颅面个体化植入物头颅CT集合

数据集获取（Figshare）

• 源站标题：Head CT collection for patient-specific craniofacial implant (PSI) design
• DOI：10.6084/m9.figshare.12423872.v2
• 发布日期：2021-03-05
• 文件数：74 个
• 文件总体积：781.57 MB
• 源站页面：https://figshare.com/articles/dataset/Head_CT_collection_for_patient-specific_craniofacial_implant_PSI_design/12423872

命令行下载

curl -L -o "CT Skull.png" "https://ndownloader.figshare.com/files/26707220"
curl -L -o "readme.txt" "https://ndownloader.figshare.com/files/25532336"
curl -L -o "Case01.zip" "https://ndownloader.figshare.com/files/23423120"
curl -L -o "Case02.zip" "https://ndownloader.figshare.com/files/23423123"
curl -L -o "Case03.zip" "https://ndownloader.figshare.com/files/23423126"
curl -L -o "Case04.zip" "https://ndownloader.figshare.com/files/23423129"
curl -L -o "Case05.zip" "https://ndownloader.figshare.com/files/23423132"
curl -L -o "Case06.zip" "https://ndownloader.figshare.com/files/23423135"

文件清单

• CT Skull.png（559.38 KB）
• readme.txt（551 B）
• Case01.zip（11.72 MB）
• Case02.zip（12.82 MB）
• Case03.zip（27.60 MB）
• Case04.zip（8.14 MB）
• Case05.zip（14.55 MB）
• Case06.zip（15.23 MB）
• Case07.zip（27.69 MB）
• Case08.zip（13.78 MB）
• Case09.zip（9.78 MB）
• Case10.zip（8.18 MB）
• Case11.zip（7.48 MB）
• Case12.zip（46.98 MB）
• Case13.zip（58.84 MB）
• Case14.zip（38.49 MB）
• Case15.zip（48.07 MB）
• Case16.zip（37.47 MB）
• Case17.zip（46.87 MB）
• Case18.zip（48.03 MB）

文件总体积 781.57 MB（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

Patient-specific cranial implants are used to repair bone defects in the human skull after trauma or previous surgery. Currently, cranial implants are designed and produced by third-party suppliers, which is both time-consuming and expensive. Recent advances in additive manufacturing (AM) made the in-hospital or in-operation room (in-OR) fabrication of personalized implants feasible. However, the design of implants is still manually performed by external manufacturer. To facilitate an optimized surgical workflow, fast and automatic implant design is highly desirable. Data-driven approaches, such as deep learning, show great potential towards automatic implant design. However, a considerable amount of data is needed to train such algorithms which is, especially in the medical domain, often a bottleneck. Therefore, we present a data set containing CT scans of healthy skulls from 24 patients, in which we injected various artificial cranial defects, resulting in 240 data pairs. In addition, we provide the 240 corresponding implants for these data pairs. With our collection, we also disclose a toolbox for processing our data, providing users wanting to work on automatic cranial implant design a solid base for their research.

Toolbox Link:https://github.com/Jianningli/SciData

Please use the following citation if you use the data in your work:J. Li, et al. Head CT Collection for Patient-specific Craniofacial Implant (PSI) Design. Figshare, 2020.J. Li, et al. Synthetic Skull Bone Defects for automatic Patient-specific Craniofacial Implant Design. Sci. Data, 2020.

The datasets can be viewed with StudierFenster:www.studierfenster.at

Please see also our AutoImplant Challenge for cranial implant design:https://autoimplant.grand-challenge.org/

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.12423872.v2（source: https://figshare.com/articles/dataset/Head_CT_collection_for_patient-specific_craniofacial_implant_PSI_design/12423872）。