Open valosekj opened 4 months ago
Trying a binary model trained on both cervical (n=31) and lumbar (n=6) rootlets:
Dataset202_LumbarRootlets
and Dataset012_M5
for file in *nii.gz;do sct_maths -i $file -bin 0.5 -o $file;done
nnUNetv2_plan_and_preprocess -d 203 --verify_dataset_integrity -c 3d_fullres
CUDA_VISIBLE_DEVICES=2 nnUNetv2_train 203 3d_fullres 0 # I do not use `-tr` --> 1000 epochs in default
Observations so far: Dataset202_LumbarRootlets
(binary, trained on 6 lumbar labels only) is performing the best so far. Models comparison on a testing image unseen during the training/validation:
Legend:
Next step: try transfer learning, i.e., pre-train on cervical, finetune on lumbar
@valosekj how different are the labels performed by Raphaelle and that performed by Theo/you? If too different, the model will get confused.
@valosekj how different are the labels performed by Raphaelle and that performed by Theo/you?
Cervical and lumbar labels differ a lot. Lumbar rootlets have much greater angulation and thus a greater overlap between levels.
If too different, the model will get confused.
Indeed, this was my concern and why I tried the lumbar model only.
aouch! that is a tricky project indeed 😅
Dataset201_LumbarRootlets and Dataset202_LumbarRootlets
This issue summarizes the training of the first models (
Dataset201_LumbarRootlets
- semantic,Dataset202_LumbarRootlets
- binary) for lumbar dorsal rootlets.Steps
(recoding using recode_nii.py)
Dataset201_LumbarRootlets
fold1
, 4 training and 2 validation images.dataset.json
```json { "name": "Dataset201_LumbarRootlets", "description": "Dataset201_LumbarRootlets", "channel_names": { "0": "acq-zoomit_T2w" }, "labels": { "background":0, "lvl1":1, "lvl2":2, "lvl3":3, "lvl4":4, "lvl5":5, "lvl6":6, "lvl7":7, "lvl8":8, "lvl9":9 }, "numTraining": 6, "file_ending": ".nii.gz", "overwrite_image_reader_writer": "SimpleITKIO" } ```1
) modelDataset202_LumbarRootlets
fold1
, 4 training and 2 validation images.dataset.json
```json { "name": "Dataset201_LumbarRootlets", "description": "Dataset201_LumbarRootlets", "channel_names": { "0": "acq-zoomit_T2w" }, "labels": { "background":0, "lvl1":1 }, "numTraining": 6, "file_ending": ".nii.gz", "overwrite_image_reader_writer": "SimpleITKIO" } ```