Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MHub / GC - Minor cleanup gc_lunglobes #42

Merged
merged 8 commits into from
Mar 4, 2024
Merged

MHub / GC - Minor cleanup gc_lunglobes #42

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
0fe8183
update e-mailaddress and cleanup/simplify default.yml
silvandeleemput Aug 2, 2023
f081bd3
removed redundant line source_segs from DsegConverter in default.yml
silvandeleemput Aug 2, 2023
ddb8c4d
Merge branch 'main' into m-gc-lobesegmentation-xie
silvandeleemput Sep 4, 2023
0ad8931
add specific commit hash for algorithm main branch at 2023/09/13
silvandeleemput Sep 13, 2023
ada6c05
Merge branch 'MHubAI:main' into m-gc-lobesegmentation-xie
silvandeleemput Nov 28, 2023
0e449b8
update algorithm version to release gclobe165 with fix for #69
silvandeleemput Nov 28, 2023
c25f532
meta.json - update date formats, data.public, and model.training fields
silvandeleemput Feb 27, 2024
37a7cae
meta.json - made public field a boolean, changed slice thickness to 0…
silvandeleemput Mar 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 1 addition & 5 deletions models/gc_lunglobes/config/default.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@ execute:
- DicomImporter
- MhaConverter
- LobeSegmentationRunner
- NiftiConverter
- DsegConverter
- DataOrganizer

Expand All @@ -20,10 +19,7 @@ modules:
mod: ct

MhaConverter:
engine: plastimatch

NiftiConverter:
in_datas: mha:mod=seg
engine: panimg

DsegConverter:
model_name: GCLungLobes
Expand Down
6 changes: 3 additions & 3 deletions models/gc_lunglobes/dockerfiles/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
FROM mhubai/base:latest

# Update authors label
LABEL authors="s[email protected],[email protected],[email protected]"
LABEL authors="sil[email protected],[email protected],[email protected]"

# Install system dependencies for OpenCV
RUN apt-get update && apt-get install ffmpeg libsm6 libxext6 -y
Expand All @@ -19,8 +19,8 @@ RUN pip3 install --no-cache-dir --force-reinstall SimpleITK==1.2.4
ARG MHUB_MODELS_REPO
RUN buildutils/import_mhub_model.sh gc_lunglobes ${MHUB_MODELS_REPO}

# Install Xie's pulmonary lobe segmentation algorithm and model weights
RUN git clone https://github.com/DIAGNijmegen/bodyct-pulmonary-lobe-segmentation.git src && \
# Install Xie's pulmonary lobe segmentation algorithm and model weights (release gclobe165 v1.6.5)
RUN git clone --depth 1 --branch v1.6.5 https://github.com/DIAGNijmegen/bodyct-pulmonary-lobe-segmentation.git src && \
sed -i 's/from models import CTSUNet/from src.models import CTSUNet/g' src/test.py

# Default run script
Expand Down
12 changes: 6 additions & 6 deletions models/gc_lunglobes/meta.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
"format": "DICOM",
"modality": "CT",
"bodypartexamined": "Chest",
"slicethickness": "2.5mm",
"slicethickness": "0.75mm",
"non-contrast": true,
"contrast": false
} ],
Expand All @@ -26,7 +26,7 @@
} ],
"model": {
"architecture": "Relational two-stage U-net",
"training": "Supervised",
"training": "supervised",
"cmpapproach": "3D"
},
"data": {
Expand All @@ -36,7 +36,7 @@
"evaluation": {
"vol_samples": 1155
},
"public": "Partially",
"public": false,
"external": true
}
},
Expand All @@ -46,9 +46,9 @@
"devteam": "DIAGNijmegen (Diagnostic Image Analysis Group, Radboud UMC, The Netherlands)",
"type": "Relational two-stage U-Net (Cascade of two relational U-Net, trained end-to-end)",
"date": {
"weights": "14/02/22",
"code": "n/a",
"pub": "n/a"
"weights": "2022-02-14",
"code": "2023-11-27",
"pub": "2020-05-15"
},
"cite": "W. Xie, C. Jacobs, J. -P. Charbonnier and B. van Ginneken, 'Relational Modeling for Robust and Efficient Pulmonary Lobe Segmentation in CT Scans,' in IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp. 2664-2675, Aug. 2020, doi: 10.1109/TMI.2020.2995108.",
"license": {
Expand Down
Loading