PTX-498: A multi-center pneumothorax segmentation chest X-ray image dataset

Pneumothorax is a common medical emergency defined as the abnormal collection of air in the pleural space between the lung and chest wall. Its typical symptoms include chest pain and dyspnea, leading to oxygen deficiency or even life-threatening in severe cases. Therefore, an efficient and automatic pneumothorax diagnosis algorithm would be useful in many clinical scenarios. Recently, deep learning methods have achieved impressive progress in medical image segmentation tasks. However, a large-scale dataset is one of the critical components for the success of deep learning. On the other hand, there are few public chest X-ray images with pneumothorax. To stimulate the researchers' interest in the pneumothorax diagnosis algorithm, we released a new data set PTX-498 here. It contains 498 chest X-ray images of pneumothorax collected from three hospitals, and each image contains pixel-level annotations. All images were resized to 1024×1024. The raw image intensity was clipped according to the window width and level inside the dicom tag and then normalized to 0 to 255. The contours of the pneumothorax area were labelled by two senior radiologists using ITK-SNAP. The dataset was anonymized and every record related to patients' privacy was removed. Only the image data and the corresponding labels were included in PTX-498. Please use the latest v2-fix version which removes duplicate images and uses the window width and level from the original dicom tag for normalization. Citation: If you are interested in this dataset and applying it in your research, please cite the following article. Paper link: https://doi.org/10.1016/j.neucom.2021.05.029 Cite this article as Yunpeng Wang, Kang Wang, Xueqing Peng, Lili Shi, Jing Sun, Shibao Zheng, Fei Shan, Weiya Shi, Lei Liu*. DeepSDM: Boundary-aware pneumothorax segmentation in chest X-ray images [J]. Neurocomputing, 2021, 454: 201-211.

气胸（Pneumothorax）是一类常见的急危重症，指肺与胸壁之间的胸膜腔内出现异常积气。其典型临床表现为胸痛与呼吸困难，重症患者可引发缺氧，甚至危及生命。因此，高效自动的气胸诊断算法在诸多临床场景中具备重要应用价值。近年来，深度学习方法在医学图像分割任务中取得了令人瞩目的进展。然而，大规模数据集是深度学习模型取得成功的核心要素之一。另一方面，当前公开可用的气胸相关胸部X线影像资源较为匮乏。为激发研究者在气胸诊断算法领域的研究兴趣，我们在此发布全新数据集PTX-498。该数据集包含来自三家医院的498幅气胸相关胸部X线影像，每幅图像均配有像素级标注。所有图像均被统一调整至1024×1024分辨率。原始图像的灰度值将根据医学数字成像与通信（DICOM）标签中的窗宽（window width）与窗位（window level）进行截断，随后归一化至0至255区间。气胸区域的轮廓由两名资深放射科医师使用ITK-SNAP软件完成标注。本数据集已完成匿名化处理，所有涉及患者隐私的信息均已移除，仅保留图像数据与对应的标注标签。请使用最新的v2-fix版本，该版本已去除重复图像，并采用原始DICOM标签中的窗宽与窗位进行归一化处理。引用说明：若您对本数据集感兴趣并将其应用于研究工作，请引用以下论文。论文链接：https://doi.org/10.1016/j.neucom.2021.05.029。引用格式如下：Yunpeng Wang, Kang Wang, Xueqing Peng, Lili Shi, Jing Sun, Shibao Zheng, Fei Shan, Weiya Shi, Lei Liu*. DeepSDM: Boundary-aware pneumothorax segmentation in chest X-ray images [J]. Neurocomputing, 2021, 454: 201-211.

搜集汇总

背景与挑战

背景概述

PTX-498是一个多中心气胸分割胸部X光图像数据集，包含来自三家医院的498张图像，每张图像都有像素级标注，图像尺寸统一为1024×1024。该数据集经过匿名化处理，旨在促进气胸诊断算法的研究。