This is a small routine for extracting metadata from DICOM files.
\nThe routine takes a image folder path as parameter (folder_path) and returns a DataFrame with the extracted fields as columns.
\ndef extract_DICOM_attributes(folder_path):\n\n images = list(os.listdir(folder_path))\n df = pd.DataFrame()\n for image in images:\n image_name = image.split(\".\")[0]\n dicom_file_path = os.path.join(folder_path,image)\n dicom_file_dataset = dcm.read_file(dicom_file_path)\n study_date = dicom_file_dataset.StudyDate\n modality = dicom_file_dataset.Modality\n age = dicom_file_dataset.PatientAge\n sex = dicom_file_dataset.PatientSex\n body_part_examined = dicom_file_dataset.BodyPartExamined\n patient_orientation = dicom_file_dataset.PatientOrientation\n photometric_interpretation = dicom_file_dataset.PhotometricInterpretation\n rows = dicom_file_dataset.Rows\n columns = dicom_file_dataset.Columns\n\n df = df.append(pd.DataFrame({'image_name': image_name, \n 'dcm_modality': modality,'dcm_study_date':study_date, 'dcm_age': age, 'dcm_sex': sex,\n 'dcm_body_part_examined': body_part_examined,'dcm_patient_orientation': patient_orientation,\n 'dcm_photometric_interpretation': photometric_interpretation,\n 'dcm_rows': rows, 'dcm_columns': columns}, index=[0]))\n return df\nThis is a small routine for extracting metadata from DICOM files.
\nThe routine takes a image folder path as parameter (folder_path) and returns a DataFrame with the extracted fields as columns.
\ndef extract_DICOM_attributes(folder_path):\n\n images = list(os.listdir(folder_path))\n df = pd.DataFrame()\n for image in images:\n image_name = image.split(\".\")[0]\n dicom_file_path = os.path.join(folder_path,image)\n dicom_file_dataset = dcm.read_file(dicom_file_path)\n study_date = dicom_file_dataset.StudyDate\n modality = dicom_file_dataset.Modality\n age = dicom_file_dataset.PatientAge\n sex = dicom_file_dataset.PatientSex\n body_part_examined = dicom_file_dataset.BodyPartExamined\n patient_orientation = dicom_file_dataset.PatientOrientation\n photometric_interpretation = dicom_file_dataset.PhotometricInterpretation\n rows = dicom_file_dataset.Rows\n columns = dicom_file_dataset.Columns\n\n df = df.append(pd.DataFrame({'image_name': image_name, \n 'dcm_modality': modality,'dcm_study_date':study_date, 'dcm_age': age, 'dcm_sex': sex,\n 'dcm_body_part_examined': body_part_examined,'dcm_patient_orientation': patient_orientation,\n 'dcm_photometric_interpretation': photometric_interpretation,\n 'dcm_rows': rows, 'dcm_columns': columns}, index=[0]))\n return df\nThanks for the code snippet. This is very helpful to those who are new to DICOM files.
", "rawMarkdown": "Thanks for the code snippet. This is very helpful to those who are new to DICOM files.", "votes": 3, "replies": [ { "id": 975447, "postDate": "2020-08-18T09:53:41.867Z", "content": "If I can help further, please let me know.
", "rawMarkdown": "If I can help further, please let me know." } ] }, { "id": 971194, "postDate": "2020-08-15T09:20:30.933Z", "content": "how do we use this for autoencoders?
", "rawMarkdown": "how do we use this for autoencoders?", "votes": 2 }, { "id": 1000538, "postDate": "2020-09-06T15:40:35.080Z", "content": "Thank you for helpful tip!! I believe the extracted metadata will help improve the prediction.
", "rawMarkdown": "Thank you for helpful tip!! I believe the extracted metadata will help improve the prediction.", "votes": 1 }, { "id": 989930, "postDate": "2020-08-29T08:15:44.733Z", "content": "I used fastai's medical sub-module for extracting meta-data. It is super optimized and also works in parallel. I would recommend checking it out. I read that some people are facing memory issues on kaggle while extracting metadata. Hope it helps such people.
", "rawMarkdown": "I used fastai's medical sub-module for extracting meta-data. It is super optimized and also works in parallel. I would recommend checking it out. I read that some people are facing memory issues on kaggle while extracting metadata. Hope it helps such people.", "votes": 1, "replies": [ { "id": 1001706, "postDate": "2020-09-07T13:55:34.287Z", "content": "Very good suggestion. I will give it a try, if I find time.
", "rawMarkdown": "Very good suggestion. I will give it a try, if I find time." } ] }, { "id": 978863, "postDate": "2020-08-20T13:06:35.407Z", "content": "Thanks.
\nHelped a lot. Saved a good amount of time as i was not aware of this format.
Very useful! I was about to try and write something like this myself…saved me some time :)
", "rawMarkdown": "Very useful! I was about to try and write something like this myself...saved me some time :)", "votes": 1, "replies": [ { "id": 975444, "postDate": "2020-08-18T09:53:02.990Z", "content": "Glad I could help. If you need any assistance, please let me know.
", "rawMarkdown": "Glad I could help. If you need any assistance, please let me know.", "votes": 1 } ] }, { "id": 971369, "postDate": "2020-08-15T13:12:24.637Z", "content": "Thanks for this. Very new to DICOM and this is a great help.
", "rawMarkdown": "Thanks for this. Very new to DICOM and this is a great help.", "votes": 1, "replies": [ { "id": 975446, "postDate": "2020-08-18T09:53:27.983Z", "content": "Sure, no problem. Please let me know if I can be of further assistance with this.
", "rawMarkdown": "Sure, no problem. Please let me know if I can be of further assistance with this.", "votes": 1 } ] }, { "id": 988421, "postDate": "2020-08-28T03:30:41.697Z", "content": "@gpreda I tried passing a folder
\nextract_DICOM_attributes('/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00007637202177411956430')
but got error name 'dcm' is not defined. I am giving the folder path correctly?
", "rawMarkdown": "@gpreda I tried passing a folder\n\n`extract_DICOM_attributes('/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00007637202177411956430')`\n\nbut got error name 'dcm' is not defined. I am giving the folder path correctly?\n", "votes": 2, "replies": [ { "id": 989105, "postDate": "2020-08-28T14:51:41.693Z", "content": "import pydicom as dcm
\nAlso, a few columns given here don't exist
Thank you so much. This was really helpful 😊
", "rawMarkdown": "Thank you so much. This was really helpful 😊" }, { "id": 1002928, "postDate": "2020-09-08T14:36:52.183Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 971015, "author_name": "Abu Zahid Bin Aziz", "author_url": "", "post_date": "2020-08-15T05:09:37.217000", "content": "Thanks for the code snippet. This is very helpful to those who are new to DICOM files.
", "votes": 3, "replies": [ { "id": 975447, "author_name": "Gabriel Preda", "author_url": "", "post_date": "2020-08-18T09:53:41.867000", "content": "If I can help further, please let me know.
", "votes": 0, "replies": [] } ] }, { "id": 971194, "author_name": "Digvijay Yadav", "author_url": "", "post_date": "2020-08-15T09:20:30.933000", "content": "how do we use this for autoencoders?
", "votes": 2, "replies": [] }, { "id": 1000538, "author_name": "Yuki Kita", "author_url": "", "post_date": "2020-09-06T15:40:35.080000", "content": "Thank you for helpful tip!! I believe the extracted metadata will help improve the prediction.
", "votes": 1, "replies": [] }, { "id": 989930, "author_name": "AnkurSingh", "author_url": "", "post_date": "2020-08-29T08:15:44.733000", "content": "I used fastai's medical sub-module for extracting meta-data. It is super optimized and also works in parallel. I would recommend checking it out. I read that some people are facing memory issues on kaggle while extracting metadata. Hope it helps such people.
", "votes": 1, "replies": [ { "id": 1001706, "author_name": "Gabriel Preda", "author_url": "", "post_date": "2020-09-07T13:55:34.287000", "content": "Very good suggestion. I will give it a try, if I find time.
", "votes": 0, "replies": [] } ] }, { "id": 978863, "author_name": "Deepak Sati", "author_url": "", "post_date": "2020-08-20T13:06:35.407000", "content": "Thanks.
\nHelped a lot. Saved a good amount of time as i was not aware of this format.
Very useful! I was about to try and write something like this myself…saved me some time :)
", "votes": 1, "replies": [ { "id": 975444, "author_name": "Gabriel Preda", "author_url": "", "post_date": "2020-08-18T09:53:02.990000", "content": "Glad I could help. If you need any assistance, please let me know.
", "votes": 1, "replies": [] } ] }, { "id": 971369, "author_name": "palak sood", "author_url": "", "post_date": "2020-08-15T13:12:24.637000", "content": "Thanks for this. Very new to DICOM and this is a great help.
", "votes": 1, "replies": [ { "id": 975446, "author_name": "Gabriel Preda", "author_url": "", "post_date": "2020-08-18T09:53:27.983000", "content": "Sure, no problem. Please let me know if I can be of further assistance with this.
", "votes": 1, "replies": [] } ] }, { "id": 988421, "author_name": "SrikanthPotukuchi", "author_url": "", "post_date": "2020-08-28T03:30:41.697000", "content": "@gpreda I tried passing a folder
\nextract_DICOM_attributes('/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00007637202177411956430')
but got error name 'dcm' is not defined. I am giving the folder path correctly?
", "votes": 2, "replies": [ { "id": 989105, "author_name": "Sumukh", "author_url": "", "post_date": "2020-08-28T14:51:41.693000", "content": "import pydicom as dcm
\nAlso, a few columns given here don't exist
Thank you so much. This was really helpful 😊
", "votes": 0, "replies": [] }, { "id": 1002928, "author_name": "", "author_url": "", "post_date": "2020-09-08T14:36:52.183000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "969194": "This is a small routine for extracting metadata from DICOM files. \n\nThe routine takes a image folder path as parameter (folder_path) and returns a DataFrame with the extracted fields as columns.\n\n\n```\ndef extract_DICOM_attributes(folder_path):\n\n images = list(os.listdir(folder_path))\n df = pd.DataFrame()\n for image in images:\n image_name = image.split(\".\")[0]\n dicom_file_path = os.path.join(folder_path,image)\n dicom_file_dataset = dcm.read_file(dicom_file_path)\n study_date = dicom_file_dataset.StudyDate\n modality = dicom_file_dataset.Modality\n age = dicom_file_dataset.PatientAge\n sex = dicom_file_dataset.PatientSex\n body_part_examined = dicom_file_dataset.BodyPartExamined\n patient_orientation = dicom_file_dataset.PatientOrientation\n photometric_interpretation = dicom_file_dataset.PhotometricInterpretation\n rows = dicom_file_dataset.Rows\n columns = dicom_file_dataset.Columns\n\n df = df.append(pd.DataFrame({'image_name': image_name, \n 'dcm_modality': modality,'dcm_study_date':study_date, 'dcm_age': age, 'dcm_sex': sex,\n 'dcm_body_part_examined': body_part_examined,'dcm_patient_orientation': patient_orientation,\n 'dcm_photometric_interpretation': photometric_interpretation,\n 'dcm_rows': rows, 'dcm_columns': columns}, index=[0]))\n return df\n```", "971015": "Thanks for the code snippet. This is very helpful to those who are new to DICOM files.", "971194": "how do we use this for autoencoders?", "1000538": "Thank you for helpful tip!! I believe the extracted metadata will help improve the prediction.", "989930": "I used fastai's medical sub-module for extracting meta-data. It is super optimized and also works in parallel. I would recommend checking it out. I read that some people are facing memory issues on kaggle while extracting metadata. Hope it helps such people.", "978863": "Thanks. \nHelped a lot. Saved a good amount of time as i was not aware of this format.", "972270": "Very useful! I was about to try and write something like this myself...saved me some time :)", "971369": "Thanks for this. Very new to DICOM and this is a great help.", "988421": "@gpreda I tried passing a folder\n\n`extract_DICOM_attributes('/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00007637202177411956430')`\n\nbut got error name 'dcm' is not defined. I am giving the folder path correctly?\n", "1325065": "Thank you so much. This was really helpful 😊", "1002928": "" } }