HAM10000
HAM10000包含10000张皮肤镜图像，用于皮肤癌良恶性分类，辅助黑色素瘤检测。
基本信息
资源简介
HAM10000
【数据集背景】
本数据集源站标题为《smit-6690/Melanoma-Skin-Cancer-Detection》。源站首次发布：2024-10-18。
【数据内容】
源站原始描述：This project aims to detect melanoma, a type of skin cancer, using Convolutional Neural Networks (CNN). The model is trained on the HAM10000 dataset, which contains images of localized skin cells. It predicts whether a tumor in the input image is benign or malignant with an accuracy of approximately 90%. # Skin Cancer Detection Using CNN This project aims to detect melanoma, a type of skin cancer, using Convolutional Neural Networks (CNN). The model is trained on the HAM10000 dataset, which cont…
【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://github.com/smit-6690/Melanoma-Skin-Cancer-Detection
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。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放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。
使用方式
数据集获取
git clone https://github.com/smit-6690/Melanoma-Skin-Cancer-Detection.git
curl -L -o repo.zip https://github.com/smit-6690/Melanoma-Skin-Cancer-Detection/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
Skin Cancer Detection Using CNN
This project aims to detect melanoma, a type of skin cancer, using Convolutional Neural Networks (CNN). The model is trained on the HAM10000 dataset, which contains images of localized skin cells. It predicts whether a tumor in the input image is benign or malignant with an accuracy of approximately 90%.
Dataset
The HAM10000 dataset consists of 10000 dermatoscopic images. Each image is labeled with either ‘‘Benign’’ or ‘‘Malignant’’ class. If the given input image lies in ‘‘Benign’’ class then the cells are non-cancerous else they are cancerous.
Technologies Used
- TensorFlow
- Keras
- Streamlit
Model Architecture
The Convolutional Neural Network (CNN) architecture used for this project consists of multiple convolutional layers followed by max-pooling layers for feature extraction. The extracted features are then passed through fully connected layers for classification. The model is trained using the HAM10000 dataset with appropriate data augmentation techniques to improve generalization.
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。
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
