[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFK2YXRAVCSGSQVKC7384R":3,"skill-same:01M6AFK2YXRAVCSGSQVKC7384R":111},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":34,"publishedAt":58,"linkOnly":59,"markdownContent":60,"markdownBody":61,"frontMatter":62,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":68,"ownerHtmlUrl":69,"ownerBlogUrl":70,"ownerDescription":71,"updatedAt":72,"install":73,"resources":86},"01M6AFK2YXRAVCSGSQVKC7384R","pydicom",null,"Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33286,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[5,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"healthcare","when","formats","reading","extracting","imaging","communications","processing","medical","pixel","files","images","writing","analysis","applications","Ray","data","library","metadata","tasks","workflows","python","image","2026-11-10 10:12:30",false,"---\nname: pydicom\ndescription: Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.\n---\n\n# Pydicom\n\n## Overview\n\nPydicom is a pure Python package for working with DICOM files, the standard format for medical imaging data. This skill provides guidance on reading, writing, and manipulating DICOM files, including working with pixel data, metadata, and various compression formats.\n\n## When to Use This Skill\n\nUse this skill when working with:\n- Medical imaging files (CT, MRI, X-ray, ultrasound, PET, etc.)\n- DICOM datasets requiring metadata extraction or modification\n- Pixel data extraction and image processing from medical scans\n- DICOM anonymization for research or data sharing\n- Converting DICOM files to standard image formats\n- Compressed DICOM data requiring decompression\n- DICOM sequences and structured reports\n- Multi-slice volume reconstruction\n- PACS (Picture Archiving and Communication System) integration\n\n## Installation\n\nInstall pydicom and common dependencies:\n\n```bash\nuv pip install pydicom\nuv pip install pillow  # For image format conversion\nuv pip install numpy   # For pixel array manipulation\nuv pip install matplotlib  # For visualization\n```\n\nFor handling compressed DICOM files, additional packages may be needed:\n\n```bash\nuv pip install pylibjpeg pylibjpeg-libjpeg pylibjpeg-openjpeg  # JPEG compression\nuv pip install python-gdcm  # Alternative compression handler\n```\n\n## Core Workflows\n\n### Reading DICOM Files\n\nRead a DICOM file using `pydicom.dcmread()`:\n\n```python\nimport pydicom\n\n# Read a DICOM file\nds = pydicom.dcmread('path\u002Fto\u002Ffile.dcm')\n\n# Access metadata\nprint(f\"Patient Name: {ds.PatientName}\")\nprint(f\"Study Date: {ds.StudyDate}\")\nprint(f\"Modality: {ds.Modality}\")\n\n# Display all elements\nprint(ds)\n```\n\n**Key points:**\n- `dcmread()` returns a `Dataset` object\n- Access data elements using attribute notation (e.g., `ds.PatientName`) or tag notation (e.g., `ds[0x0010, 0x0010]`)\n- Use `ds.file_meta` to access file metadata like Transfer Syntax UID\n- Handle missing attributes with `getattr(ds, 'AttributeName', default_value)` or `hasattr(ds, 'AttributeName')`\n\n### Working with Pixel Data\n\nExtract and manipulate image data from DICOM files:\n\n```python\nimport pydicom\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# Read DICOM file\nds = pydicom.dcmread('image.dcm')\n\n# Get pixel array (requires numpy)\npixel_array = ds.pixel_array\n\n# Image information\nprint(f\"Shape: {pixel_array.shape}\")\nprint(f\"Data type: {pixel_array.dtype}\")\nprint(f\"Rows: {ds.Rows}, Columns: {ds.Columns}\")\n\n# Apply windowing for display (CT\u002FMRI)\nif hasattr(ds, 'WindowCenter') and hasattr(ds, 'WindowWidth'):\n    from pydicom.pixel_data_handlers.util import apply_voi_lut\n    windowed_image = apply_voi_lut(pixel_array, ds)\nelse:\n    windowed_image = pixel_array\n\n# Display image\nplt.imshow(windowed_image, cmap='gray')\nplt.title(f\"{ds.Modality} - {ds.StudyDescription}\")\nplt.axis('off')\nplt.show()\n```\n\n**Working with color images:**\n\n```python\n# RGB images have shape (rows, columns, 3)\nif ds.PhotometricInterpretation == 'RGB':\n    rgb_image = ds.pixel_array\n    plt.imshow(rgb_image)\nelif ds.PhotometricInterpretation == 'YBR_FULL':\n    from pydicom.pixel_data_handlers.util import convert_color_space\n    rgb_image = convert_color_space(ds.pixel_array, 'YBR_FULL', 'RGB')\n    plt.imshow(rgb_image)\n```\n\n**Multi-frame images (videos\u002Fseries):**\n\n```python\n# For multi-frame DICOM files\nif hasattr(ds, 'NumberOfFrames') and ds.NumberOfFrames > 1:\n    frames = ds.pixel_array  # Shape: (num_frames, rows, columns)\n    print(f\"Number of frames: {frames.shape[0]}\")\n\n    # Display specific frame\n    plt.imshow(frames[0], cmap='gray')\n```\n\n### Converting DICOM to Image Formats\n\nUse the provided `dicom_to_image.py` script or convert manually:\n\n```python\nfrom PIL import Image\nimport pydicom\nimport numpy as np\n\nds = pydicom.dcmread('input.dcm')\npixel_array = ds.pixel_array\n\n# Normalize to 0-255 range\nif pixel_array.dtype != np.uint8:\n    pixel_array = ((pixel_array - pixel_array.min()) \u002F\n                   (pixel_array.max() - pixel_array.min()) * 255).astype(np.uint8)\n\n# Save as PNG\nimage = Image.fromarray(pixel_array)\nimage.save('output.png')\n```\n\nUse the script: `python scripts\u002Fdicom_to_image.py input.dcm output.png`\n\n### Modifying Metadata\n\nModify DICOM data elements:\n\n```python\nimport pydicom\nfrom datetime import datetime\n\nds = pydicom.dcmread('input.dcm')\n\n# Modify existing elements\nds.PatientName = \"Doe^John\"\nds.StudyDate = datetime.now().strftime('%Y%m%d')\nds.StudyDescription = \"Modified Study\"\n\n# Add new elements\nds.SeriesNumber = 1\nds.SeriesDescription = \"New Series\"\n\n# Remove elements\nif hasattr(ds, 'PatientComments'):\n    delattr(ds, 'PatientComments')\n# Or using del\nif 'PatientComments' in ds:\n    del ds.PatientComments\n\n# Save modified file\nds.save_as('modified.dcm')\n```\n\n### Anonymizing DICOM Files\n\nRemove or replace patient identifiable information:\n\n```python\nimport pydicom\nfrom datetime import datetime\n\nds = pydicom.dcmread('input.dcm')\n\n# Tags commonly containing PHI (Protected Health Information)\ntags_to_anonymize = [\n    'PatientName', 'PatientID', 'PatientBirthDate',\n    'PatientSex', 'PatientAge', 'PatientAddress',\n    'InstitutionName', 'InstitutionAddress',\n    'ReferringPhysicianName', 'PerformingPhysicianName',\n    'OperatorsName', 'StudyDescription', 'SeriesDescription',\n]\n\n# Remove or replace sensitive data\nfor tag in tags_to_anonymize:\n    if hasattr(ds, tag):\n        if tag in ['PatientName', 'PatientID']:\n            setattr(ds, tag, 'ANONYMOUS')\n        elif tag == 'PatientBirthDate':\n            setattr(ds, tag, '19000101')\n        else:\n            delattr(ds, tag)\n\n# Update dates to maintain temporal relationships\nif hasattr(ds, 'StudyDate'):\n    # Shift dates by a random offset\n    ds.StudyDate = '20000101'\n\n# Keep pixel data intact\nds.save_as('anonymized.dcm')\n```\n\nUse the provided script: `python scripts\u002Fanonymize_dicom.py input.dcm output.dcm`\n\n### Writing DICOM Files\n\nCreate DICOM files from scratch:\n\n```python\nimport pydicom\nfrom pydicom.dataset import Dataset, FileDataset\nfrom datetime import datetime\nimport numpy as np\n\n# Create file meta information\nfile_meta = Dataset()\nfile_meta.MediaStorageSOPClassUID = pydicom.uid.generate_uid()\nfile_meta.MediaStorageSOPInstanceUID = pydicom.uid.generate_uid()\nfile_meta.TransferSyntaxUID = pydicom.uid.ExplicitVRLittleEndian\n\n# Create the FileDataset instance\nds = FileDataset('new_dicom.dcm', {}, file_meta=file_meta, preamble=b\"\\0\" * 128)\n\n# Add required DICOM elements\nds.PatientName = \"Test^Patient\"\nds.PatientID = \"123456\"\nds.Modality = \"CT\"\nds.StudyDate = datetime.now().strftime('%Y%m%d')\nds.StudyTime = datetime.now().strftime('%H%M%S')\nds.ContentDate = ds.StudyDate\nds.ContentTime = ds.StudyTime\n\n# Add image-specific elements\nds.SamplesPerPixel = 1\nds.PhotometricInterpretation = \"MONOCHROME2\"\nds.Rows = 512\nds.Columns = 512\nds.BitsAllocated = 16\nds.BitsStored = 16\nds.HighBit = 15\nds.PixelRepresentation = 0\n\n# Create pixel data\npixel_array = np.random.randint(0, 4096, (512, 512), dtype=np.uint16)\nds.PixelData = pixel_array.tobytes()\n\n# Add required UIDs\nds.SOPClassUID = pydicom.uid.CTImageStorage\nds.SOPInstanceUID = file_meta.MediaStorageSOPInstanceUID\nds.SeriesInstanceUID = pydicom.uid.generate_uid()\nds.StudyInstanceUID = pydicom.uid.generate_uid()\n\n# Save the file\nds.save_as('new_dicom.dcm')\n```\n\n### Compression and Decompression\n\nHandle compressed DICOM files:\n\n```python\nimport pydicom\n\n# Read compressed DICOM file\nds = pydicom.dcmread('compressed.dcm')\n\n# Check transfer syntax\nprint(f\"Transfer Syntax: {ds.file_meta.TransferSyntaxUID}\")\nprint(f\"Transfer Syntax Name: {ds.file_meta.TransferSyntaxUID.name}\")\n\n# Decompress and save as uncompressed\nds.decompress()\nds.save_as('uncompressed.dcm', write_like_original=False)\n\n# Or compress when saving (requires appropriate encoder)\nds_uncompressed = pydicom.dcmread('uncompressed.dcm')\nds_uncompressed.compress(pydicom.uid.JPEGBaseline8Bit)\nds_uncompressed.save_as('compressed_jpeg.dcm')\n```\n\n**Common transfer syntaxes:**\n- `ExplicitVRLittleEndian` - Uncompressed, most common\n- `JPEGBaseline8Bit` - JPEG lossy compression\n- `JPEGLossless` - JPEG lossless compression\n- `JPEG2000Lossless` - JPEG 2000 lossless\n- `RLELossless` - Run-Length Encoding lossless\n\nSee `references\u002Ftransfer_syntaxes.md` for complete list.\n\n### Working with DICOM Sequences\n\nHandle nested data structures:\n\n```python\nimport pydicom\n\nds = pydicom.dcmread('file.dcm')\n\n# Access sequences\nif 'ReferencedStudySequence' in ds:\n    for item in ds.ReferencedStudySequence:\n        print(f\"Referenced SOP Instance UID: {item.ReferencedSOPInstanceUID}\")\n\n# Create a sequence\nfrom pydicom.sequence import Sequence\n\nsequence_item = Dataset()\nsequence_item.ReferencedSOPClassUID = pydicom.uid.CTImageStorage\nsequence_item.ReferencedSOPInstanceUID = pydicom.uid.generate_uid()\n\nds.ReferencedImageSequence = Sequence([sequence_item])\n```\n\n### Processing DICOM Series\n\nWork with multiple related DICOM files:\n\n```python\nimport pydicom\nimport numpy as np\nfrom pathlib import Path\n\n# Read all DICOM files in a directory\ndicom_dir = Path('dicom_series\u002F')\nslices = []\n\nfor file_path in dicom_dir.glob('*.dcm'):\n    ds = pydicom.dcmread(file_path)\n    slices.append(ds)\n\n# Sort by slice location or instance number\nslices.sort(key=lambda x: float(x.ImagePositionPatient[2]))\n# Or: slices.sort(key=lambda x: int(x.InstanceNumber))\n\n# Create 3D volume\nvolume = np.stack([s.pixel_array for s in slices])\nprint(f\"Volume shape: {volume.shape}\")  # (num_slices, rows, columns)\n\n# Get spacing information for proper scaling\npixel_spacing = slices[0].PixelSpacing  # [row_spacing, col_spacing]\nslice_thickness = slices[0].SliceThickness\nprint(f\"Voxel size: {pixel_spacing[0]}x{pixel_spacing[1]}x{slice_thickness} mm\")\n```\n\n## Helper Scripts\n\nThis skill includes utility scripts in the `scripts\u002F` directory:\n\n### anonymize_dicom.py\nAnonymize DICOM files by removing or replacing Protected Health Information (PHI).\n\n```bash\npython scripts\u002Fanonymize_dicom.py input.dcm output.dcm\n```\n\n### dicom_to_image.py\nConvert DICOM files to common image formats (PNG, JPEG, TIFF).\n\n```bash\npython scripts\u002Fdicom_to_image.py input.dcm output.png\npython scripts\u002Fdicom_to_image.py input.dcm output.jpg --format JPEG\n```\n\n### extract_metadata.py\nExtract and display DICOM metadata in a readable format.\n\n```bash\npython scripts\u002Fextract_metadata.py file.dcm\npython scripts\u002Fextract_metadata.py file.dcm --output metadata.txt\n```\n\n## Reference Materials\n\nDetailed reference information is available in the `references\u002F` directory:\n\n- **common_tags.md**: Comprehensive list of commonly used DICOM tags organized by category (Patient, Study, Series, Image, etc.)\n- **transfer_syntaxes.md**: Complete reference of DICOM transfer syntaxes and compression formats\n\n## Common Issues and Solutions\n\n**Issue: \"Unable to decode pixel data\"**\n- Solution: Install additional compression handlers: `uv pip install pylibjpeg pylibjpeg-libjpeg python-gdcm`\n\n**Issue: \"AttributeError\" when accessing tags**\n- Solution: Check if attribute exists with `hasattr(ds, 'AttributeName')` or use `ds.get('AttributeName', default)`\n\n**Issue: Incorrect image display (too dark\u002Fbright)**\n- Solution: Apply VOI LUT windowing: `apply_voi_lut(pixel_array, ds)` or manually adjust with `WindowCenter` and `WindowWidth`\n\n**Issue: Memory issues with large series**\n- Solution: Process files iteratively, use memory-mapped arrays, or downsample images\n\n## Best Practices\n\n1. **Always check for required attributes** before accessing them using `hasattr()` or `get()`\n2. **Preserve file metadata** when modifying files by using `save_as()` with `write_like_original=True`\n3. **Use Transfer Syntax UIDs** to understand compression format before processing pixel data\n4. **Handle exceptions** when reading files from untrusted sources\n5. **Apply proper windowing** (VOI LUT) for medical image visualization\n6. **Maintain spatial information** (pixel spacing, slice thickness) when processing 3D volumes\n7. **Verify anonymization** thoroughly before sharing medical data\n8. **Use UIDs correctly** - generate new UIDs when creating new instances, preserve them when modifying\n\n## Documentation\n\nOfficial pydicom documentation: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002F\n- User Guide: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Fguides\u002Fuser\u002Findex.html\n- Tutorials: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Ftutorials\u002Findex.html\n- API Reference: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Freference\u002Findex.html\n- Examples: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Fauto_examples\u002Findex.html\n","# Pydicom\n\n## Overview\n\nPydicom is a pure Python package for working with DICOM files, the standard format for medical imaging data. This skill provides guidance on reading, writing, and manipulating DICOM files, including working with pixel data, metadata, and various compression formats.\n\n## When to Use This Skill\n\nUse this skill when working with:\n- Medical imaging files (CT, MRI, X-ray, ultrasound, PET, etc.)\n- DICOM datasets requiring metadata extraction or modification\n- Pixel data extraction and image processing from medical scans\n- DICOM anonymization for research or data sharing\n- Converting DICOM files to standard image formats\n- Compressed DICOM data requiring decompression\n- DICOM sequences and structured reports\n- Multi-slice volume reconstruction\n- PACS (Picture Archiving and Communication System) integration\n\n## Installation\n\nInstall pydicom and common dependencies:\n\n```bash\nuv pip install pydicom\nuv pip install pillow  # For image format conversion\nuv pip install numpy   # For pixel array manipulation\nuv pip install matplotlib  # For visualization\n```\n\nFor handling compressed DICOM files, additional packages may be needed:\n\n```bash\nuv pip install pylibjpeg pylibjpeg-libjpeg pylibjpeg-openjpeg  # JPEG compression\nuv pip install python-gdcm  # Alternative compression handler\n```\n\n## Core Workflows\n\n### Reading DICOM Files\n\nRead a DICOM file using `pydicom.dcmread()`:\n\n```python\nimport pydicom\n\n# Read a DICOM file\nds = pydicom.dcmread('path\u002Fto\u002Ffile.dcm')\n\n# Access metadata\nprint(f\"Patient Name: {ds.PatientName}\")\nprint(f\"Study Date: {ds.StudyDate}\")\nprint(f\"Modality: {ds.Modality}\")\n\n# Display all elements\nprint(ds)\n```\n\n**Key points:**\n- `dcmread()` returns a `Dataset` object\n- Access data elements using attribute notation (e.g., `ds.PatientName`) or tag notation (e.g., `ds[0x0010, 0x0010]`)\n- Use `ds.file_meta` to access file metadata like Transfer Syntax UID\n- Handle missing attributes with `getattr(ds, 'AttributeName', default_value)` or `hasattr(ds, 'AttributeName')`\n\n### Working with Pixel Data\n\nExtract and manipulate image data from DICOM files:\n\n```python\nimport pydicom\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# Read DICOM file\nds = pydicom.dcmread('image.dcm')\n\n# Get pixel array (requires numpy)\npixel_array = ds.pixel_array\n\n# Image information\nprint(f\"Shape: {pixel_array.shape}\")\nprint(f\"Data type: {pixel_array.dtype}\")\nprint(f\"Rows: {ds.Rows}, Columns: {ds.Columns}\")\n\n# Apply windowing for display (CT\u002FMRI)\nif hasattr(ds, 'WindowCenter') and hasattr(ds, 'WindowWidth'):\n    from pydicom.pixel_data_handlers.util import apply_voi_lut\n    windowed_image = apply_voi_lut(pixel_array, ds)\nelse:\n    windowed_image = pixel_array\n\n# Display image\nplt.imshow(windowed_image, cmap='gray')\nplt.title(f\"{ds.Modality} - {ds.StudyDescription}\")\nplt.axis('off')\nplt.show()\n```\n\n**Working with color images:**\n\n```python\n# RGB images have shape (rows, columns, 3)\nif ds.PhotometricInterpretation == 'RGB':\n    rgb_image = ds.pixel_array\n    plt.imshow(rgb_image)\nelif ds.PhotometricInterpretation == 'YBR_FULL':\n    from pydicom.pixel_data_handlers.util import convert_color_space\n    rgb_image = convert_color_space(ds.pixel_array, 'YBR_FULL', 'RGB')\n    plt.imshow(rgb_image)\n```\n\n**Multi-frame images (videos\u002Fseries):**\n\n```python\n# For multi-frame DICOM files\nif hasattr(ds, 'NumberOfFrames') and ds.NumberOfFrames > 1:\n    frames = ds.pixel_array  # Shape: (num_frames, rows, columns)\n    print(f\"Number of frames: {frames.shape[0]}\")\n\n    # Display specific frame\n    plt.imshow(frames[0], cmap='gray')\n```\n\n### Converting DICOM to Image Formats\n\nUse the provided `dicom_to_image.py` script or convert manually:\n\n```python\nfrom PIL import Image\nimport pydicom\nimport numpy as np\n\nds = pydicom.dcmread('input.dcm')\npixel_array = ds.pixel_array\n\n# Normalize to 0-255 range\nif pixel_array.dtype != np.uint8:\n    pixel_array = ((pixel_array - pixel_array.min()) \u002F\n                   (pixel_array.max() - pixel_array.min()) * 255).astype(np.uint8)\n\n# Save as PNG\nimage = Image.fromarray(pixel_array)\nimage.save('output.png')\n```\n\nUse the script: `python scripts\u002Fdicom_to_image.py input.dcm output.png`\n\n### Modifying Metadata\n\nModify DICOM data elements:\n\n```python\nimport pydicom\nfrom datetime import datetime\n\nds = pydicom.dcmread('input.dcm')\n\n# Modify existing elements\nds.PatientName = \"Doe^John\"\nds.StudyDate = datetime.now().strftime('%Y%m%d')\nds.StudyDescription = \"Modified Study\"\n\n# Add new elements\nds.SeriesNumber = 1\nds.SeriesDescription = \"New Series\"\n\n# Remove elements\nif hasattr(ds, 'PatientComments'):\n    delattr(ds, 'PatientComments')\n# Or using del\nif 'PatientComments' in ds:\n    del ds.PatientComments\n\n# Save modified file\nds.save_as('modified.dcm')\n```\n\n### Anonymizing DICOM Files\n\nRemove or replace patient identifiable information:\n\n```python\nimport pydicom\nfrom datetime import datetime\n\nds = pydicom.dcmread('input.dcm')\n\n# Tags commonly containing PHI (Protected Health Information)\ntags_to_anonymize = [\n    'PatientName', 'PatientID', 'PatientBirthDate',\n    'PatientSex', 'PatientAge', 'PatientAddress',\n    'InstitutionName', 'InstitutionAddress',\n    'ReferringPhysicianName', 'PerformingPhysicianName',\n    'OperatorsName', 'StudyDescription', 'SeriesDescription',\n]\n\n# Remove or replace sensitive data\nfor tag in tags_to_anonymize:\n    if hasattr(ds, tag):\n        if tag in ['PatientName', 'PatientID']:\n            setattr(ds, tag, 'ANONYMOUS')\n        elif tag == 'PatientBirthDate':\n            setattr(ds, tag, '19000101')\n        else:\n            delattr(ds, tag)\n\n# Update dates to maintain temporal relationships\nif hasattr(ds, 'StudyDate'):\n    # Shift dates by a random offset\n    ds.StudyDate = '20000101'\n\n# Keep pixel data intact\nds.save_as('anonymized.dcm')\n```\n\nUse the provided script: `python scripts\u002Fanonymize_dicom.py input.dcm output.dcm`\n\n### Writing DICOM Files\n\nCreate DICOM files from scratch:\n\n```python\nimport pydicom\nfrom pydicom.dataset import Dataset, FileDataset\nfrom datetime import datetime\nimport numpy as np\n\n# Create file meta information\nfile_meta = Dataset()\nfile_meta.MediaStorageSOPClassUID = pydicom.uid.generate_uid()\nfile_meta.MediaStorageSOPInstanceUID = pydicom.uid.generate_uid()\nfile_meta.TransferSyntaxUID = pydicom.uid.ExplicitVRLittleEndian\n\n# Create the FileDataset instance\nds = FileDataset('new_dicom.dcm', {}, file_meta=file_meta, preamble=b\"\\0\" * 128)\n\n# Add required DICOM elements\nds.PatientName = \"Test^Patient\"\nds.PatientID = \"123456\"\nds.Modality = \"CT\"\nds.StudyDate = datetime.now().strftime('%Y%m%d')\nds.StudyTime = datetime.now().strftime('%H%M%S')\nds.ContentDate = ds.StudyDate\nds.ContentTime = ds.StudyTime\n\n# Add image-specific elements\nds.SamplesPerPixel = 1\nds.PhotometricInterpretation = \"MONOCHROME2\"\nds.Rows = 512\nds.Columns = 512\nds.BitsAllocated = 16\nds.BitsStored = 16\nds.HighBit = 15\nds.PixelRepresentation = 0\n\n# Create pixel data\npixel_array = np.random.randint(0, 4096, (512, 512), dtype=np.uint16)\nds.PixelData = pixel_array.tobytes()\n\n# Add required UIDs\nds.SOPClassUID = pydicom.uid.CTImageStorage\nds.SOPInstanceUID = file_meta.MediaStorageSOPInstanceUID\nds.SeriesInstanceUID = pydicom.uid.generate_uid()\nds.StudyInstanceUID = pydicom.uid.generate_uid()\n\n# Save the file\nds.save_as('new_dicom.dcm')\n```\n\n### Compression and Decompression\n\nHandle compressed DICOM files:\n\n```python\nimport pydicom\n\n# Read compressed DICOM file\nds = pydicom.dcmread('compressed.dcm')\n\n# Check transfer syntax\nprint(f\"Transfer Syntax: {ds.file_meta.TransferSyntaxUID}\")\nprint(f\"Transfer Syntax Name: {ds.file_meta.TransferSyntaxUID.name}\")\n\n# Decompress and save as uncompressed\nds.decompress()\nds.save_as('uncompressed.dcm', write_like_original=False)\n\n# Or compress when saving (requires appropriate encoder)\nds_uncompressed = pydicom.dcmread('uncompressed.dcm')\nds_uncompressed.compress(pydicom.uid.JPEGBaseline8Bit)\nds_uncompressed.save_as('compressed_jpeg.dcm')\n```\n\n**Common transfer syntaxes:**\n- `ExplicitVRLittleEndian` - Uncompressed, most common\n- `JPEGBaseline8Bit` - JPEG lossy compression\n- `JPEGLossless` - JPEG lossless compression\n- `JPEG2000Lossless` - JPEG 2000 lossless\n- `RLELossless` - Run-Length Encoding lossless\n\nSee `references\u002Ftransfer_syntaxes.md` for complete list.\n\n### Working with DICOM Sequences\n\nHandle nested data structures:\n\n```python\nimport pydicom\n\nds = pydicom.dcmread('file.dcm')\n\n# Access sequences\nif 'ReferencedStudySequence' in ds:\n    for item in ds.ReferencedStudySequence:\n        print(f\"Referenced SOP Instance UID: {item.ReferencedSOPInstanceUID}\")\n\n# Create a sequence\nfrom pydicom.sequence import Sequence\n\nsequence_item = Dataset()\nsequence_item.ReferencedSOPClassUID = pydicom.uid.CTImageStorage\nsequence_item.ReferencedSOPInstanceUID = pydicom.uid.generate_uid()\n\nds.ReferencedImageSequence = Sequence([sequence_item])\n```\n\n### Processing DICOM Series\n\nWork with multiple related DICOM files:\n\n```python\nimport pydicom\nimport numpy as np\nfrom pathlib import Path\n\n# Read all DICOM files in a directory\ndicom_dir = Path('dicom_series\u002F')\nslices = []\n\nfor file_path in dicom_dir.glob('*.dcm'):\n    ds = pydicom.dcmread(file_path)\n    slices.append(ds)\n\n# Sort by slice location or instance number\nslices.sort(key=lambda x: float(x.ImagePositionPatient[2]))\n# Or: slices.sort(key=lambda x: int(x.InstanceNumber))\n\n# Create 3D volume\nvolume = np.stack([s.pixel_array for s in slices])\nprint(f\"Volume shape: {volume.shape}\")  # (num_slices, rows, columns)\n\n# Get spacing information for proper scaling\npixel_spacing = slices[0].PixelSpacing  # [row_spacing, col_spacing]\nslice_thickness = slices[0].SliceThickness\nprint(f\"Voxel size: {pixel_spacing[0]}x{pixel_spacing[1]}x{slice_thickness} mm\")\n```\n\n## Helper Scripts\n\nThis skill includes utility scripts in the `scripts\u002F` directory:\n\n### anonymize_dicom.py\nAnonymize DICOM files by removing or replacing Protected Health Information (PHI).\n\n```bash\npython scripts\u002Fanonymize_dicom.py input.dcm output.dcm\n```\n\n### dicom_to_image.py\nConvert DICOM files to common image formats (PNG, JPEG, TIFF).\n\n```bash\npython scripts\u002Fdicom_to_image.py input.dcm output.png\npython scripts\u002Fdicom_to_image.py input.dcm output.jpg --format JPEG\n```\n\n### extract_metadata.py\nExtract and display DICOM metadata in a readable format.\n\n```bash\npython scripts\u002Fextract_metadata.py file.dcm\npython scripts\u002Fextract_metadata.py file.dcm --output metadata.txt\n```\n\n## Reference Materials\n\nDetailed reference information is available in the `references\u002F` directory:\n\n- **common_tags.md**: Comprehensive list of commonly used DICOM tags organized by category (Patient, Study, Series, Image, etc.)\n- **transfer_syntaxes.md**: Complete reference of DICOM transfer syntaxes and compression formats\n\n## Common Issues and Solutions\n\n**Issue: \"Unable to decode pixel data\"**\n- Solution: Install additional compression handlers: `uv pip install pylibjpeg pylibjpeg-libjpeg python-gdcm`\n\n**Issue: \"AttributeError\" when accessing tags**\n- Solution: Check if attribute exists with `hasattr(ds, 'AttributeName')` or use `ds.get('AttributeName', default)`\n\n**Issue: Incorrect image display (too dark\u002Fbright)**\n- Solution: Apply VOI LUT windowing: `apply_voi_lut(pixel_array, ds)` or manually adjust with `WindowCenter` and `WindowWidth`\n\n**Issue: Memory issues with large series**\n- Solution: Process files iteratively, use memory-mapped arrays, or downsample images\n\n## Best Practices\n\n1. **Always check for required attributes** before accessing them using `hasattr()` or `get()`\n2. **Preserve file metadata** when modifying files by using `save_as()` with `write_like_original=True`\n3. **Use Transfer Syntax UIDs** to understand compression format before processing pixel data\n4. **Handle exceptions** when reading files from untrusted sources\n5. **Apply proper windowing** (VOI LUT) for medical image visualization\n6. **Maintain spatial information** (pixel spacing, slice thickness) when processing 3D volumes\n7. **Verify anonymization** thoroughly before sharing medical data\n8. **Use UIDs correctly** - generate new UIDs when creating new instances, preserve them when modifying\n\n## Documentation\n\nOfficial pydicom documentation: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002F\n- User Guide: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Fguides\u002Fuser\u002Findex.html\n- Tutorials: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Ftutorials\u002Findex.html\n- API Reference: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Freference\u002Findex.html\n- Examples: https:\u002F\u002Fpydicom.github.io\u002Fpydicom\u002Fdev\u002Fauto_examples\u002Findex.html\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom",3909,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-11 11:53:30",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add davila7\u002Fclaude-code-templates --skill pydicom",{"tool":79,"command":80},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill pydicom",{"tool":82,"command":83},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill pydicom","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002FSKILL.md",true,[87,93,97,103,107],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fcommon_tags.md","REFERENCE","参考文档",10246,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002Freferences\u002Fcommon_tags.md",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Ftransfer_syntaxes.md",9627,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002Freferences\u002Ftransfer_syntaxes.md",{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fanonymize_dicom.py","SCRIPT","脚本",5254,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002Fscripts\u002Fanonymize_dicom.py",{"path":104,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fdicom_to_image.py",6101,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002Fscripts\u002Fdicom_to_image.py",{"path":108,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Fextract_metadata.py",5686,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fpydicom\u002Fscripts\u002Fextract_metadata.py",[112,139,166,197,232,255],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":58},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[118],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[120,121,122,123,124,125,126,127,128,36,129,130,131,132,133,134,135,136,137,138],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":58},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[145],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[147,148,149,150,151,152,153,154,155,156,157,36,158,159,160,161,162,163,164,165],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":179,"publishedAt":58},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[172,175,176],{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":177,"categoryName":178,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000033","数据分析师",[180,181,182,183,184,185,186,125,187,188,189,190,191,192,193,128,194,195,36,196],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":201,"licenseFileUrl":202,"sourceHtmlUrl":203,"categories":204,"keywords":208,"publishedAt":58},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[205],{"categoryNo":206,"categoryName":207,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,125,231],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":201,"licenseFileUrl":236,"sourceHtmlUrl":237,"categories":238,"keywords":243,"publishedAt":58},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[239,242],{"categoryNo":240,"categoryName":241,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":206,"categoryName":207,"taxonomyType":21,"taxonomyTypeDesc":22},[244,245,246,247,248,210,49,219,220,249,250,251,252,125,253,130,254],"webapp testing","testing","webapp","browser","playwright","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":256,"name":257,"nameZh":6,"description":258,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":201,"licenseFileUrl":259,"sourceHtmlUrl":260,"categories":261,"keywords":265,"publishedAt":58},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[262,263,264],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},[266,267,268,269,270,271,51,47,212,272,222,158,273,274,275,276,277,192,278,36,279,48,280,281,282,136,283],"discernment nudge","nudge","interpretation","help","run","reasoning","lookup","content","review","conversation","short","up","invoke","you","claims","argument","assemble","recommendations"]