使用 Potato 进行医学图像标注

Potato 的图像标注功能可用于标注医学图像，如 X 光片、皮肤病变照片或其他标准格式（PNG、JPG）的临床图像。本指南涵盖了设置医学图像标注项目的最佳实践。

重要注意事项

在启动任何医学标注项目之前：

去标识化：确保在标注前已从图像中移除所有受保护的健康信息（PHI）
数据处理：使用机构的安全基础设施存储和处理医学数据
访问控制：通过现有的身份验证系统管理标注者访问
合规性：与 IRB 和合规团队合作，满足机构要求

注意：Potato 是一个标注工具，不包含内置的 HIPAA 合规功能、DICOM 查看器或专用医学影像功能。这些需求应在基础设施层面解决。

基本医学图像标注设置

以下是为标准医学图像配置 Potato 的方法：

yaml

annotation_task_name: "Medical Image Annotation"
 
data_files:
  - path: data/medical_images.json
    type: json
 
annotation_schemes:
  - annotation_type: bounding_box
    name: lesions
    allow_multiple: true
    labels:
      - name: primary
        color: "#EF4444"
        description: "Primary finding"
 
      - name: secondary
        color: "#F97316"
        description: "Secondary finding"
 
      - name: artifact
        color: "#6B7280"
        description: "Artifact or noise"
 
  - annotation_type: radio
    name: image_quality
    question: "Overall image quality?"
    options:
      - name: diagnostic
        label: "Diagnostic Quality"
      - name: limited
        label: "Limited Quality"
      - name: non_diagnostic
        label: "Non-Diagnostic"

X 光片和临床照片标注

对于已导出为标准图像格式的 X 光片或临床照片：

yaml

annotation_task_name: "X-Ray Findings Annotation"
 
data_files:
  - path: data/xray_images.json
    type: json
 
annotation_schemes:
  - annotation_type: polygon
    name: abnormalities
    allow_multiple: true
    labels:
      - name: opacity
        color: "#EF4444"
        description: "Pulmonary opacity"
 
      - name: consolidation
        color: "#F97316"
        description: "Consolidation"
 
      - name: nodule
        color: "#EAB308"
        description: "Pulmonary nodule"
 
      - name: effusion
        color: "#3B82F6"
        description: "Pleural effusion"
 
  - annotation_type: multiselect
    name: findings
    question: "Select all findings present"
    options:
      - name: normal
        label: "No acute findings"
      - name: pneumonia
        label: "Pneumonia"
      - name: atelectasis
        label: "Atelectasis"
      - name: pneumothorax
        label: "Pneumothorax"
      - name: fracture
        label: "Fracture"

皮肤病变标注

用于皮肤科图像：

yaml

annotation_task_name: "Dermoscopy Annotation"
 
data_files:
  - path: data/skin_lesions.json
    type: json
 
annotation_schemes:
  - annotation_type: polygon
    name: lesion_boundary
    labels:
      - name: lesion
        color: "#EF4444"
        description: "Lesion boundary"
 
  - annotation_type: multiselect
    name: dermoscopic_features
    question: "Select all features present"
    options:
      - name: pigment_network
        label: "Pigment Network"
      - name: dots_globules
        label: "Dots/Globules"
      - name: streaks
        label: "Streaks"
      - name: blue_white_veil
        label: "Blue-White Veil"
      - name: regression
        label: "Regression Structures"
      - name: vascular
        label: "Vascular Structures"
 
  - annotation_type: radio
    name: diagnosis
    question: "Most likely diagnosis?"
    options:
      - name: benign_nevus
        label: "Benign Nevus"
      - name: seborrheic_keratosis
        label: "Seborrheic Keratosis"
      - name: basal_cell
        label: "Basal Cell Carcinoma"
      - name: melanoma
        label: "Melanoma"
      - name: other
        label: "Other"
 
  - annotation_type: likert
    name: confidence
    question: "Diagnostic confidence"
    size: 5
    min_label: "Low"
    max_label: "High"

视网膜图像标注

用于眼底照片和其他视网膜图像：

yaml

annotation_task_name: "Fundus Image Annotation"
 
data_files:
  - path: data/fundus_images.json
    type: json
 
annotation_schemes:
  - annotation_type: polygon
    name: anatomical_structures
    labels:
      - name: optic_disc
        color: "#FDE68A"
        description: "Optic disc boundary"
 
      - name: fovea
        color: "#A78BFA"
        description: "Fovea region"
 
      - name: macula
        color: "#93C5FD"
        description: "Macular region"
 
  - annotation_type: polygon
    name: pathology
    allow_multiple: true
    labels:
      - name: hemorrhage
        color: "#EF4444"
        description: "Retinal hemorrhage"
 
      - name: exudate
        color: "#FCD34D"
        description: "Hard/soft exudate"
 
      - name: microaneurysm
        color: "#F97316"
        description: "Microaneurysm"
 
  - annotation_type: radio
    name: dr_grade
    question: "Diabetic retinopathy grade"
    options:
      - name: none
        label: "No DR"
      - name: mild
        label: "Mild NPDR"
      - name: moderate
        label: "Moderate NPDR"
      - name: severe
        label: "Severe NPDR"
      - name: proliferative
        label: "PDR"

数据格式

以 JSON 格式准备图像数据：

json

[
  {
    "id": "case_001",
    "image": "images/case_001.png",
    "metadata": {
      "body_part": "chest",
      "modality": "xray"
    }
  },
  {
    "id": "case_002",
    "image": "images/case_002.png",
    "metadata": {
      "body_part": "chest",
      "modality": "xray"
    }
  }
]

注意：图像必须为标准的 Web 兼容格式（PNG、JPG 等）。DICOM 文件需要在使用 Potato 之前转换为标准图像格式。

最佳实践

使用合格的标注者：医学标注需要临床专业知识——确保标注者接受过适当培训
预处理图像：将专用格式（DICOM 等）转换为标准图像格式，并确保 PHI 已移除
多标注者：让多个标注者标注每张图像以衡量标注者间一致性
清晰的指南：提供针对临床领域的详细标注指南
质量检查：包含金标准案例以监控标注者准确性
机构合规：与合规团队合作确保数据处理符合要求

局限性

Potato 提供通用图像标注，不包含：

原生 DICOM 文件支持或 DICOM 查看器
全切片图像（WSI）查看器及多分辨率缩放
内置 HIPAA 合规或审计日志
医学资质验证
专业放射学窗位工具

如需这些功能，请考虑预处理数据或将 Potato 与专业医学影像基础设施集成。

有关图像标注的更多信息，请参阅 /docs/features/image-annotation。