-
Notifications
You must be signed in to change notification settings - Fork 16
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
8 changed files
with
162 additions
and
64 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,3 +1,14 @@ | ||
| """ | ||
| --------------------------------------------------------- | ||
| Post processing Module on segmentation output | ||
| --------------------------------------------------------- | ||
| ------------------------------------------------- | ||
| Author: Jithendra Kumar | ||
| Email: [email protected] | ||
| ------------------------------------------------- | ||
| """ | ||
| import os | ||
| import SimpleITK as sitk | ||
| import numpy as np | ||
|
|
@@ -10,22 +21,6 @@ | |
|
|
||
| class BreastPostProcessor(Module): | ||
|
|
||
| def mask_labels(self, labels, ts): | ||
| """ | ||
| Create a mask based on given labels. | ||
| Args: | ||
| labels (list): List of labels to be masked. | ||
| ts (np.ndarray): Image data. | ||
| Returns: | ||
| np.ndarray: Masked image data. | ||
| """ | ||
| lung = np.zeros(ts.shape) | ||
| for lbl in labels: | ||
| lung[ts == lbl] = 1 | ||
| return lung | ||
|
|
||
| def bbox2_3D(self, img): | ||
| r = np.any(img, axis=(1, 2)) | ||
| c = np.any(img, axis=(0, 2)) | ||
|
|
@@ -65,21 +60,6 @@ def n_connected(self, img_data): | |
| img_data[img_filtered != 1] = 0 | ||
| return img_data | ||
|
|
||
| def arr_2_sitk_img(self, arr, ref): | ||
| """ | ||
| Convert numpy array to SimpleITK image. | ||
| Args: | ||
| arr (np.ndarray): Input image data as a numpy array. | ||
| ref: Reference image for copying information. | ||
| Returns: | ||
| sitk.Image: Converted SimpleITK image. | ||
| """ | ||
| op_img = sitk.GetImageFromArray(arr) | ||
| op_img.CopyInformation(ref) | ||
| return op_img | ||
|
|
||
| @IO.Instance() | ||
| @IO.Input('in_ct_data', 'nifti:mod=ct:registered=true', the='input ct data') | ||
| @IO.Input('in_tumor_data', 'nifti:mod=seg:model=nnunet', the='input tumor segmentation') | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,20 +1,31 @@ | ||
| """ | ||
| --------------------------------------------------------- | ||
| Registration Module using SimpleITK | ||
| --------------------------------------------------------- | ||
| ------------------------------------------------- | ||
| Author: Jithendra Kumar | ||
| Email: [email protected] | ||
| ------------------------------------------------- | ||
| """ | ||
| import os | ||
| import shutil | ||
| import SimpleITK as sitk | ||
| import numpy as np | ||
| from mhubio.core import IO | ||
| from mhubio.core import Module, Instance, InstanceData | ||
|
|
||
|
|
||
| class Registration(Module): | ||
|
|
||
| @IO.Instance() | ||
| @IO.Input('in_fixed_data', 'nifti:mod=pt', the='input pt data') | ||
| @IO.Input('in_moving_data', 'nifti:mod=ct', the='input ct data') | ||
| @IO.Input('in_fixed_data', 'nifti:mod=pt', the='input fixed data') | ||
| @IO.Input('in_moving_data', 'nifti:mod=ct', the='input moving data') | ||
| @IO.Output('out_data', 'VOL000_registered.nii.gz', 'nifti:mod=ct:registered=true', the="registered ct data") | ||
| def task(self, instance: Instance, in_moving_data: InstanceData, in_fixed_data: InstanceData, out_data: InstanceData): | ||
| """ | ||
| Perform registration | ||
| Perform registration and resampling | ||
| """ | ||
| fixed = sitk.ReadImage(in_fixed_data.abspath, sitk.sitkFloat32) | ||
| moving = sitk.ReadImage(in_moving_data.abspath, sitk.sitkFloat32) | ||
|
|
@@ -27,7 +38,7 @@ def task(self, instance: Instance, in_moving_data: InstanceData, in_fixed_data: | |
| R.SetOptimizerAsRegularStepGradientDescent(1.0, 0.001, 200) | ||
| R.SetInitialTransform(sitk.TranslationTransform(fixed.GetDimension())) | ||
| R.SetInterpolator(sitk.sitkLinear) | ||
|
|
||
| def command_iteration(method): | ||
| print(f"{method.GetOptimizerIteration():3} = {method.GetMetricValue():10.5f}") | ||
|
|
||
|
|
||
106 changes: 106 additions & 0 deletions
106
models/bamf_pet_ct_breast_tumor/utils/SitkNiftiConverter.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,106 @@ | ||
| """ | ||
| --------------------------------------------------------- | ||
| Custom - Dicom to Nifti Conversion Module using SimpleITK | ||
| --------------------------------------------------------- | ||
| ------------------------------------------------- | ||
| Author: Jithendra Kumar | ||
| Email: [email protected] | ||
| ------------------------------------------------- | ||
| """ | ||
|
|
||
| from enum import Enum | ||
| from typing import List, Dict, Any | ||
|
|
||
| import pydicom | ||
| import shutil | ||
| import os, subprocess | ||
| import pyplastimatch as pypla # type: ignore | ||
| import SimpleITK as sitk | ||
| from pathlib import Path | ||
|
|
||
| from mhubio.core import Module, Instance, InstanceDataCollection, InstanceData, DataType, FileType | ||
| from mhubio.core.IO import IO | ||
|
|
||
|
|
||
| @IO.ConfigInput('in_datas', 'dicom:mod=ct|pt', the="target data that will be converted to nifti") | ||
| @IO.Config('allow_multi_input', bool, False, the='allow multiple input files') | ||
| #@IO.Config('targets', List[DataType], ['dicom:mod=ct', 'nrrd:mod=ct'], factory=IO.F.list(DataType.fromString), the='target data types to convert to nifti') | ||
| @IO.Config('bundle_name', str, 'nifti', the="bundle name converted data will be added to") | ||
| @IO.Config('converted_file_name', str, '[filename].nii.gz', the='name of the converted file') | ||
| @IO.Config('overwrite_existing_file', bool, False, the='overwrite existing file if it exists') | ||
| #@IO.Config('wrap_output', bool, False, the='Wrap output in bundles. Required, if multiple input data is allowed that is not yet separated into distinct bundles.') | ||
| class SitkNiftiConverter(Module): | ||
| """ | ||
| Conversion module. | ||
| Convert instance data from dicom | ||
| """ | ||
|
|
||
| allow_multi_input: bool | ||
| bundle_name: str # TODO optional type declaration | ||
| converted_file_name: str | ||
| overwrite_existing_file: bool | ||
| #wrap_output: bool | ||
|
|
||
| @IO.Instance() | ||
| #@IO.Inputs('in_datas', IO.C('targets'), the="data to be converted") | ||
| @IO.Inputs('in_datas', the="data to be converted") | ||
| @IO.Outputs('out_datas', path=IO.C('converted_file_name'), dtype='nifti:converter=sitk', data='in_datas', bundle=IO.C('bundle_name'), auto_increment=True, the="converted data") | ||
| @IO.Outputs('log_datas', path='[basename].pmconv.log', dtype='log:log-task=conversion', data='in_datas', bundle=IO.C('bundle_name'), auto_increment=True, the="log generated by conversion engine") | ||
| def task(self, instance: Instance, in_datas: InstanceDataCollection, out_datas: InstanceDataCollection, log_datas: InstanceDataCollection, **kwargs) -> None: | ||
|
|
||
| # some sanity checks | ||
| assert isinstance(in_datas, InstanceDataCollection) | ||
| assert isinstance(out_datas, InstanceDataCollection) | ||
| assert len(in_datas) == len(out_datas) | ||
| assert len(in_datas) == len(log_datas) | ||
|
|
||
| print("debug NiftiConverter 1 len(in_datas)",len(in_datas)) | ||
| print("debug NiftiConverter 2 len(out_datas)",len(out_datas)) | ||
| # filtered collection must not be empty | ||
| if len(in_datas) == 0: | ||
| print(f"CONVERT ERROR: no data found in instance {str(instance)}.") | ||
| return None | ||
|
|
||
| # check if multi file conversion is enables | ||
| if not self.allow_multi_input and len(in_datas) > 1: | ||
| print("WARNING: found more than one matching file but multi file conversion is disabled. Only the first file will be converted.") | ||
| in_datas = InstanceDataCollection([in_datas.first()]) | ||
|
|
||
| # conversion step | ||
| for i, in_data in enumerate(in_datas): | ||
| out_data = out_datas.get(i) | ||
| log_data = log_datas.get(i) | ||
|
|
||
| # check if output data already exists | ||
| if os.path.isfile(out_data.abspath) and not self.overwrite_existing_file: | ||
| print("CONVERT ERROR: File already exists: ", out_data.abspath) | ||
| continue | ||
|
|
||
| # check datatype | ||
| if in_data.type.ftype == FileType.DICOM: | ||
| files = [] | ||
| dcm_dir = Path(in_data.abspath) | ||
| for f in dcm_dir.glob("*.dcm"): | ||
| ds = pydicom.dcmread(f, stop_before_pixels=True) | ||
| slicer_loc = ds.SliceLocation if hasattr(ds, "SlicerLocation") else 0 | ||
| files.append((slicer_loc, f)) | ||
| slices = sorted(files, key=lambda s: s[0]) | ||
| ordered_files = [x[1] for x in slices] | ||
|
|
||
| o_tmp_dir = self.config.data.requestTempDir(label="convert-processor") | ||
| ptmp_dir = Path(o_tmp_dir) | ||
| for i, f in enumerate(ordered_files): | ||
| shutil.copy(f, ptmp_dir / f"{i}.dcm") | ||
| # load in with SimpleITK | ||
| reader = sitk.ImageSeriesReader() | ||
| dicom_names = reader.GetGDCMSeriesFileNames(str(ptmp_dir)) | ||
| reader.SetFileNames(dicom_names) | ||
| image = reader.Execute() | ||
|
|
||
| # save as nifti | ||
| sitk.WriteImage(image, out_data.abspath, useCompression=True, compressionLevel=9) | ||
|
|
||
| else: | ||
| raise ValueError(f"CONVERT ERROR: unsupported file type {in_data.type.ftype}.") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -6,7 +6,6 @@ | |
| ------------------------------------------------- | ||
| Author: Leonard Nürnberg | ||
| Email: [email protected] | ||
| Comments: Reused the file from model/totalsegmentator | ||
| ------------------------------------------------- | ||
| """ | ||
|
|
||
|
|
@@ -124,20 +123,21 @@ | |
| # ROI = ','.join(mapping[class_map['total'][ci]] for ci in range(1, 105)) | ||
| ROI = 'SPLEEN,RIGHT_KIDNEY,LEFT_KIDNEY,GALLBLADDER,LIVER,STOMACH,AORTA,INFERIOR_VENA_CAVA,PORTAL_AND_SPLENIC_VEIN,PANCREAS,RIGHT_ADRENAL_GLAND,LEFT_ADRENAL_GLAND,LEFT_UPPER_LUNG_LOBE,LEFT_LOWER_LUNG_LOBE,RIGHT_UPPER_LUNG_LOBE,RIGHT_MIDDLE_LUNG_LOBE,RIGHT_LOWER_LUNG_LOBE,VERTEBRAE_L5,VERTEBRAE_L4,VERTEBRAE_L3,VERTEBRAE_L2,VERTEBRAE_L1,VERTEBRAE_T12,VERTEBRAE_T11,VERTEBRAE_T10,VERTEBRAE_T9,VERTEBRAE_T8,VERTEBRAE_T7,VERTEBRAE_T6,VERTEBRAE_T5,VERTEBRAE_T4,VERTEBRAE_T3,VERTEBRAE_T2,VERTEBRAE_T1,VERTEBRAE_C7,VERTEBRAE_C6,VERTEBRAE_C5,VERTEBRAE_C4,VERTEBRAE_C3,VERTEBRAE_C2,VERTEBRAE_C1,ESOPHAGUS,TRACHEA,MYOCARDIUM,LEFT_ATRIUM,LEFT_VENTRICLE,RIGHT_ATRIUM,RIGHT_VENTRICLE,PULMONARY_ARTERY,BRAIN,LEFT_ILIAC_ARTERY,RIGHT_ILIAC_ARTERY,LEFT_ILIAC_VEIN,RIGHT_ILIAC_VEIN,SMALL_INTESTINE,DUODENUM,COLON,LEFT_RIB_1,LEFT_RIB_2,LEFT_RIB_3,LEFT_RIB_4,LEFT_RIB_5,LEFT_RIB_6,LEFT_RIB_7,LEFT_RIB_8,LEFT_RIB_9,LEFT_RIB_10,LEFT_RIB_11,LEFT_RIB_12,RIGHT_RIB_1,RIGHT_RIB_2,RIGHT_RIB_3,RIGHT_RIB_4,RIGHT_RIB_5,RIGHT_RIB_6,RIGHT_RIB_7,RIGHT_RIB_8,RIGHT_RIB_9,RIGHT_RIB_10,RIGHT_RIB_11,RIGHT_RIB_12,LEFT_HUMERUS,RIGHT_HUMERUS,LEFT_SCAPULA,RIGHT_SCAPULA,LEFT_CLAVICLE,RIGHT_CLAVICLE,LEFT_FEMUR,RIGHT_FEMUR,LEFT_HIP,RIGHT_HIP,SACRUM,FACE,LEFT_GLUTEUS_MAXIMUS,RIGHT_GLUTEUS_MAXIMUS,LEFT_GLUTEUS_MEDIUS,RIGHT_GLUTEUS_MEDIUS,LEFT_GLUTEUS_MINIMUS,RIGHT_GLUTEUS_MINIMUS,LEFT_AUTOCHTHONOUS_BACK_MUSCLE,RIGHT_AUTOCHTHONOUS_BACK_MUSCLE,LEFT_ILIOPSOAS,RIGHT_ILIOPSOAS,URINARY_BLADDER' | ||
|
|
||
| @IO.ConfigInput('in_data', 'nifti:mod=ct', the="input data to run TotalSegmentator on") | ||
| @IO.Config('use_fast_mode', bool, True, the="flag to set to run TotalSegmentator in fast mode") | ||
| class TotalSegmentatorMLRunner(Module): | ||
|
|
||
| use_fast_mode: bool | ||
|
|
||
| @IO.Instance() | ||
| @IO.Input('in_data', 'nifti:mod=ct:registered=true', the="input whole body ct scan") | ||
| @IO.Input('in_data', the="input whole body ct scan") | ||
| @IO.Output('out_data', 'segmentations.nii.gz', 'nifti:mod=seg:model=TotalSegmentator:roi=SPLEEN,RIGHT_KIDNEY,LEFT_KIDNEY,GALLBLADDER,LIVER,STOMACH,AORTA,INFERIOR_VENA_CAVA,PORTAL_AND_SPLENIC_VEIN,PANCREAS,RIGHT_ADRENAL_GLAND,LEFT_ADRENAL_GLAND,LEFT_UPPER_LUNG_LOBE,LEFT_LOWER_LUNG_LOBE,RIGHT_UPPER_LUNG_LOBE,RIGHT_MIDDLE_LUNG_LOBE,RIGHT_LOWER_LUNG_LOBE,VERTEBRAE_L5,VERTEBRAE_L4,VERTEBRAE_L3,VERTEBRAE_L2,VERTEBRAE_L1,VERTEBRAE_T12,VERTEBRAE_T11,VERTEBRAE_T10,VERTEBRAE_T9,VERTEBRAE_T8,VERTEBRAE_T7,VERTEBRAE_T6,VERTEBRAE_T5,VERTEBRAE_T4,VERTEBRAE_T3,VERTEBRAE_T2,VERTEBRAE_T1,VERTEBRAE_C7,VERTEBRAE_C6,VERTEBRAE_C5,VERTEBRAE_C4,VERTEBRAE_C3,VERTEBRAE_C2,VERTEBRAE_C1,ESOPHAGUS,TRACHEA,MYOCARDIUM,LEFT_ATRIUM,LEFT_VENTRICLE,RIGHT_ATRIUM,RIGHT_VENTRICLE,PULMONARY_ARTERY,BRAIN,LEFT_ILIAC_ARTERY,RIGHT_ILIAC_ARTERY,LEFT_ILIAC_VEIN,RIGHT_ILIAC_VEIN,SMALL_INTESTINE,DUODENUM,COLON,LEFT_RIB_1,LEFT_RIB_2,LEFT_RIB_3,LEFT_RIB_4,LEFT_RIB_5,LEFT_RIB_6,LEFT_RIB_7,LEFT_RIB_8,LEFT_RIB_9,LEFT_RIB_10,LEFT_RIB_11,LEFT_RIB_12,RIGHT_RIB_1,RIGHT_RIB_2,RIGHT_RIB_3,RIGHT_RIB_4,RIGHT_RIB_5,RIGHT_RIB_6,RIGHT_RIB_7,RIGHT_RIB_8,RIGHT_RIB_9,RIGHT_RIB_10,RIGHT_RIB_11,RIGHT_RIB_12,LEFT_HUMERUS,RIGHT_HUMERUS,LEFT_SCAPULA,RIGHT_SCAPULA,LEFT_CLAVICLE,RIGHT_CLAVICLE,LEFT_FEMUR,RIGHT_FEMUR,LEFT_HIP,RIGHT_HIP,SACRUM,FACE,LEFT_GLUTEUS_MAXIMUS,RIGHT_GLUTEUS_MAXIMUS,LEFT_GLUTEUS_MEDIUS,RIGHT_GLUTEUS_MEDIUS,LEFT_GLUTEUS_MINIMUS,RIGHT_GLUTEUS_MINIMUS,LEFT_AUTOCHTHONOUS_BACK_MUSCLE,RIGHT_AUTOCHTHONOUS_BACK_MUSCLE,LEFT_ILIOPSOAS,RIGHT_ILIOPSOAS,URINARY_BLADDER', data='in_data', the="output segmentation mask containing all labels") | ||
| def task(self, instance: Instance, in_data: InstanceData, out_data: InstanceData) -> None: | ||
|
|
||
| # build command | ||
| bash_command = ["TotalSegmentator"] | ||
| bash_command += ["-i", in_data.abspath] | ||
|
|
||
| # multi-label output (one nifti file containing all labels instead of one nifti file per label) | ||
| self.v("Generating multi-label output ('--ml')") | ||
| bash_command += ["-o", out_data.abspath] | ||
|
|
@@ -150,7 +150,7 @@ def task(self, instance: Instance, in_data: InstanceData, out_data: InstanceData | |
| else: | ||
| self.v("Running TotalSegmentator in default mode (1.5mm)") | ||
|
|
||
| # TODO: remove | ||
| # TODO: remove | ||
| self.v(">> run: ", " ".join(bash_command)) | ||
|
|
||
| # run the model | ||
|
|
||