IVCM角膜炎数据集

数据集获取（Figshare）

• 源站标题：Dataset
• DOI：10.6084/m9.figshare.19838083.v2
• 发布日期：2022-06-10
• 文件数：4 个
• 文件总体积：223.49 MB
• 源站页面：https://figshare.com/articles/dataset/Dataset/19838083

命令行下载

curl -L -o "FK pic-20210204T031833Z-001.zip" "https://ndownloader.figshare.com/files/35248996"
curl -L -o "normal-20210630T193110Z-001.zip" "https://ndownloader.figshare.com/files/35248999"
curl -L -o "NSK pic-20210204T031836Z-001.zip" "https://ndownloader.figshare.com/files/35249002"
curl -L -o "AK.zip" "https://ndownloader.figshare.com/files/35846723"

文件清单

• FK pic-20210204T031833Z-001.zip（56.40 MB）
• normal-20210630T193110Z-001.zip（31.22 MB）
• NSK pic-20210204T031836Z-001.zip（15.52 MB）
• AK.zip（120.35 MB）

文件总体积 223.49 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

Infectious keratitis is a group of corneal disorders in which corneal tissues suffer inflammation and damage caused by pathogenic infections. Among these, Fungal Keratitis (FK) and Acanthamoeba Keratitis (AK) are some of the most severe, with a high chance of permanent blindness if they are not diagnosed early and accurately. In Vivo Confocal Microscopy (IVCM) allows the imaging of different layers of the cornea, providing an important tool for an early and more accurate diagnosis. In this paper, we introduce the IVCM-Keratitis dataset consisting of a total of 4001 sample images of AK and FK, as well as Non-Specific Keratitis (NSK) and healthy corneas classes. We also use this dataset to develop multiple deep-learning models based on Convolutional Neural Networks (CNNs) for the automated diagnosis of infectious keratitis. Among these models, Densenet161, had the best performance with accuracy, precision, recall, and F1 score of 93.55%, 92.52%, 94.77%, and 96.93%, respectively. These results demonstrate the potential of deep learning-based models in early and automated diagnosis of AK and FK. We further showed that these models can be used to highlight the areas of infection in the IVCM images and explain the reason behind their diagnosis by utilizing saliency maps as a technique used in eXplainable Artificial Intelligence (XAI) to interpret these models.

许可

MIT

引用

学术使用请引用 DOI 10.6084/m9.figshare.19838083.v2（source: https://figshare.com/articles/dataset/Dataset/19838083）。