全血细胞计数数据集
360张血涂片图像及边界框标注，用于血细胞识别和计数，支持目标检测任务。
基本信息
资源简介
全血细胞计数数据集
【数据集背景】
本数据集源站标题为《CBC》。
【主题与分类】
主题标签：{''id'': 11861, ''datasetId'': 25774, ''domain'': ''publishDate'', ''task'': ''2019'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''2019'', ''level1TagName'': ''2019'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11862, ''datasetId'': 25774, ''domain'': ''publisher'', ''task'': ''Bangladesh University of Engineering and Technology'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''Bangladesh University of Engineering and Technology'', ''level1TagName'': ''Bangladesh University of Engineering and Technology'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11859, ''datasetId'': 25774, ''domain'': ''labelTypes'', ''task'': ''Box2D'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''Box2D'', ''level1TagName'': ''Box2D'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11860, ''datasetId'': 25774, ''domain'': ''displayName'', ''task'': ''CBC (Complete Blood Count)'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''CBC (Complete Blood Count)'', ''level1TagName'': ''CBC (Complete Blood Count)'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11864, ''datasetId'': 25774, ''domain'': ''publishUrl'', ''task'': ''https://github.com/MahmudulAlam/Complete-Blood-Cell-Count-Dataset'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''https://github.com/MahmudulAlam/Complete-Blood-Cell-Count-Dataset'', ''level1TagName'': ''https://github.com/MahmudulAlam/Complete-Blood-Cell-Count-Dataset'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11857, ''datasetId'': 25774, ''domain'': ''paperUrl'', ''task'': ''https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl.2018.5098'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl.2018.5098'', ''level1TagName'': ''https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl.2018.5098'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11858, ''datasetId'': 25774, ''domain'': ''mediaTypes'', ''task'': ''Image'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''Image'', ''level1TagName'': ''Image'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}、{''id'': 11863, ''datasetId'': 25774, ''domain'': ''taskTypes'', ''task'': ''Object Detection'', ''filter'': None, ''label'': None, ''dataType'': 0, ''level1Tag'': ''Object Detection'', ''level1TagName'': ''Object Detection'', ''level2Tag'': None, ''level2TagName'': None, ''level3Tag'': None, ''level3TagName'': None, ''gmtCreate'': 1719850307, ''gmtModified'': 1719850307, ''tagId'': None}。
【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://modelscope.cn/datasets/OmniData/CBC
使用许可：[MIT]。
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（ModelScope）
方式一：MsDataset（Python）
# 前置依赖: pip install modelscope
from modelscope.msdatasets import MsDataset
ds = MsDataset.load("OmniData/CBC", subset_name="default", split="train")
print(ds)
方式二：CLI（命令行）
pip install modelscope
modelscope download dataset OmniData/CBC
数据集卡片摘录（源站）
displayName: CBC (Complete Blood Count)
labelTypes:
-
Box2D
license: -
MIT
mediaTypes: -
Image
paperUrl: https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl.2018.5098
publishDate: “2019”
publishUrl: https://github.com/MahmudulAlam/Complete-Blood-Cell-Count-Dataset
publisher: -
Bangladesh University of Engineering and Technology
tags: -
Hemocyte
taskTypes: -
Object Detection
数据集介绍
简介
全血细胞计数 (CBC) 数据集包含 360 张血涂片图像及其注释文件，分为训练集、测试集和验证集。训练文件夹包含 300 张带注释的图像。测试和验证文件夹都包含 60 张带注释的图像。我们对原始数据集进行了一些修改以准备此 CBC 数据集，其中一些图像注释文件包含的红细胞 (RBC) 比实际值非常低，并且一个注释文件根本不包含任何 RBC，尽管细胞涂片图像包含 RBC .因此，我们清除所有错误文件并将数据集分成三个部分。在 360 张涂片图像中，先将 300 张带注释的血细胞图像作为训练集，然后将剩下的 60 张带注释的图像作为测试集。由于数据不足，训练集的一个子集用于准备验证集，其中包含 60 张带注释的图像。
引文
@article{alam2019machine,
title={Machine learning approach of automatic identification and counting of blood cells},
author={Alam, Mohammad Mahmudul and Islam, Mohammad Tariqul},
journal={Healthcare technology letters},
volume={6},
number={4},
pages={103108},
year={2019},
publisher={IET}
}
Download dataset
:modelscope-code[]
许可
[MIT]
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。
