Hands-Free Image Capture, Data Tagging and Transfer Using Google Glass: A Pilot Study for Improved Wound Care Management

数据集获取（Figshare）

• 源站标题：Hands-Free Image Capture, Data Tagging and Transfer Using Google Glass: A Pilot Study for Improved Wound Care Management
• DOI：10.1371/journal.pone.0121179
• 发布日期：2015-04-22
• 文件数：4 个
• 文件总体积：19.16 MB
• 源站页面：https://plos.figshare.com/articles/dataset/_Hands_Free_Image_Capture_Data_Tagging_and_Transfer_Using_Google_Glass_A_Pilot_Study_for_Improved_Wound_Care_Management_/1391058

命令行下载

curl -L -o "S1_Fig.pdf" "https://ndownloader.figshare.com/files/2035341"
curl -L -o "S2_Fig.pdf" "https://ndownloader.figshare.com/files/2035342"
curl -L -o "S3_Fig.pdf" "https://ndownloader.figshare.com/files/2035343"
curl -L -o "S4_Fig.pdf" "https://ndownloader.figshare.com/files/2035344"

文件清单

• S1_Fig.pdf（64.53 KB）
• S2_Fig.pdf（18.98 MB）
• S3_Fig.pdf（57.83 KB）
• S4_Fig.pdf（54.87 KB）

文件总体积 19.16 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

Chronic wounds, including pressure ulcers, compromise the health of 6.5 million Americans and pose an annual estimated burden of $25 billion to the U.S. health care system. When treating chronic wounds, clinicians must use meticulous documentation to determine wound severity and to monitor healing progress over time. Yet, current wound documentation practices using digital photography are often cumbersome and labor intensive. The process of transferring photos into Electronic Medical Records (EMRs) requires many steps and can take several days. Newer smartphone and tablet-based solutions, such as Epic Haiku, have reduced EMR upload time. However, issues still exist involving patient positioning, image-capture technique, and patient identification. In this paper, we present the development and assessment of the SnapCap System for chronic wound photography. Through leveraging the sensor capabilities of Google Glass, SnapCap enables hands-free digital image capture, and the tagging and transfer of images to a patient’s EMR. In a pilot study with wound care nurses at Stanford Hospital (n=16), we (i) examined feature preferences for hands-free digital image capture and documentation, and (ii) compared SnapCap to the state of the art in digital wound care photography, the Epic Haiku application. We used the Wilcoxon Signed-ranks test to evaluate differences in mean ranks between preference options. Preferred hands-free navigation features include barcode scanning for patient identification, Z(15) = -3.873, p < 0.001, r = 0.71, and double-blinking to take photographs, Z(13) = -3.606, p < 0.001, r = 0.71. In the comparison between SnapCap and Epic Haiku, the SnapCap System was preferred for sterile image-capture technique, Z(16) = -3.873, p < 0.001, r = 0.68. Responses were divided with respect to image quality and overall ease of use. The study’s results have contributed to the future implementation of new features aimed at enhancing mobile hands-free digital photography for chronic wound care.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0121179（source: https://plos.figshare.com/articles/dataset/_Hands_Free_Image_Capture_Data_Tagging_and_Transfer_Using_Google_Glass_A_Pilot_Study_for_Improved_Wound_Care_Management_/1391058）。