从放射科医生视角可靠准确区分视神经周围炎和视神经鞘脑膜瘤

数据集获取（Figshare）

• 源站标题：Reliable and Accurate Differentiation of Optic Perineuritis and Optic Nerve Sheath Meningioma from the Radiologists’ Perspective
• DOI：10.6084/m9.figshare.29910682.v1
• 发布日期：2025-08-14
• 文件数：2 个
• 文件总体积：87.57 KB
• 源站页面：https://tandf.figshare.com/articles/dataset/Reliable_and_Accurate_Differentiation_of_Optic_Perineuritis_and_Optic_Nerve_Sheath_Meningioma_from_the_Radiologists_Perspective/29910682

命令行下载

curl -L -o "ioph_a_2542229_sm5326.docx" "https://ndownloader.figshare.com/files/57189835"
curl -L -o "ioph_a_2542229_sm5325.docx" "https://ndownloader.figshare.com/files/57189838"

文件清单

• ioph_a_2542229_sm5326.docx（35.39 KB）
• ioph_a_2542229_sm5325.docx（52.17 KB）

文件总体积 87.57 KB（源站 API 实测）。

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。

数据说明

Optic perineuritis (OPN) and optic nerve sheath meningioma (ONSM) can present overlapping clinical and MRI findings. We aim to identify reliable MRI features to accurately differentiate between the two, ensuring timely optimal management. Patients diagnosed with OPN or ONSM were retrospectively selected. Two board-certified neuroradiologists independently reviewed contrast-enhanced, fat-saturated T1-weighted orbital MRI. Masked to patient information, they assessed nerve sheath contrast enhancement across optic nerve segments, quadrants, and intraconal fat, and measured maximum enhancing thickness (MET) and maximum enhancing length (MEL). Subsequently, they provided diagnoses based on their expertise. In a second run, controls were included, and they were allowed to see MRI order notes. Inter-rater agreements and diagnostic performances were calculated. We studied 35 patients with 41 pathological orbits. OPN had more bilateral involvement (p = .012). Only MET reached the desired agreement (ICC = .902). Mean MET was 1 mm for OPN and 5.34 mm for ONSM (p < .001). AUC was 0.823 with optimal threshold of 1.38 mm, giving 75% sensitivity, 73.8% specificity, and 74.3% accuracy. In the first evaluation, neuroradiologists demonstrated sensitivities of 56.3% and 62.5%, specificities of 78.9%, accuracies of 68.6% and 71.4%. In the second evaluation, first neuroradiologist accurately identified 50% of ONSM and 80% of OPN cases. Second neuroradiologist identified 100% of ONSM and 50% of OPN. Both neuroradiologists identified all controls. Neuroradiologists struggled to distinguish OPN from ONSM. MET is reliable, accurate, and useful for differentiating them alongside clinical features.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.29910682.v1（source: https://tandf.figshare.com/articles/dataset/Reliable_and_Accurate_Differentiation_of_Optic_Perineuritis_and_Optic_Nerve_Sheath_Meningioma_from_the_Radiologists_Perspective/29910682）。