AI看到的癌症图像(乳腺癌、前列腺癌、胰腺癌)

AI生成的乳腺癌、前列腺癌和胰腺癌图像数据集,包含文件名说明,用于研究AI在癌症视觉沟通中的表现。

Figshare
2024-06-24 更新
浏览 16
图像Social discourseSociologyCancer discoursesPublic health discoursesVisual sociologyGenerative Artificial Intelligence
00_README_FilenamesWhat does AI see

基本信息

模态
图像
大小
0.000001461 GB
许可
CC BY 4.0
创建/更新时间
2024-06-24
版本
v2

资源简介

AI看到的癌症图像(乳腺癌、前列腺癌、胰腺癌)

【数据集背景】

本数据集源站标题为《00_README_FilenamesWhat does AI see》。源站首次发布:2026-02-06。

【数据内容】

源站原始描述:This file describes the filenaming system used in the files for project "AI-generated images of breast, prostate and pancreatic cancer - What does Artificial Intelligence see?" Visual cancer communication often leans on survivorship discourses, shunning other experiences and negating the medical dimension of cancer. Generative AI has emerged as a helpful tool in the generation images in cancer communication. While AI provides an opportunity to promote more inclusive visual discourses, it may als…

文件 What does AI see_File naming for Figshare.txt 为文本内容,开头为:File naming: - Files are named using the prompt identifier (ID) first, and then the code for each AI (SD = Stable Diffusion). A file called "5_2_SD" is a …

【数据结构与技术规格】

文件数 1 个,合计 1.46 KB。What does AI see_File naming for Figshare.txt:text/plain,1.46 KB。数据集 DOI:10.6084/m9.figshare.26088070.v2。

【主题与分类】

源站学科分类:Applications in social sciences and education、Public health not elsewhere classified、Artificial intelligence not elsewhere classified。主题标签:Social discourse、Sociology、Cancer discourses、Public health discourses、Visual sociology、Generative Artificial Intelligence。

【适用方向】

影像类数据可用于医学图像分析模型(检测、分割、分类)的训练与评测,也可用于标注质量与成像参数相关性的研究。

【获取与许可】

源站页面:https://figshare.com/articles/dataset/A_README_Filenames/26088070

使用许可:CC BY 4.0(https://creativecommons.org/licenses/by/4.0/)。

规范引用:Varela-Rodríguez, Miguel (2024). 00_README_FilenamesWhat does AI see. figshare. Dataset

下载信息

注册下载

需要注册 Kaggle 账号并登录后下载,适合需要跟踪下载记录和使用 API 的用户。

暂未开放

公开下载

无需注册即可直接获取公开样本或文档,适合快速预览和评估数据集质量。

免登录

当前数据集主要来源为 Kaggle 公开托管,完整影像包建议通过原始链接或 Kaggle API 获取。

免费样本无法满足模型训练要求?千方提供经三甲医院脱敏、带病理回证与专家标注的商业级专病数据集。

使用方式

数据集获取(Figshare)

命令行下载

curl -L -o "What does AI see_File naming for Figshare.txt" "https://ndownloader.figshare.com/files/47209813"

文件清单

  • What does AI see_File naming for Figshare.txt(1.46 KB)

文件总体积 1.46 KB(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

This file describes the filenaming system used in the files for project “AI-generated images of breast, prostate and pancreatic cancer - What does Artificial Intelligence see?”
Visual cancer communication often leans on survivorship discourses, shunning other experiences and negating the medical dimension of cancer. Generative AI has emerged as a helpful tool in the generation images in cancer communication. While AI provides an opportunity to promote more inclusive visual discourses, it may also reproduce dominant discourses. This raises the questions, what does cancer look like in the imagination of AI, and what can this tell us about the public image of cancer?

These images were generated by Dall-E 2.0 and Stable Diffusion in response to a series of prompts related to breast, prostate and pancreatic cancer, and cancer in general.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.26088070.v2(source: https://figshare.com/articles/dataset/A_README_Filenames/26088070)。

需要用于商业化训练或医疗器械注册(NMPA/FDA)?

公开数据往往缺乏完整的病理回证与专家标注。千方医数集依托三甲直采网络,提供合规、去标识化、支持注册级质控的专病数据集交易服务。