Malaria dataset (thin blood smear, updated)

Giemsa-stained thin blood smear slides from 150 P. falciparum-infected and 50 healthy patients were collected and photographed at Chittagong Medical College Hospital, Bangladesh. The smartphone’s built-in camera acquired images of slides for each microscopic field of view. Initially, the images were manually annotated by an expert slide reader at the Mahidol-Oxford Tropical Medicine Research Unit in Bangkok, Thailand (the originals can be found at NLM, ftp://lhcftp.nlm.nih.gov/Open-Access-Datasets/Malaria/).nbsp;Due to the fact that a relatively large proportion of images was mislabeled, the dataset has been double-checked and relabeled by Michael Delves. The images have been reorganised into five folders: parasitised, uninfected, weird, bad segmentation, unsure.本数据集采集自孟加拉国吉大港医学院附属医院的150份恶性疟原虫（Plasmodium falciparum）感染患者与50份健康受试者的吉姆萨染色薄血涂片，并完成拍摄。采用智能手机内置摄像头采集每个显微视野下的血涂片图像。最初，图像由泰国曼谷玛希隆-牛津热带医学研究中心的专业玻片阅片专家进行人工标注（原始数据集可于美国国立医学图书馆（National Library of Medicine，NLM）的FTP地址ftp://lhcftp.nlm.nih.gov/Open-Access-Datasets/Malaria/获取）。由于存在相当比例的图像标注错误，该数据集已由Michael Delves完成双重校验与重新标注。目前所有图像已被整理至5个文件夹中，分别为：感染样本（parasitised）、未感染样本（uninfected）、异常样本（weird）、分割不良样本（bad segmentation）、不确定样本（unsure）。

搜集汇总

背景与挑战

背景概述

该数据集是一个经过更新和验证的疟疾薄血涂片图像集合，包含来自感染者和健康患者的智能手机拍摄图像，并经过专家重新标注以确保准确性。数据集已结构化分为五个类别，适用于疟疾诊断和机器学习研究，具有高可靠性和组织性。