pydicom DICOM Toolkit

uv pip install pydicom
uv pip install pillow  # For image format conversion
uv pip install numpy   # For pixel array manipulation
uv pip install matplotlib  # For visualization

uv pip install pylibjpeg pylibjpeg-libjpeg pylibjpeg-openjpeg  # JPEG compression
uv pip install python-gdcm  # Alternative compression handler

import pydicom

# Read a DICOM file
ds = pydicom.dcmread('path/to/file.dcm')

# Access metadata
print(f"Patient Name: {ds.PatientName}")
print(f"Study Date: {ds.StudyDate}")
print(f"Modality: {ds.Modality}")

# Display all elements
print(ds)

import pydicom
import numpy as np
import matplotlib.pyplot as plt

# Read DICOM file
ds = pydicom.dcmread('image.dcm')

# Get pixel array (requires numpy)
pixel_array = ds.pixel_array

# Image information
print(f"Shape: {pixel_array.shape}")
print(f"Data type: {pixel_array.dtype}")
print(f"Rows: {ds.Rows}, Columns: {ds.Columns}")

# Apply windowing for display (CT/MRI)
if hasattr(ds, 'WindowCenter') and hasattr(ds, 'WindowWidth'):
    from pydicom.pixel_data_handlers.util import apply_voi_lut
    windowed_image = apply_voi_lut(pixel_array, ds)
else:
    windowed_image = pixel_array

# Display image
plt.imshow(windowed_image, cmap='gray')
plt.title(f"{ds.Modality} - {ds.StudyDescription}")
plt.axis('off')
plt.show()

# RGB images have shape (rows, columns, 3)
if ds.PhotometricInterpretation == 'RGB':
    rgb_image = ds.pixel_array
    plt.imshow(rgb_image)
elif ds.PhotometricInterpretation == 'YBR_FULL':
    from pydicom.pixel_data_handlers.util import convert_color_space
    rgb_image = convert_color_space(ds.pixel_array, 'YBR_FULL', 'RGB')
    plt.imshow(rgb_image)

# For multi-frame DICOM files
if hasattr(ds, 'NumberOfFrames') and ds.NumberOfFrames > 1:
    frames = ds.pixel_array  # Shape: (num_frames, rows, columns)
    print(f"Number of frames: {frames.shape[0]}")

    # Display specific frame
    plt.imshow(frames[0], cmap='gray')

from PIL import Image
import pydicom
import numpy as np

ds = pydicom.dcmread('input.dcm')
pixel_array = ds.pixel_array

# Normalize to 0-255 range
if pixel_array.dtype != np.uint8:
    pixel_array = ((pixel_array - pixel_array.min()) /
                   (pixel_array.max() - pixel_array.min()) * 255).astype(np.uint8)

# Save as PNG
image = Image.fromarray(pixel_array)
image.save('output.png')

import pydicom
from datetime import datetime

ds = pydicom.dcmread('input.dcm')

# Modify existing elements
ds.PatientName = "Doe^John"
ds.StudyDate = datetime.now().strftime('%Y%m%d')
ds.StudyDescription = "Modified Study"

# Add new elements
ds.SeriesNumber = 1
ds.SeriesDescription = "New Series"

# Remove elements
if hasattr(ds, 'PatientComments'):
    delattr(ds, 'PatientComments')
# Or using del
if 'PatientComments' in ds:
    del ds.PatientComments

# Save modified file
ds.save_as('modified.dcm')

import pydicom
from datetime import datetime

ds = pydicom.dcmread('input.dcm')

# Tags commonly containing PHI (Protected Health Information)
tags_to_anonymize = [
    'PatientName', 'PatientID', 'PatientBirthDate',
    'PatientSex', 'PatientAge', 'PatientAddress',
    'InstitutionName', 'InstitutionAddress',
    'ReferringPhysicianName', 'PerformingPhysicianName',
    'OperatorsName', 'StudyDescription', 'SeriesDescription',
]

# Remove or replace sensitive data
for tag in tags_to_anonymize:
    if hasattr(ds, tag):
        if tag in ['PatientName', 'PatientID']:
            setattr(ds, tag, 'ANONYMOUS')
        elif tag == 'PatientBirthDate':
            setattr(ds, tag, '19000101')
        else:
            delattr(ds, tag)

# Update dates to maintain temporal relationships
if hasattr(ds, 'StudyDate'):
    # Shift dates by a random offset
    ds.StudyDate = '20000101'

# Keep pixel data intact
ds.save_as('anonymized.dcm')

import pydicom
from pydicom.dataset import Dataset, FileDataset
from datetime import datetime
import numpy as np

# Create file meta information
file_meta = Dataset()
file_meta.MediaStorageSOPClassUID = pydicom.uid.generate_uid()
file_meta.MediaStorageSOPInstanceUID = pydicom.uid.generate_uid()
file_meta.TransferSyntaxUID = pydicom.uid.ExplicitVRLittleEndian

# Create the FileDataset instance
ds = FileDataset('new_dicom.dcm', {}, file_meta=file_meta, preamble=b"\0" * 128)

# Add required DICOM elements
ds.PatientName = "Test^Patient"
ds.PatientID = "123456"
ds.Modality = "CT"
ds.StudyDate = datetime.now().strftime('%Y%m%d')
ds.StudyTime = datetime.now().strftime('%H%M%S')
ds.ContentDate = ds.StudyDate
ds.ContentTime = ds.StudyTime

# Add image-specific elements
ds.SamplesPerPixel = 1
ds.PhotometricInterpretation = "MONOCHROME2"
ds.Rows = 512
ds.Columns = 512
ds.BitsAllocated = 16
ds.BitsStored = 16
ds.HighBit = 15
ds.PixelRepresentation = 0

# Create pixel data
pixel_array = np.random.randint(0, 4096, (512, 512), dtype=np.uint16)
ds.PixelData = pixel_array.tobytes()

# Add required UIDs
ds.SOPClassUID = pydicom.uid.CTImageStorage
ds.SOPInstanceUID = file_meta.MediaStorageSOPInstanceUID
ds.SeriesInstanceUID = pydicom.uid.generate_uid()
ds.StudyInstanceUID = pydicom.uid.generate_uid()

# Save the file
ds.save_as('new_dicom.dcm')

import pydicom

# Read compressed DICOM file
ds = pydicom.dcmread('compressed.dcm')

# Check transfer syntax
print(f"Transfer Syntax: {ds.file_meta.TransferSyntaxUID}")
print(f"Transfer Syntax Name: {ds.file_meta.TransferSyntaxUID.name}")

# Decompress and save as uncompressed
ds.decompress()
ds.save_as('uncompressed.dcm', write_like_original=False)

# Or compress when saving (requires appropriate encoder)
ds_uncompressed = pydicom.dcmread('uncompressed.dcm')
ds_uncompressed.compress(pydicom.uid.JPEGBaseline8Bit)
ds_uncompressed.save_as('compressed_jpeg.dcm')

import pydicom

ds = pydicom.dcmread('file.dcm')

# Access sequences
if 'ReferencedStudySequence' in ds:
    for item in ds.ReferencedStudySequence:
        print(f"Referenced SOP Instance UID: {item.ReferencedSOPInstanceUID}")

# Create a sequence
from pydicom.sequence import Sequence

sequence_item = Dataset()
sequence_item.ReferencedSOPClassUID = pydicom.uid.CTImageStorage
sequence_item.ReferencedSOPInstanceUID = pydicom.uid.generate_uid()

ds.ReferencedImageSequence = Sequence([sequence_item])

import pydicom
import numpy as np
from pathlib import Path

# Read all DICOM files in a directory
dicom_dir = Path('dicom_series/')
slices = []

for file_path in dicom_dir.glob('*.dcm'):
    ds = pydicom.dcmread(file_path)
    slices.append(ds)

# Sort by slice location or instance number
slices.sort(key=lambda x: float(x.ImagePositionPatient[2]))
# Or: slices.sort(key=lambda x: int(x.InstanceNumber))

# Create 3D volume
volume = np.stack([s.pixel_array for s in slices])
print(f"Volume shape: {volume.shape}")  # (num_slices, rows, columns)

# Get spacing information for proper scaling
pixel_spacing = slices[0].PixelSpacing  # [row_spacing, col_spacing]
slice_thickness = slices[0].SliceThickness
print(f"Voxel size: {pixel_spacing[0]}x{pixel_spacing[1]}x{slice_thickness} mm")

python scripts/anonymize_dicom.py input.dcm output.dcm

python scripts/dicom_to_image.py input.dcm output.png
python scripts/dicom_to_image.py input.dcm output.jpg --format JPEG