Train a baseline REGION-BASED model from scratch on dcm-zurich-lesions datasets using nnUNet
#1
Comments
|
Thanks for opening the issue, Jan!
Regarding this, I pushed a script for generating QC for both SC and lesions for
As for this, Patrick confirmed in an email on Nov 15th 2023 that the original
and lastly, for this, I noticed that the |
naga-karthik
changed the title
dcm-zurich datasets using nnUNet
naga-karthik
changed the title
dcm-zurich datasets using nnUNetdcm-zurich-lesions datasets using nnUNet
SCIseg worked well -- only 5 subjects needed corrections; labels are pushed.
Great, thanks for confirmation!
Compression labels are single pixels with a value
Yes, this would be super relevant! We have discussed this idea many times with Julien and Sandrine; context here. Note that we have compression labels also for >100 subjects in |
Sounds good!
Right, usually there are more than 1 levels of compression, right? I think for
Nice! at least the model could be pre-trained for detecting compression sites, which, hypothetically could be useful for lesion segmentation (i.e. hyperintensities most likely appear around compressions, if I'm not wrong) |
SC seg and lesion QC copied to
Yes, usually, DCM patients have so-called multi-level compression, i.e., compressions at several levels (e.g., disc C4/C5 and disc C5/C6). So far, we label each compression with a single pixel, meaning that for two compressions, we would have two pixels with the value
Correct, indeed, I believe that hyperintensities most likely appear around compressions. We can verify this with clinicians during a future meeting. |
|
This comment summarizes training progress. commandsDataset merging and conversion from BIDS to nnUNetpython ~/code/model-seg-dcm/dataset_conversion/convert_bids_to_nnUNetv2.py
--path-data
~/data/dcm-zurich-lesions
~/data/dcm-zurich-lesions-20231115
--region-based
--split 0.8 0.2
--seed 42
--dataset-number 601
--dataset-name DCMlesions
--path-out
${nnUNet_raw}/dcm-zurich-lesions_combined_nnunetResulting in: Number of training and validation images (across all sites): 41
Number of test images (across all sites): 11
Number of test images in dcm-zurich-lesions: 3
Number of test images in dcm-zurich-lesions-20231115: 8Trainingconda activate nnunet
cd ~/code/model-seg-dcm
./training/01_run_training_dcm-zurich-lesions.shNote: all folds below were trained using the default fold 0 - crashed to zero
fold 1 - crashed to zero
fold 2 - crashed to zero
fold 3 - crashed to zero
fold 4 - crashed to zero
|
valosekj
changed the title
dcm-zurich-lesions datasets using nnUNetdcm-zurich-lesions datasets using nnUNet
|
Since all folds trained with the default |
|
fold 0, seed42
fold 1, seed42
|
|
`dcm-zurich-lesions``dcm-zurich-lesions-20231115` |
This issue summarizes experiments related to
Dataset601_DCMlesions(region-based model trained to using a single input channel (T2w_ax) to segment both SC and lesions).dataset.json:nnUNetPlans.json:
{ "dataset_name": "Dataset601_DCMlesions", "plans_name": "nnUNetPlans", "original_median_spacing_after_transp": [ 3.5999999046325684, 0.5, 0.5 ], "original_median_shape_after_transp": [ 15, 320, 319 ], "image_reader_writer": "SimpleITKIO", "transpose_forward": [ 0, 1, 2 ], "transpose_backward": [ 0, 1, 2 ], "configurations": { "2d": { "data_identifier": "nnUNetPlans_2d", "preprocessor_name": "DefaultPreprocessor", "batch_size": 31, "patch_size": [ 320, 320 ], "median_image_size_in_voxels": [ 320.0, 319.0 ], "spacing": [ 0.5, 0.5 ], "normalization_schemes": [ "ZScoreNormalization" ], "use_mask_for_norm": [ false ], "UNet_class_name": "PlainConvUNet", "UNet_base_num_features": 32, "n_conv_per_stage_encoder": [ 2, 2, 2, 2, 2, 2, 2 ], "n_conv_per_stage_decoder": [ 2, 2, 2, 2, 2, 2 ], "num_pool_per_axis": [ 6, 6 ], "pool_op_kernel_sizes": [ [ 1, 1 ], [ 2, 2 ], [ 2, 2 ], [ 2, 2 ], [ 2, 2 ], [ 2, 2 ], [ 2, 2 ] ], "conv_kernel_sizes": [ [ 3, 3 ], [ 3, 3 ], [ 3, 3 ], [ 3, 3 ], [ 3, 3 ], [ 3, 3 ], [ 3, 3 ] ], "unet_max_num_features": 512, "resampling_fn_data": "resample_data_or_seg_to_shape", "resampling_fn_seg": "resample_data_or_seg_to_shape", "resampling_fn_data_kwargs": { "is_seg": false, "order": 3, "order_z": 0, "force_separate_z": null }, "resampling_fn_seg_kwargs": { "is_seg": true, "order": 1, "order_z": 0, "force_separate_z": null }, "resampling_fn_probabilities": "resample_data_or_seg_to_shape", "resampling_fn_probabilities_kwargs": { "is_seg": false, "order": 1, "order_z": 0, "force_separate_z": null }, "batch_dice": true }, "3d_fullres": { "data_identifier": "nnUNetPlans_3d_fullres", "preprocessor_name": "DefaultPreprocessor", "batch_size": 2, "patch_size": [ 16, 320, 320 ], "median_image_size_in_voxels": [ 15.0, 320.0, 319.0 ], "spacing": [ 3.5999979972839355, 0.5, 0.5 ], "normalization_schemes": [ "ZScoreNormalization" ], "use_mask_for_norm": [ false ], "UNet_class_name": "PlainConvUNet", "UNet_base_num_features": 32, "n_conv_per_stage_encoder": [ 2, 2, 2, 2, 2, 2, 2 ], "n_conv_per_stage_decoder": [ 2, 2, 2, 2, 2, 2 ], "num_pool_per_axis": [ 2, 6, 6 ], "pool_op_kernel_sizes": [ [ 1, 1, 1 ], [ 1, 2, 2 ], [ 1, 2, 2 ], [ 2, 2, 2 ], [ 2, 2, 2 ], [ 1, 2, 2 ], [ 1, 2, 2 ] ], "conv_kernel_sizes": [ [ 1, 3, 3 ], [ 1, 3, 3 ], [ 3, 3, 3 ], [ 3, 3, 3 ], [ 3, 3, 3 ], [ 3, 3, 3 ], [ 3, 3, 3 ] ], "unet_max_num_features": 320, "resampling_fn_data": "resample_data_or_seg_to_shape", "resampling_fn_seg": "resample_data_or_seg_to_shape", "resampling_fn_data_kwargs": { "is_seg": false, "order": 3, "order_z": 0, "force_separate_z": null }, "resampling_fn_seg_kwargs": { "is_seg": true, "order": 1, "order_z": 0, "force_separate_z": null }, "resampling_fn_probabilities": "resample_data_or_seg_to_shape", "resampling_fn_probabilities_kwargs": { "is_seg": false, "order": 1, "order_z": 0, "force_separate_z": null }, "batch_dice": false } }, "experiment_planner_used": "ExperimentPlanner", "label_manager": "LabelManager", "foreground_intensity_properties_per_channel": { "0": { "max": 2102.0, "mean": 312.2383728027344, "median": 304.0, "min": 0.0, "percentile_00_5": 100.0, "percentile_99_5": 654.0, "std": 92.65310668945312 } } }Dataset601_DCMlesionswill be trained ondcm-zurich-lesionsanddcm-zurich-lesions-20231115datasets using nnUNetv2 region-based approach (i.e., segmenting both SC and lesions).Manual lesion GTs are available for both datasets.
TODO
dcm-zurich-lesions-20231115- run inference using the SCIseg model using segment_sc.sh - done; SCIseg worked relatively well -- only 5 of 38 SC segs needed slight manual corrections. Labels are now pushedsct_maths -add) - not needed; see hereThe text was updated successfully, but these errors were encountered: