简单的批量匿名化dicom的代码，

将INPUT_DIR里的子文件夹保存的每个案例的dicom数据匿名化（删除隐私信息），输出到OUTPUT_DIR

if __name__ == "__main__":
    INPUT_DIR = r"D:\code\GYN_plans_nodose_153"
    OUTPUT_DIR = r"D:\code\GYN_Anonymized_153"
    main(INPUT_DIR, OUTPUT_DIR)

遍历子文件夹进行处理：

def main(input_directory, output_directory):
    """
    Anonymize all DICOM files in each subfolder of the input directory and save to an output directory.
    """
    for patient_folder in os.listdir(input_directory):
        patient_folder_path = os.path.join(input_directory, patient_folder)
        if os.path.isdir(patient_folder_path):
            anonymize_dicom_directory(patient_folder_path, output_directory)
            print(f"Anonymized DICOM files from: {patient_folder_path}")

def anonymize_dicom_directory(input_directory, output_directory):
    """
    Anonymize all DICOM files in an input directory and save to an output directory.
    """
    for root, dirs, files in os.walk(input_directory):
        for file in files:
            if file.endswith(".dcm"):  # Assuming DICOM files have .dcm extension
                dicom_path = os.path.join(root, file)
                anonymize_dicom_file(dicom_path, output_directory)

针对单个dcm文件，自定义新的ID和Name，处理需要匿名化的tag：

def anonymize_dicom_file(dicom_path, output_path):
    """
    Anonymize a single DICOM file and save to a new directory.
    """
    dataset = pydicom.dcmread(dicom_path)
    
    # Anonymize the required tags
    if "PatientID" in dataset:
        old_id = dataset.data_element("PatientID").value
        new_id = "Test" + old_id
        dataset.data_element("PatientID").value = new_id
        
    if "PatientName" in dataset:
        old_name = str(dataset.data_element("PatientName").value)
        new_name = "Anonymized" + extract_initials(old_name)
        dataset.data_element("PatientName").value = new_name
    
    # Define the tags to be anonymized (can be extended)
    tags_to_anonymize = [
        "InstitutionName", 
        #"PatientBirthDate",
        #"PatientAddress",
        # Add more tags as necessary
    ]

    for tag in tags_to_anonymize:
        if tag in dataset:
            dataset.data_element(tag).value = ""

    # Create the output directory if it doesn't exist
    output_dir = os.path.join(output_path, dataset.data_element("PatientID").value)
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)
    
    # Save the anonymized DICOM to the output directory
    output_file_path = os.path.join(output_dir, os.path.basename(dicom_path))
    dataset.save_as(output_file_path)

# use initial character of each word,  as new name
def extract_initials(name):
    #print(name)
    words = name.split()
    initials = [word[0].upper() for word in words]
    return ''.join(initials)