Skip to content

Commit 1696be1

Browse files
m-reuterm-reuter
committed
switch to minimal mistakes theme
1 parent 5c20da0 commit 1696be1

10 files changed

Lines changed: 234 additions & 50 deletions

File tree

‎Gemfile‎

Lines changed: 5 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,10 @@
11
source 'https://rubygems.org'
22

3-
# Specify Ruby version for consistency
4-
ruby '>= 2.7.0'
3+
# Use GitHub Pages gem which includes Jekyll and compatible plugins
4+
gem "github-pages", group: :jekyll_plugins
55

6-
# GitHub Pages gem (includes Jekyll and plugins used by GitHub Pages)
7-
gem 'github-pages'
8-
# HTML validation and link checking for CI/CD
9-
gem "html-proofer"
6+
# Additional plugins for Minimal Mistakes theme
7+
gem "jekyll-include-cache", group: :jekyll_plugins
108

11-
# Required for Ruby 3.x to run Jekyll server
9+
# Required for Ruby 3.x+ to run Jekyll server
1210
gem "webrick"

‎LICENSE‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
The MIT License (MIT)
22

33
Copyright (c) 2014 fraser-lab
4-
Copyright (c) 2020 DeepMI-lab
4+
Copyright (c) 2020-2026 DeepMI-lab
55

66
Permission is hereby granted, free of charge, to any person obtaining a copy
77
of this software and associated documentation files (the "Software"), to deal

‎README.md‎

Lines changed: 20 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,14 @@
1-
# Deep-MI.github.io
1+
# Deep-MI Lab Website
22

3+
This is the official website for the Deep Medical Imaging (Deep-MI) Lab.
4+
5+
The website is built with Jekyll and hosted on GitHub Pages.
6+
7+
## Quick Links
8+
9+
- **Live Website**: [https://deep-mi.github.io](https://deep-mi.github.io)
10+
- **Contributing**: See [CONTRIBUTING.md](CONTRIBUTING.md)
11+
- **Quick Start**: See [QUICKSTART.md](QUICKSTART.md)
312

413
## Create News Posts
514

@@ -82,16 +91,20 @@ cp scripts/pre-commit.sh .git/hooks/pre-commit
8291
chmod +x .git/hooks/pre-commit
8392
```
8493

85-
## Sources
94+
For more detailed guidelines, see [CONTRIBUTING.md](CONTRIBUTING.md).
95+
96+
## Attribution
8697

87-
This website was built using the Fraser Lab [website](http://fraserlab.com/) as a template. James Fraser's website is open-source and available on [Github](https://github.com/fraser-lab/fraser-lab.github.io)
98+
This website uses the [Minimal Mistakes Jekyll theme](https://mmistakes.github.io/minimal-mistakes/) by Michael Rose, which is open-source and available on [GitHub](https://github.com/mmistakes/minimal-mistakes).
8899

100+
The original Deep-MI website was built using the [Fraser Lab website](http://fraserlab.com/) as a template.
89101

90-
Technologies this website uses:
102+
### Technologies Used
91103

92-
Jekyll
93-
Github Pages
94-
Twitter Bootstrap 4.4.1
104+
- Jekyll - Static site generator
105+
- Minimal Mistakes - Modern responsive theme
106+
- GitHub Pages - Hosting
107+
- Ruby - Programming language
95108

96109
## Local Development
97110

‎_config.yml‎

Lines changed: 133 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,140 @@
1+
# Site Settings
2+
title: "Deep Medical Imaging Lab"
13
name: "Deep Medical Imaging Lab"
2-
description: "This is the official web page for the Deep Medical Imaging Lab at DZNE and MGH/HMS."
4+
description: "Advancing medical imaging through deep learning and AI - research at DZNE, MGH/HMS, and MIT CSAIL"
5+
url: "https://Deep-MI.github.io"
6+
baseurl: ""
7+
repository: "Deep-MI/Deep-MI.github.io"
38

4-
url: "https://Deep-MI.org"
9+
# Theme - using remote_theme for GitHub Pages compatibility
10+
remote_theme: "mmistakes/minimal-mistakes@4.24.0"
11+
minimal_mistakes_skin: "default" # "air", "aqua", "contrast", "dark", "dirt", "neon", "mint", "plum", "sunrise"
512

6-
paginate: 5
7-
plugins: [jekyll-paginate]
8-
paginate_path: "news/page:num"
13+
# Site Author
14+
author:
15+
name: "Deep MI Lab"
16+
avatar: "/static/img/logos/deepmi.png"
17+
bio: "Deep learning and AI for medical imaging and computational neuroimaging"
18+
location: "Bonn, Germany & Boston, USA"
19+
links:
20+
- label: "GitHub"
21+
icon: "fab fa-fw fa-github"
22+
url: "https://github.com/Deep-MI"
23+
- label: "Website"
24+
icon: "fas fa-fw fa-link"
25+
url: "https://Deep-MI.github.io"
926

10-
permalink: pretty
27+
# Site Footer
28+
footer:
29+
links:
30+
- label: "GitHub"
31+
icon: "fab fa-fw fa-github"
32+
url: "https://github.com/Deep-MI"
33+
- label: "DZNE"
34+
icon: "fas fa-fw fa-link"
35+
url: "https://www.dzne.de"
36+
37+
# Reading Files
38+
include:
39+
- .htaccess
40+
- _pages
41+
exclude:
42+
- vendor
43+
- .asset-cache
44+
- .bundle
45+
- .jekyll-assets-cache
46+
- .sass-cache
47+
- assets/js/plugins
48+
- assets/js/_main.js
49+
- assets/js/vendor
50+
- Capfile
51+
- CHANGELOG
52+
- config
53+
- Gemfile
54+
- Gruntfile.js
55+
- gulpfile.js
56+
- LICENSE
57+
- log
58+
- node_modules
59+
- package.json
60+
- Rakefile
61+
- README
62+
- tmp
63+
keep_files:
64+
- .git
65+
- .svn
66+
encoding: "utf-8"
67+
markdown_ext: "markdown,mkdown,mkdn,mkd,md"
68+
69+
# Conversion
1170
markdown: kramdown
12-
kramdown:
71+
highlighter: rouge
72+
lsi: false
73+
excerpt_separator: "\n\n"
74+
incremental: false
75+
76+
# Markdown Processing
77+
kramdown:
78+
input: GFM
79+
hard_wrap: false
80+
auto_ids: true
81+
footnote_nr: 1
82+
entity_output: as_char
83+
toc_levels: 1..6
84+
smart_quotes: lsquo,rsquo,ldquo,rdquo
85+
enable_coderay: false
1386
parse_block_html: true
1487

15-
exclude: [vendor]
88+
# Sass/SCSS
89+
sass:
90+
sass_dir: _sass
91+
style: compressed
92+
93+
# Outputting
94+
permalink: /:categories/:title/
95+
paginate: 10
96+
paginate_path: /news/page:num/
97+
timezone: Europe/Berlin
98+
99+
# Plugins
100+
plugins:
101+
- jekyll-paginate
102+
- jekyll-sitemap
103+
- jekyll-gist
104+
- jekyll-feed
105+
- jekyll-include-cache
106+
107+
# Archives
108+
category_archive:
109+
type: liquid
110+
path: /categories/
111+
tag_archive:
112+
type: liquid
113+
path: /tags/
114+
115+
# HTML Compression
116+
compress_html:
117+
clippings: all
118+
ignore:
119+
envs: development
120+
121+
# Defaults
122+
defaults:
123+
# _posts
124+
- scope:
125+
path: ""
126+
type: posts
127+
values:
128+
layout: single
129+
author_profile: true
130+
read_time: true
131+
comments: false
132+
share: true
133+
related: true
134+
# _pages
135+
- scope:
136+
path: "_pages"
137+
type: pages
138+
values:
139+
layout: single
140+
author_profile: false

‎_data/navigation.yml‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
# Main Navigation
2+
main:
3+
- title: "Research"
4+
url: /research/
5+
- title: "Publications"
6+
url: /publications/
7+
- title: "Team"
8+
url: /members/
9+
- title: "News"
10+
url: /news/
11+
- title: "Join Us"
12+
url: /join/
13+
- title: "Contact"
14+
url: /contact/
15+

‎_posts/2020-03-07-New-Webpage.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,19 +6,19 @@ group: news
66
---
77
Today we finally took the time out of the always-busy schedule of writing grants and papers and created an initial version of the
88
DeepMI Lab Webpage. This step has long been overdue and we are happy to present it to the world.
9-
There has been a long discussion how to solve mutliple problems at the same time:
9+
There has been a long discussion how to solve multiple problems at the same time:
1010

1111
- how can we have a webpage that is flexible, yet easy to maintain for more than one curator
1212
- how can we represent the fact that the Lab is associated across multiple institutions
1313
- how can we version control the page, edit quickly without local IT
14-
- where can we host it
14+
- where can we host it
1515
- and how should we even call the lab (I vetoed Reuter-Lab)
1616

1717
The first few points were solved by starting with github.io and jekyll - easy. The name was another beast!
1818
The Lab's background is in developing computational methods for medical image analysis. We did this since 2008 and recently people
1919
like to call it AI (basically whenever a computer does something cool, like analyze an image). Most of our recent methods are
2020
deep-learning based, extending existing architectures for specific goals, e.g. brain MRI segmentation.
2121
This is why Deep Medical Imaging Lab (DeepMI) was selected. Yet, we are not limited to deep-learning and have a lot of work on traditional
22-
methods (robust image registration, shape analysis, geometry processing etc). So expect to see some variety.
22+
methods (robust image registration, shape analysis, geometry processing etc). So expect to see some variety.
2323

2424
We hope you enjoy this site. Please contact us with any comments. We look forward hearing from you ...

‎index.md‎

Lines changed: 44 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,20 +1,53 @@
11
---
2-
title: Deep MI Lab
3-
layout: home
4-
group: home
2+
layout: splash
3+
title: "Deep Medical Imaging Lab"
4+
permalink: /
5+
header:
6+
overlay_color: "#000"
7+
overlay_filter: "0.5"
8+
overlay_image: /static/img/deepmi.png
9+
actions:
10+
- label: "Our Research"
11+
url: "/research/"
12+
- label: "Publications"
13+
url: "/publications/"
14+
excerpt: "Advancing medical imaging through deep learning and AI"
15+
intro:
16+
- excerpt: "Our research focuses on the development of novel computational methods (deep learning, AI) for the automated analysis, segmentation, classification, diagnosis, and prognosis of medical imaging data to support the study of neurodegenerative diseases."
17+
feature_row:
18+
- image_path: /static/img/research/fastsurfer/01_teaser_white.png
19+
alt: "FastSurfer"
20+
title: "FastSurfer"
21+
excerpt: "Fast and accurate deep-learning based neuroimaging pipeline"
22+
url: "/research/fastsurfer/"
23+
btn_label: "Learn More"
24+
btn_class: "btn--primary"
25+
- image_path: /static/img/research/brainprint/brainprint_teaser.png
26+
alt: "BrainPrint"
27+
title: "BrainPrint"
28+
excerpt: "Shape analysis and asymmetry quantification of neuroanatomical structures"
29+
url: "/research/brainprint/"
30+
btn_label: "Learn More"
31+
btn_class: "btn--primary"
32+
- image_path: /static/img/research/fatsegnet/fatsegnet_teaser.png
33+
alt: "FatSegNet"
34+
title: "FatSegNet"
35+
excerpt: "Automated adipose tissue segmentation in Dixon MRI"
36+
url: "/research/fatsegnet/"
37+
btn_label: "Learn More"
38+
btn_class: "btn--primary"
539
---
640

7-
# Welcome to Deep MI Lab!
8-
{: .display-4}
41+
{% include feature_row id="intro" type="center" %}
942

10-
Our research is focused on the development of novel computational methods (deep-learning, AI) for the automated analysis, segmentation, classification, diagnosis and prognosis of medical imaging data to support the study of neurodegenerative diseases.
11-
{: .welcomefont}
43+
## Our Affiliations
1244

1345
We are part of the:
14-
{: .welcomefont}
1546

16-
- [German Center for Neurodegenerative Diseases, Bonn, Germany](https://www.dzne.de/en/research/research-areas/population-health-sciences/forschungsgruppen/reuter/research-areasfocus/)
47+
- [German Center for Neurodegenerative Diseases, Bonn, Germany](https://www.dzne.de/en/research/research-areas/population-health-sciences/forschungsgruppen/reuter/research-areasfocus/)
1748
- [Martinos Center for Biomedical Imaging, MGH/HMS Boston, USA](https://www.martinos.org/investigator/martin-reuter/)
18-
- and associated to [MIT CSAIL](http://reuter.mit.edu).
19-
{: .welcomefont}
49+
- and associated to [MIT CSAIL](http://reuter.mit.edu)
50+
{: .notice--info}
51+
52+
{% include feature_row %}
2053

‎join/index.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -20,33 +20,33 @@ While every lab member is expected to contribute to the lab, we also expect to g
2020
- We strive to provide excellent training across a wide range of computational and experimental techniques.
2121
- We provide a strong network of international collaborators at various prestigious institutions, such as Harvard and MIT.
2222
- We are located at DZNE, a German Helmholtz Center, with outstanding funding, resources, and research environment.
23-
- We have access to exciting and richly phenotyped datasets, e.g. the Rhineland Study (a large population study with thousdands of participants).
23+
- We have access to exciting and richly phenotyped datasets, e.g. the Rhineland Study (a large population study with thousands of participants).
2424
- We currently train on 24 NVIDIA V100 (32 GB each, NVlink'ed) and 8 A100 GPUs (40 GB each) available exclusively for our lab.
2525
- We provide access to the DZNE HPC cluster with 94 V100 GPU's.
2626
- We have a modern MRI facility in house (with a 3T and a 7T Siemens scanner), and further 3T scanners at two scan centers.
27-
- We have strong local collaborative ties with clinial science, population science, neuroscience, radiology, epileptiology etc.
27+
- We have strong local collaborative ties with clinical science, population science, neuroscience, radiology, epileptiology etc.
2828
- We develop FastSurfer and contribute to FreeSurfer (a popular open source software suite for brain MRI processing) via collaborations at Harvard Medical School.
29-
- ... (if you are not yet convicend, please ask)
29+
- ... (if you are not yet convinced, please ask)
3030

3131
# Postdoctoral Fellows
3232

3333
We currently do not have any open positions, sorry.
3434

3535
<!-- Inquiries about Postdoctoral positions should be emailed directly to Martin Reuter (use Subject: MIC-PD-JOIN). Our lab welcomes applicants of any race, religion, national origin, gender identity, caregiver and family commitments, political affiliation, and eligible age or ability. Furthermore, we are committed to maintaining a supportive and collaborative lab environment. Our lab doesn’t always post for specific positions, so please reach out! We are interested in hearing about your scientific background and goals. -->
3636

37-
As a member of the Humboldt Foundation Network, we would love to host you via a prestigious postdoctoral [Humboldt Fellowship](https://www.humboldt-foundation.de/bewerben/foerderprogramme/humboldt-forschungsstipendium) for a stay of 6 - 24 months at the Deep-MI Lab in Germany! Please contact us.
37+
As a member of the Humboldt Foundation Network, we would love to host you via a prestigious postdoctoral [Humboldt Fellowship](https://www.humboldt-foundation.de/bewerben/foerderprogramme/humboldt-forschungsstipendium) for a stay of 6 - 24 months at the Deep-MI Lab in Germany! Please contact us.
3838

3939
# Graduate Students
4040

41-
Sadly, we currently do not have any open PhD positions. If you obtained a PhD fellowship or are exploring external funding possibilities and would like to visit or stay at our Lab, please contact us.
41+
Sadly, we currently do not have any open PhD positions. If you obtained a PhD fellowship or are exploring external funding possibilities and would like to visit or stay at our Lab, please contact us.
4242

4343
# Master Students
4444

4545
We can offer various exciting topics for your Master Thesis project in our lab. Please contact us for details.
4646

4747
# Other
4848

49-
In the past, our lab has enjoyed having foreign exchange students, interns, (sabbatical) visitors from academia and industry.
49+
In the past, our lab has enjoyed having foreign exchange students, interns, (sabbatical) visitors from academia and industry.
5050

5151
<p style="text-align: center;">
5252
![alt text](/static/img/join/bonn.jpg "Bonn")

‎research/fastsurfer.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -89,7 +89,7 @@ To ensure the usefulness of our entire pipeline, FastSurfer was extensively vali
8989

9090
#### 1. Accuracy and Generalizability - How good is the whole brain segmentation generated by FastSurferCNN?
9191

92-
__Answer__: Very good! FastSurcerCNN outperforms other deep-learning architectures by a significant margin both wrt to FreeSurfer
92+
__Answer__: Very good! FastSurferCNN outperforms other deep-learning architectures by a significant margin both wrt to FreeSurfer
9393
and a manual standard (Mindboggle). It generalizes well across five different datasets including subjects with different disease states (e.g.
9494
cognitive normal, mild cognitive impaired or demented subjects in OASIS, ADNI, MIRIAD), different
9595
vendors (e.g. THP), age groups, downsampled and defaced images (e.g. HCP) and alternative T1-imaging protocols (e.g. MIRIAD)

0 commit comments

Comments
 (0)