多发性硬化症MRI数据集合集
该数据集是一个整合了多个公开子集的多发性硬化症MRI图像集合，包含来自SCLEROSIS、ISBI 2015、MICCAI挑战赛等来源的数百张脑部MRI图像，数据模态主要为T1、T2和FLAIR等序列的医学影像，主要用于多发性硬化症的自动诊断、病变分割和纵向研究，支持医学影像分析算法的开发和评估。
基本信息
资源简介
多发性硬化症MRI数据集合集
【数据集背景】
本数据集源站标题为《RafaelKorb/iMRI-Dataset》。源站首次发布：2019-12-08。
【数据内容】
源站原始描述：Base de Dados Integrada de Imagens de Ressonância Magnética para Diagnóstico Automático de Esclerose Múltipla # projeto_tcc Introduction - This repository contains scripts to preprocessing MRI images of healthy and multiple sclerosis patients, based on NicMsLesions tool. Adapted to work with json, support unlimited number of datasets. The aim of this work is to provide a preprocessed magnetic resonance imaging base for the application of multiple scleros…
【获取与许可】
源站页面：https://github.com/RafaelKorb/iMRI-Dataset
【使用注意】
· 源站最后修改于 2023-10-03，引用时请注意版本时效。
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/RafaelKorb/iMRI-Dataset.git
curl -L -o repo.zip https://github.com/RafaelKorb/iMRI-Dataset/archive/refs/heads/master.zip
unzip repo.zip
源站 README 摘录（使用方式）
projeto_tcc
Introduction
This repository contains scripts to preprocessing MRI images of healthy and multiple sclerosis patients, based on NicMsLesions tool.
Adapted to work with json, support unlimited number of datasets.
The aim of this work is to provide a preprocessed magnetic resonance imaging base for the application of multiple sclerosis lesion classification and segmentation algorithms.
Datasets Images
The preprocessing work just with the modalities T1, T2 and FLAIR, and they three has to be present.
The json dictionary offers 5 public datasets images:
SCLEROSIS: 109 images
*ISBI 2015 (Longitudinal multiple sclerosis lesion segmentation challenge)
21 images
Training: 5 patients
Test: 14 patients
*ljubljana (Laboratory of Imaging Technologies)
30 images
Only training: 30 patients
Demographics Features:
“age”
“sex” (7 Male(“M”) 23 Female(“F”))
“ms_type” (disgnostic of desease by specialists)
Relapsing remitting(“RR”) - 24 cases
Clinically isolated syndrome(“CIS”) - 2 cases
Primary progressive(“PR”) - 1 case
Secondary progressive(“SP”) - 2 cases
Whitout diagnostic - 1 case
*MICCAI 2008 (International Conference on Medical Imaging and Computer Assisted Intervention - MS Lesion Segmentation Challenge)
51 images
Training: 20 patients
Test: 25 patients
Has no annotated features
*MICCAI 2016 (International Conference on Medical Imaging and Computer Assisted Intervention - MS Lesion Segmentation Challenge)
15 images
Only training: 15 patients
Features:
“age”
“sex” (7 Male 8 Female)
HEALTHY: 21
*KIRBY (Multi-Modal MRI Reproducibility Resource)
42 images
Puting on training: 21 patients
Features:
"ag
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。
