内镜下直入路Draf IIa（Carolyn窗入路）与内镜下斜入路Draf IIa治疗伴额窦受累慢性鼻窦炎的对比研究

数据集获取

源站：https://clinicaltrials.gov/study/NCT06668844

标准获取流程：

1. 访问源站链接，注册/登录账号；
2. 进入数据集详情页，按页面指引申请权限或直接下载；
3. 部分平台提供 SDK，例如：
   • OpenDataLab: pip install openxlab 后 openxlab.dataset.get(...)
   • ModelScope: pip install modelscope 后 modelscope download
   • 天池: 登录后页面提供直链下载
     以源站「数据下载/使用文档」页面为准。

数据说明

Conditions: Chronic Rhinosinusitis (CRS), Frontal Sinusitis, Draf I or IIa, Functional Endoscopic Sinus Surgery (FESS). Frontal sinus surgery is a challenging component of endoscopic sinus surgery due to the intricacy and variability of frontal recess and sinus anatomy. Before the introduction of endoscopy in sinus surgery, complex cases of the frontal sinus were managed through the anterior wall using an osteoplastic flap approach. This technique was relatively successful in treating frontal sinus pathologies, but was invasive with adverse effects and failure in 6-25 percent of patients. Different endoscopic techniques have been introduced for performing frontal sinusotomy. Draf categorized them into four techniques (Draf I, Draf IIa, Draf IIb, Draf III). Draf II procedures widen the frontal sinus outflow tract from the lamina papyracea laterally to the middle turbinate (Draf IIa) or the nasal septum medially (Draf IIb). The thickness of the nasofrontal beak, and a limited anterior-posterior dimension of the frontal recess, make the Draf IIa frontal sinus surgery with angled endoscopy and instrumentation visually diffcult and requires skilled dexterity. The direct access or Carolyn’s window approach to the frontal recess replicates Draf’s technique via the endoscopic approach. The approach utilizes only the 0° endoscope. In this approach, the entire frontal process of the maxilla, agger nasi and nasal process of the frontal bone, is removed with a high-speed drill.The goal of the approach is to visualize all walls of the frontal sinus via a ° endoscope. This postoperative view predicts better irrigation access and drainage of the frontal sinuses.

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。