皮肤科医生对黑色素瘤和痣皮肤镜图像AI辅助诊断的读者研究数据

数据集获取（Figshare）

• 源站标题：HAM10000 expert-annotated explanations and pseudonymized reader study data.
• DOI：10.6084/m9.figshare.23766477.v9
• 发布日期：2025-07-14
• 文件数：8 个
• 文件总体积：18.23 MB
• 源站页面：https://figshare.com/articles/dataset/Reader_study_data_of_dermatologists_diagnoses_confidence_and_trust_in_an_AI_system_on_dermoscopic_images_of_melanomas_and_nevi/23766477

命令行下载

curl -L -o "README.md" "https://ndownloader.figshare.com/files/44726692"
curl -L -o "metadata_phase1.csv" "https://ndownloader.figshare.com/files/41729526"
curl -L -o "metadata_phase2.csv" "https://ndownloader.figshare.com/files/41729529"
curl -L -o "metadata_phase3.csv" "https://ndownloader.figshare.com/files/41729532"
curl -L -o "Source Data.zip" "https://ndownloader.figshare.com/files/42372012"
curl -L -o "Datasets.zip" "https://ndownloader.figshare.com/files/42886087"
curl -L -o "metadata_gt.csv" "https://ndownloader.figshare.com/files/56238497"
curl -L -o "annotations_gt.zip" "https://ndownloader.figshare.com/files/56238653"

文件清单

• README.md（1.50 KB）
• metadata_phase1.csv（65.59 KB）
• metadata_phase2.csv（79.69 KB）
• metadata_phase3.csv（78.90 KB）
• Source Data.zip（1.03 MB）
• Datasets.zip（4.24 MB）
• metadata_gt.csv（256.30 KB）
• annotations_gt.zip（12.47 MB）

文件总体积 18.23 MB（源站 API 实测）。

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

数据说明

Reader study was conducted in 3 phases: no ai (phase 1), ai support (phase 2), xai support (phase 3). The data generated in each phase is available in metadata_phase1.csv, metadata_phase2.csv, and metadata_phase3.csv.
There are 113 unique participants in phase 1. Additional participants were added in phase 2, resulting in 116 unique clinicians in phases 2 and 3.
Important: The 3rd and 13th image in each group are identical. Be careful when performing table joins as the duplicate image_ids can affect them. In metadata_phase1.csv, the AI predictions for the 13th image in each group are null. Please take that into account when performing analysis. In metadata_phase2 and metadata_phase3, the AI predictions for the repeating images are not omitted.

participant: Each clinician was assigned a participant Id represented by the participant column.
group: Each clinician was randomly assigned to a group. Each group was assigned mutually exclusive sets of images.
mask: An internal identifier used for the images. Can be ignored.
benign_malignant: ground truth diagnosis.
prediction: Diagnosis chosen by the clinician. 1 represents melanoma, 0 represents nevus, 0.5 represents a nevus diagnosis but the clinician chose to excise.
confidence: Confidence value entered by the clinician.
trust: Trust value entered by the clinician.
AI_prediction: Diagnosis predicted by the AI. 1 represents melanoma and 0 represents nevus.
language: Language chosen by the clinician.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.23766477.v9（source: https://figshare.com/articles/dataset/Reader_study_data_of_dermatologists_diagnoses_confidence_and_trust_in_an_AI_system_on_dermoscopic_images_of_melanomas_and_nevi/23766477）。