MedSeg Covid Dataset 1

This is a dataset of 100 axial CT images from &gt;40 patients with COVID-19 that were converted from openly accessible JPG images found at https://www.sirm.org/en/ . The conversion process is described in detail in the following blogpost: https://medium.com/@hbjenssen/covid-19-radiology-data-collection-and-preparation-for-artificial-intelligence-4ecece97bb5b<br>In short, the images were segmented by a radiologist using 3 labels: <em>ground-glass</em> (mask value =1), <em>consolidation</em> (=2) and <em>pleural effusion</em> (=3). We then trained a 2d multilabel U-Net model, which you can find and apply in MedSeg

本数据集包含40余名新型冠状病毒肺炎（COVID-19）患者的100张轴位CT图像，所有图像均由公开可获取的JPG图像转换而来，来源网址为https://www.sirm.org/en/。
该转换流程的详细说明见下述博文：https://medium.com/@hbjenssen/covid-19-radiology-data-collection-and-preparation-for-artificial-intelligence-4ecece97bb5b
简言之，本数据集的图像已由放射科医师基于三类标签完成分割：磨玻璃影（ground-glass，掩码值=1）、实变（consolidation，掩码值=2）与胸腔积液（pleural effusion，掩码值=3）。随后我们训练了一款二维多标签U-Net模型，该模型可在MedSeg中获取并使用。

搜集汇总

背景与挑战

背景概述

该数据集包含100张COVID-19患者的CT图像，经过专业分割标注（磨玻璃样变、实变和胸腔积液），主要用于训练医学图像分割AI模型。数据来源于公开JPG图片的专业转换，具有明确的研究用途和医学价值。