BAMF FDG-Avid Breast Tumor #87

jithenece · 2024-07-02T13:41:41Z

AIMI1 - Pretrained model for 3D semantic image segmentation of the FDG-avid lesions from PT/CT scans

jithenece · 2024-07-02T13:42:49Z

sample:
  idc_version: Version 2: Updated 2020/01/10
  data:
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.200887946066796652452097013479
    aws_url: s3://idc-open-data/7a375cfa-8708-46f0-b056-248dbaca851e/*
    path: case1/ct
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.182230913012492714502249429083
    aws_url: s3://idc-open-data/739449f3-286c-4511-86a9-39172a50dc95/*
    path: case1/pt

reference:
  url: https://drive.google.com/file/d/1afkRFJqwgii1tUSMiQV_dPlDsUBl6_0g/view?usp=sharing

jithenece · 2024-07-02T13:44:01Z

Archive.zip
Slicer screenshots added

LennyN95

Thank you for this implementation, this appears to be a more elaborate pipeline. Well done! I added some questions and discussion points in my review.

models/bamf_pet_ct_breast_tumor/utils/Registration.py

LennyN95 · 2024-07-24T11:46:21Z

models/bamf_pet_ct_breast_tumor/config/default.yml

+
+execute:
+- FileStructureImporter
+- SitkNiftiConverter


Why do we need this converter? Cannot we use the NiftiConverter module? There you can configure the backend to use dcm2niix which offers high performance.

i have changed engine to dcm2niix. it required upgrading dcm2niix==1.0.20220715 to fix the conversion issue on few ct scans.

models/bamf_pet_ct_breast_tumor/utils/BreastPostProcessor.py

LennyN95 · 2024-07-24T11:47:48Z

models/bamf_pet_ct_breast_tumor/utils/NNUnetPETCTRunner.py

+    def export_prob_mask(self, nnunet_out_dir: str, ref_file: InstanceData, output_dtype: str = 'float32', structure_list: Optional[List[str]] = None):
+        """
+        Convert softmax probability maps to NRRD. For simplicity, the probability maps
+        are converted by default to UInt8
+        Arguments:
+            model_output_folder : required - path to the folder where the inferred segmentation masks should be stored.
+            ref_file            : required - InstanceData object of the generated segmentation mask used as reference file.
+            output_dtype        : optional - output data type. Data type float16 is not supported by the NRRD standard,
+                                            so the choice should be between uint8, uint16 or float32. 
+            structure_list      : optional - list of the structures whose probability maps are stored in the 
+                                            first channel of the `.npz` file (output from the nnU-Net pipeline
+                                            when `export_prob_maps` is set to True). 
+        Outputs:
+            This function [...]
+        """
+
+        # initialize structure list
+        if structure_list is None:
+            if self.roi is not None:
+                structure_list = self.roi.split(',')
+            else:
+                structure_list = []
+
+        # sanity check user inputs
+        assert(output_dtype in ["uint8", "uint16", "float32"])      
+
+        # input file containing the raw information
+        pred_softmax_fn = 'VOLUME_001.npz'
+        pred_softmax_path = os.path.join(nnunet_out_dir, pred_softmax_fn)
+
+        # parse NRRD file - we will make use of if to populate the header of the
+        # NRRD mask we are going to get from the inferred segmentation mask
+        sitk_ct = sitk.ReadImage(ref_file.abspath)
+
+        # generate bundle for prob masks
+        # TODO: we really have to create folders (or add this as an option that defaults to true) automatically
+        prob_masks_bundle = ref_file.getDataBundle('prob_masks')
+        if not os.path.isdir(prob_masks_bundle.abspath):
+            os.mkdir(prob_masks_bundle.abspath)
+
+        # load softmax probability maps
+        pred_softmax_all = np.load(pred_softmax_path)["softmax"]
+
+        # iterate all channels
+        for channel in range(0, len(pred_softmax_all)):
+
+            structure = structure_list[channel] if channel < len(structure_list) else f"structure_{channel}"
+            pred_softmax_segmask = pred_softmax_all[channel].astype(dtype = np.float32)
+
+            if output_dtype == "float32":
+                # no rescale needed - the values will be between 0 and 1
+                # set SITK image dtype to Float32
+                sitk_dtype = sitk.sitkFloat32
+
+            elif output_dtype == "uint8":
+                # rescale between 0 and 255, quantize
+                pred_softmax_segmask = (255*pred_softmax_segmask).astype(np.int32)
+                # set SITK image dtype to UInt8
+                sitk_dtype = sitk.sitkUInt8
+
+            elif output_dtype == "uint16":
+                # rescale between 0 and 65536
+                pred_softmax_segmask = (65536*pred_softmax_segmask).astype(np.int32)
+                # set SITK image dtype to UInt16
+                sitk_dtype = sitk.sitkUInt16
+            else:
+                raise ValueError("Invalid output data type. Please choose between uint8, uint16 or float32.")
+
+            pred_softmax_segmask_sitk = sitk.GetImageFromArray(pred_softmax_segmask)
+            pred_softmax_segmask_sitk.CopyInformation(sitk_ct)
+            pred_softmax_segmask_sitk = sitk.Cast(pred_softmax_segmask_sitk, sitk_dtype)
+
+            # generate data
+            prob_mask = InstanceData(f'{structure}.nrrd', DataType(FileType.NRRD, {'mod': 'prob_mask', 'structure': structure}), bundle=prob_masks_bundle)
+
+            # export file
+            writer = sitk.ImageFileWriter()
+            writer.UseCompressionOn()
+            writer.SetFileName(prob_mask.abspath)
+            writer.Execute(pred_softmax_segmask_sitk)
+
+            # check if the file was written
+            if os.path.isfile(prob_mask.abspath):
+                self.v(f" > prob mask for {structure} saved to {prob_mask.abspath}")
+                prob_mask.confirm()


Did you test the probability map export under the modified circumstances?

LennyN95 · 2024-07-24T11:49:46Z

models/bamf_pet_ct_breast_tumor/config/default.yml

+- SitkNiftiConverter
+- Registration
+- NNUnetPETCTRunner
+- TotalSegmentatorMLRunner


Why is TotalSegmentator run as part of this model?

LennyN95 · 2024-07-24T11:50:26Z

models/bamf_pet_ct_breast_tumor/config/default.yml

+  TotalSegmentatorMLRunner:
+    in_data: nifti:mod=ct:registered=true
+    use_fast_mode: false


I'd assume that fast mode would work just as well but should significantly speed up the process.

LennyN95 · 2024-07-24T11:50:32Z

models/bamf_pet_ct_breast_tumor/config/default.yml

+  SitkNiftiConverter:    
+    in_datas: dicom:mod=pt|ct
+    allow_multi_input: true


LennyN95 · 2024-07-24T11:51:18Z

models/bamf_pet_ct_breast_tumor/dockerfiles/Dockerfile

+# Install nnunet
+# Install TotalSegmentator
+RUN pip3 install TotalSegmentator==1.5.7 nnunet==1.6.6


See above (why do we need TS for this model).

LennyN95 · 2024-07-24T11:54:51Z

models/bamf_pet_ct_breast_tumor/utils/TotalSegmentatorMLRunner.py

+    'pancreas': 'PANCREAS',
+    'adrenal_gland_right': 'RIGHT_ADRENAL_GLAND',
+    'adrenal_gland_left': 'LEFT_ADRENAL_GLAND',
+    'lung_upper_lobe_left': 'LEFT_UPPER_LUNG_LOBE',
+    'lung_lower_lobe_left': 'LEFT_LOWER_LUNG_LOBE',
+    'lung_upper_lobe_right': 'RIGHT_UPPER_LUNG_LOBE',
+    'lung_middle_lobe_right': 'RIGHT_MIDDLE_LUNG_LOBE',
+    'lung_lower_lobe_right': 'RIGHT_LOWER_LUNG_LOBE',
+    'vertebrae_L5': 'VERTEBRAE_L5',
+    'vertebrae_L4': 'VERTEBRAE_L4',
+    'vertebrae_L3': 'VERTEBRAE_L3',
+    'vertebrae_L2': 'VERTEBRAE_L2',
+    'vertebrae_L1': 'VERTEBRAE_L1',
+    'vertebrae_T12': 'VERTEBRAE_T12',
+    'vertebrae_T11': 'VERTEBRAE_T11',
+    'vertebrae_T10': 'VERTEBRAE_T10',
+    'vertebrae_T9': 'VERTEBRAE_T9',
+    'vertebrae_T8': 'VERTEBRAE_T8',
+    'vertebrae_T7': 'VERTEBRAE_T7',
+    'vertebrae_T6': 'VERTEBRAE_T6',
+    'vertebrae_T5': 'VERTEBRAE_T5',
+    'vertebrae_T4': 'VERTEBRAE_T4',
+    'vertebrae_T3': 'VERTEBRAE_T3',
+    'vertebrae_T2': 'VERTEBRAE_T2',
+    'vertebrae_T1': 'VERTEBRAE_T1',
+    'vertebrae_C7': 'VERTEBRAE_C7',
+    'vertebrae_C6': 'VERTEBRAE_C6',
+    'vertebrae_C5': 'VERTEBRAE_C5',
+    'vertebrae_C4': 'VERTEBRAE_C4',
+    'vertebrae_C3': 'VERTEBRAE_C3',
+    'vertebrae_C2': 'VERTEBRAE_C2',
+    'vertebrae_C1': 'VERTEBRAE_C1',
+    'esophagus': 'ESOPHAGUS',
+    'trachea': 'TRACHEA',
+    'heart_myocardium': 'MYOCARDIUM',
+    'heart_atrium_left': 'LEFT_ATRIUM',
+    'heart_ventricle_left': 'LEFT_VENTRICLE',
+    'heart_atrium_right': 'RIGHT_ATRIUM',
+    'heart_ventricle_right': 'RIGHT_VENTRICLE',
+    'pulmonary_artery': 'PULMONARY_ARTERY',
+    'brain': 'BRAIN',
+    'iliac_artery_left': 'LEFT_ILIAC_ARTERY',
+    'iliac_artery_right': 'RIGHT_ILIAC_ARTERY',
+    'iliac_vena_left': 'LEFT_ILIAC_VEIN',
+    'iliac_vena_right': 'RIGHT_ILIAC_VEIN',
+    'small_bowel': 'SMALL_INTESTINE',
+    'duodenum': 'DUODENUM',
+    'colon': 'COLON',
+    'rib_left_1': 'LEFT_RIB_1',
+    'rib_left_2': 'LEFT_RIB_2',
+    'rib_left_3': 'LEFT_RIB_3',
+    'rib_left_4': 'LEFT_RIB_4',
+    'rib_left_5': 'LEFT_RIB_5',
+    'rib_left_6': 'LEFT_RIB_6',
+    'rib_left_7': 'LEFT_RIB_7',
+    'rib_left_8': 'LEFT_RIB_8',
+    'rib_left_9': 'LEFT_RIB_9',
+    'rib_left_10': 'LEFT_RIB_10',
+    'rib_left_11': 'LEFT_RIB_11',
+    'rib_left_12': 'LEFT_RIB_12',
+    'rib_right_1': 'RIGHT_RIB_1',
+    'rib_right_2': 'RIGHT_RIB_2',
+    'rib_right_3': 'RIGHT_RIB_3',
+    'rib_right_4': 'RIGHT_RIB_4',
+    'rib_right_5': 'RIGHT_RIB_5',
+    'rib_right_6': 'RIGHT_RIB_6',
+    'rib_right_7': 'RIGHT_RIB_7',
+    'rib_right_8': 'RIGHT_RIB_8',
+    'rib_right_9': 'RIGHT_RIB_9',
+    'rib_right_10': 'RIGHT_RIB_10',
+    'rib_right_11': 'RIGHT_RIB_11',
+    'rib_right_12': 'RIGHT_RIB_12',
+    'humerus_left': 'LEFT_HUMERUS',
+    'humerus_right': 'RIGHT_HUMERUS',
+    'scapula_left': 'LEFT_SCAPULA',
+    'scapula_right': 'RIGHT_SCAPULA',
+    'clavicula_left': 'LEFT_CLAVICLE',
+    'clavicula_right': 'RIGHT_CLAVICLE',
+    'femur_left': 'LEFT_FEMUR',
+    'femur_right': 'RIGHT_FEMUR',
+    'hip_left': 'LEFT_HIP',
+    'hip_right': 'RIGHT_HIP',
+    'sacrum': 'SACRUM',
+    'face': 'FACE',
+    'gluteus_maximus_left': 'LEFT_GLUTEUS_MAXIMUS',
+    'gluteus_maximus_right': 'RIGHT_GLUTEUS_MAXIMUS',
+    'gluteus_medius_left': 'LEFT_GLUTEUS_MEDIUS',
+    'gluteus_medius_right': 'RIGHT_GLUTEUS_MEDIUS',
+    'gluteus_minimus_left': 'LEFT_GLUTEUS_MINIMUS',
+    'gluteus_minimus_right': 'RIGHT_GLUTEUS_MINIMUS',
+    'autochthon_left': 'LEFT_AUTOCHTHONOUS_BACK_MUSCLE',
+    'autochthon_right': 'RIGHT_AUTOCHTHONOUS_BACK_MUSCLE',
+    'iliopsoas_left': 'LEFT_ILIOPSOAS',
+    'iliopsoas_right': 'RIGHT_ILIOPSOAS',
+    'urinary_bladder': 'URINARY_BLADDER'
+}
+
+# from totalsegmentator.map_to_binary import class_map
+# 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'


can be removed, right?

LennyN95 · 2024-07-24T11:57:20Z

models/bamf_pet_ct_breast_tumor/utils/BreastPostProcessor.py

+        tumor_seg_path = in_tumor_data.abspath
+        total_seg_path = in_total_seg_data.abspath
+
+        ts_data = sitk.GetArrayFromImage(sitk.ReadImage(total_seg_path))
+        ts_abdominal = sitk.GetArrayFromImage(sitk.ReadImage(total_seg_path))
+        ts_data[ts_data > 1] = 1
+        lesions = sitk.GetArrayFromImage(sitk.ReadImage(tumor_seg_path))
+        tumor_label = 9
+        lesions[lesions != tumor_label] = 0
+        lesions[lesions == tumor_label] = 1
+
+        op_data = np.zeros(ts_data.shape)
+        ref = sitk.ReadImage(in_ct_data.abspath)
+        ct_data = sitk.GetArrayFromImage(ref)
+
+        op_data[lesions == 1] = 1
+        th = np.min(ct_data)
+        op_data[ct_data == th] = 0  # removing predicitons where CT not available
+        # Use the coordinates of the bounding box to crop the 3D numpy array.
+        ts_abdominal[ts_abdominal > 4] = 0
+        ts_abdominal[ts_abdominal > 1] = 1
+        if ts_abdominal.max() > 0:
+            x1, x2, y1, y2, z1, z2 = self.bbox2_3D(ts_abdominal)
+        # Create a structuring element with ones in the middle and zeros around it
+        structuring_element = np.ones((3, 3))


Isn't running TS a bit overkill for the task? What about taking abdominal segmentation masks as an input to the pipeline? Then a user could run any model (e.g. TotalSegmentator from MHub) and provide the dicomseg file alongside the input dicom files.

I#m asking this to evaluate the situation and to get the best possible user experience.

The simplest user experience would be to have dicom in -> dicom out. and not have a segmentation also be an input.

@LennyN95 please let us know if you are fine with this.

It'd be nice to provide an alternative workflow (config file) then, where you start with a DicomImporter expecting TotalSegmentator DICOMSEG files (e.g. as generated when running the MHub TotalSegmentator model) and use a DsegExtractor in the execute chain to extract the segmentations.

@jithenece an alternative workflow sounds great, then we have both options

@LennyN95 I have added multi flow which takes total segmentator files as input. please check and let me know for any changes.

I have changed the alternative workflow (config file) to composite. Please check

jithenece · 2024-08-08T10:52:15Z

/test

sample:
  idc_version: "Data Release 2.0 January 10, 2020"
  data:
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.200887946066796652452097013479
    aws_url: s3://idc-open-data/7a375cfa-8708-46f0-b056-248dbaca851e/*
    path: 'case_study1/ct'
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.182230913012492714502249429083
    aws_url: s3://idc-open-data/739449f3-286c-4511-86a9-39172a50dc95/*
    path: 'case_study1/pt'

reference:
  url: https://drive.google.com/file/d/1yivXqTBMXslsmj3uD8gE9LojLCKh-BqV/view?usp=sharing

LennyN95 · 2024-08-26T17:34:49Z

@jithenece I wanted to run our test routine on all read for testing PR's, however, I noticed, the sample reference url you provided won't work with wget -O /tmp/ref.zip $RESSOURCE_URL. This might be specific to using a google drive link, however, I generally advice you to instead to attach your data to the PR directly (e.g., by uploading them to the comment) and to use the permanent link as a reference.

Please note, this needs to be updated on all effected PRs until testing can proceed.

jithenece · 2024-09-09T07:41:15Z

/test

Not many collection available for breast-pet-ct.

attaching segmentation
output.zip

sample: 
  idc_version: 17.0
  data:
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.539267076861125410814830191835
    aws_url: s3://idc-open-data/84c9b972-76e1-4fa3-a7ea-19b6500e497a/*
    path: case_study1/ct
  - SeriesInstanceUID: 1.3.6.1.4.1.14519.5.2.1.8162.7003.196821690630879561473146713439
    aws_url: s3://idc-open-data/33f0bd14-4bf5-469c-83db-183e1ab96f02/*
    path: case_study1/pt

reference:
  url: https://github.com/user-attachments/files/16927110/output.zip

LennyN95 · 2024-09-19T13:46:36Z

Please note, we updated our base image. All mhub dependencies are now installed in a virtual environment under /app/.venv running Python 3.11. Python, virtual environment and dependencies are now managed with uv. If required, you can create custom virtual environments, e.g., uv venv -p 3.8 .venv38 and use uv pip install -p .venv38 packge-name to install dependencies and uv run -p .venv3.8 python script.py to run a python script.

We also simplified our test routine. Sample and reference data now have to be uploaded to Zenodo and provided in a mhub.tom file at the project root. The process how to create and provide these sample data is explained in the updated testing phase article of our documentation. Under doi.org/10.5281/zenodo.13785615 we provide sample data as a reference.

jithenece added 14 commits May 1, 2024 13:23

create multi modality PET CT nnUnet Runner

a47bc80

add Resampler module

c571530

define workflow

b46db65

generate Total Segmentator organs

a9f959c

limiting tumor to breast

c9ffeb7

add custom registration module

8859687

update metadata

412cd01

use FDG_AVID_TUMOR entry

e8f5fee

roi segments updated

1faac1b

use FDG_AVID_TUMOR label

4c29ce9

more results stats

cd4ba5f

Merge branch 'MHubAI:main' into bamf_nnunet_pet_ct_breast

ee9a3ff

updated label and comments

652c092

reformat code

af0eab0

jithenece mentioned this pull request Jul 2, 2024

BAMF FDG-Avid Breast Tumor #79

Closed

jithenece marked this pull request as ready for review July 2, 2024 13:44

LennyN95 requested changes Jul 24, 2024

View reviewed changes

jithenece added 2 commits August 8, 2024 15:27

review comment fixes

a3f67cc

update comments

bed9a6b

github-actions bot added the TEST REQUESTED label Aug 8, 2024

jithenece added 5 commits August 27, 2024 01:24

update model name

4570d50

Merge branch 'MHubAI:main' into bamf_pet_ct_breast_tumor

76c1876

multi workflow for tseg file as input

c6b1f1c

format code

e7861be

update body part

3885709

rahul99 mentioned this pull request Sep 4, 2024

[FEAT]: BAMF nnUNet Breast MR Model #82

Open

github-actions bot added INVALID TEST REQUEST The contributor requested a test but the test block is not valid. TEST REQUESTED and removed TEST REQUESTED INVALID TEST REQUEST The contributor requested a test but the test block is not valid. labels Sep 9, 2024

jithenece added 3 commits October 2, 2024 04:20

Merge branch 'MHubAI:main' into bamf_pet_ct_breast_tumor

bcbd0d5

update publication link

406fd78

/test validation

64e19b5

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

BAMF FDG-Avid Breast Tumor #87

BAMF FDG-Avid Breast Tumor #87

jithenece commented Jul 2, 2024

jithenece commented Jul 2, 2024

jithenece commented Jul 2, 2024

LennyN95 left a comment

LennyN95 Jul 24, 2024

jithenece Aug 8, 2024

LennyN95 Jul 24, 2024

LennyN95 Jul 24, 2024

LennyN95 Jul 24, 2024

LennyN95 Aug 22, 2024

LennyN95 Jul 24, 2024

LennyN95 Jul 24, 2024

LennyN95 Jul 24, 2024

LennyN95 Jul 24, 2024

vanossj Aug 1, 2024

jithenece Aug 21, 2024

LennyN95 Aug 22, 2024

vanossj Aug 22, 2024

jithenece Sep 4, 2024

jithenece Oct 9, 2024

jithenece commented Aug 8, 2024

LennyN95 commented Aug 26, 2024 •

edited

Loading

jithenece commented Sep 9, 2024 •

edited

Loading

LennyN95 commented Sep 19, 2024

BAMF FDG-Avid Breast Tumor #87

Are you sure you want to change the base?

BAMF FDG-Avid Breast Tumor #87

Conversation

jithenece commented Jul 2, 2024

jithenece commented Jul 2, 2024

jithenece commented Jul 2, 2024

LennyN95 left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

jithenece commented Aug 8, 2024

LennyN95 commented Aug 26, 2024 • edited Loading

jithenece commented Sep 9, 2024 • edited Loading

LennyN95 commented Sep 19, 2024

LennyN95 commented Aug 26, 2024 •

edited

Loading

jithenece commented Sep 9, 2024 •

edited

Loading