segmentation pipelines.
36+
37+
In this study, we introduce a novel pipeline for the automatic segmentation of MS lesions in the spinal cord using multiple MRI acquisitions from the same patient. Our approach combines a deep learning model with a robust post-processing framework to produce accurate lesion instance segmentations and estimate prediction uncertainty, addressing the specific challenges of spinal cord imaging.
38+
39+
### Objectives
40+
41+
In this project, I focus on the [Multiple Sclerosis Spinal Cord Lesions Detection from MultiSequence MRIs Challenge (MS-Multi-Spine)](https://zenodo.org/records/14051168) and develop a model capable of multimodal MS lesion segmentation.
42+
43+
- Train a multimodal nnUNet [6] on the challenge’s dataset (private)
44+
- Make the model and pipeline open-source on GitHub (public)
45+
- Containerize the pipeline and provide a Boutiques descriptor to facilitate reuse (public)
46+
47+
### Tools
48+
49+
This project uses the following tools:
50+
51+
- **Terminal**: all code is designed to run in the terminal
52+
- **Python**: all scripts are written in Python
53+
- **Spinal Cord Toolbox (SCT)** [7]: used for preprocessing steps such as coregistration
54+
- **Git and GitHub**: for version control and open access
55+
- **Docker**: to ensure reproducibility
56+
- **Boutiques**: to automate and simplify tool usage
57+
58+
### Data
59+
60+
The dataset used in this project is provided by the challenge and is private. It includes:
61+
62+
- 100 subjects in total
63+
- 50 subjects with T2w + STIR acquisitions
64+
- 25 subjects with T2w + PSIR acquisitions
65+
- 25 subjects with T2w + MP2RAGE acquisitions
66+
67+
### Deliverables in Week 4
68+
69+
- A GitHub repository containing Python scripts for data preprocessing, inference, and postprocessing
70+
- A Dockerfile used to create the Docker image available [here](https://hub.docker.com/repository/docker/tomdag25/ms-seg-challenge2025-multimodal/general)
71+
- A Boutiques descriptor to perform inference
72+
73+
### Results
74+
75+
Over the four weeks, I developed a pipeline for the automatic segmentation of MS lesions in a multimodal context. I gained hands-on experience with:
76+
77+
- **Python scripting**: all processing steps are implemented in Python
78+
- **Git and GitHub**: all project code and resources are versioned and publicly available
79+
- **Spinal Cord Toolbox**: used for preprocessing (e.g., coregistration)
80+
- **Docker**: used to package the pipeline and publish the image to Docker Hub
81+
- **Boutiques**: used to create a descriptor for automated execution of the tool
82+
83+
### Deliverable 1: GitHub Repository
84+
85+
This repository contains everything needed to reproduce the training, inference, and submission process. Instructions to train and perform inference are available [here](multimodal-model/training-and-inference-script).
86+
87+
### Deliverable 2: Docker
88+
89+
The repository includes the Dockerfile used to build the image available on [Docker Hub](https://hub.docker.com/repository/docker/tomdag25/ms-seg-challenge2025-multimodal/general). Instructions for building the image locally are provided [here](multimodal-model/docker).
90+
91+
### Deliverable 3: Boutiques Descriptor
92+
93+
The Boutiques descriptor is available [here](multimodal-model/docker/miccai2025_challenge_descriptor_neuropoly_multimodal.json), with usage instructions [here](multimodal-model/docker).
94+
95+
### Contribution to Open Science
96+
97+
This project contributes to open science by:
98+
99+
- Publishing the complete pipeline code and documentation on GitHub
100+
- Providing a Docker image to ensure reproducibility across environments
101+
- Creating a Boutiques descriptor to facilitate automated reuse by other researchers
102+
- Building on and extending open-source tools such as nnUNet and SCT
103+
- Enabling multimodal spinal cord lesion segmentation—an underexplored area in neuroimaging research
104+
105+
### Conclusion
106+
107+
This project presents a complete pipeline for multimodal MS lesion segmentation in the spinal cord, from preprocessing to inference and postprocessing. It leverages state-of-the-art tools and open standards to enable reproducibility and accessibility. The pipeline successfully integrates multimodal imaging data and handles the complexity of spinal cord anatomy, providing reliable segmentation outputs.
108+
109+
### Next Steps
110+
111+
- Evaluate the model on additional test data and quantify performance per modality
112+
- Extend support to include missing modalities through imputation or modality-agnostic models
113+
- Release a demo dataset to allow users to test the pipeline without requiring private data
114+
- Submit the pipeline to MICCAI MS Challenge 2025 results and benchmark against other approaches
115+
116+
### References
117+
118+
1. Thompson AJ, Banwell BL, Barkhof F, Carroll WM, Coetzee T, Comi G, et al. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. *Lancet Neurol*. 2018;17: 162–173.
119+
2. Valverde S, Cabezas M, Roura E, González-Villà S, Pareto D, Vilanova JC, et al. Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach. *Neuroimage*. 2017;155: 159–168.
120+
3. Aslani S, Dayan M, Storelli L, Filippi M, Murino V, Rocca MA, et al. Multi-branch convolutional neural network for multiple sclerosis lesion segmentation. *Neuroimage*. 2019;196: 1–15.
121+
4. Kaur A, Kaur L, Singh A. State-of-the-art segmentation techniques and future directions for multiple sclerosis brain lesions. *Arch Comput Methods Eng*. 2021;28: 951–977.
122+
5. Walsh R, Meurée C, Kerbrat A, Masson A, Hussein BR, Gaubert M, et al. Expert variability and deep learning performance in spinal cord lesion segmentation for multiple sclerosis patients. *2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS)*. doi:10.1109/cbms58004.2023.00263
123+
6. Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. *Nat Methods*. 2021;18: 203–211.
124+
7. Leener BD, Lévy S, Dupont SM, Fonov VS, Stikov N, Collins DL, et al. SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data. *NeuroImage*. 2017;145, Part A: 24–43.

‎content/en/project/Multimodal-ms-lesions-segmentation/ms_segmentation.png‎

1.58 MB
Loading

0 commit comments

Comments
 (0)