高催乳素血症MRI原始数据集

数据集获取（Figshare）

• 源站标题：<p>File containing raw dataset.</p>
• DOI：10.1371/journal.pone.0346134.s001
• 发布日期：2026-04-08
• 文件数：1 个
• 文件总体积：333.95 KB
• 源站页面：https://plos.figshare.com/articles/dataset/_p_File_containing_raw_dataset_p_/31966054

命令行下载

curl -L -o "pone.0346134.s001.xlsx" "https://ndownloader.figshare.com/files/63566164"

文件清单

• pone.0346134.s001.xlsx（333.95 KB）

文件总体积 333.95 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

Background
Hyperprolactinemia is a common biochemical finding detected in primary care, and guidelines suggest confirmation with a second prolactin measurement to rule out spurious elevation prior to further workup. Premature magnetic resonance imaging (MRI) is a costly potential consequence of improperly worked-up hyperprolactinemia. We aimed to quantify the proportion of prematurely ordered MRI for isolated hyperprolactinemia without confirmation.
Methods
A retrospective chart review was performed between 2012–2021 in Alberta, Canada. We identified cases of mildly elevated serum prolactin (18 years who underwent MRI brain or sella following prolactin measurement. MRI was classified as “clinically appropriate” or “premature” based on clinical indication. Clinically appropriate and premature groups were compared based on patient age, sex, and scan year.
Results
We identified 1,730 cases meeting inclusion criteria with a single prolactin measurement prior to MRI; over half (56.1%, n = 970) were categorized as “premature.” Of the MRIs in the premature cohort, 39.4% (n = 382) reported at least one abnormal finding, most commonly microadenoma (n = 200). There was no statistically significant difference between premature and clinically appropriate groups for patient sex (p = 0.12) or year of MRI (p = 0.35), but patients in the premature group were significantly older (p Conclusions
MRI for investigation of mild hyperprolactinemia is often ordered prematurely without confirmation by repeat prolactin level and generates incidental findings of uncertain clinical significance to the presenting issue. To reduce patient stress and healthcare system burden, providers should ensure proper workup of hyperprolactinemia with repeat prolactin measurement prior to ordering MRI.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0346134.s001（source: https://plos.figshare.com/articles/dataset/_p_File_containing_raw_dataset_p_/31966054）。