Complex medical image dataset

Citation Author(s):
Yonghuang
Wu
Submitted by:
Jinhua Yu
Last updated:
Mon, 07/08/2024 - 15:58
DOI:
10.21227/v7t3-1r11
Data Format:
License:
32 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

 

The dataset comprises intricate medical imaging data, encompassing CT images and annotated processed files (.npy or .mat) of both cerebral vasculature and trachea. Within the subfolder "Cerebrovascular dataset," the images are stored in the "images" folder while the corresponding annotations reside in the "masks" folder. Additionally, the unlabeled data is stored in the "images_unlabeled" folder. We have provided a limited set of 150 annotated samples and 100 unlabeled samples. As for the subfolder "Airway dataset," it contains two folders. The "ImagesAndMasks" folder houses 100 mat files, each containing image arrays and annotations with dimensions of 320*192*32. In the "Images_unlabeled" folder, we have stored 60 unlabeled data samples, with each mat file containing only image arrays. We intend to release the complete dataset once we have obtained the necessary data permissions.

 

Instructions: 

In the Markdown file, we have provided the construction methods and reading procedures for the two datasets. Firstly, the dataset construction can be achieved by following *step 1* outlined in the file. Subsequently, the data can be read using *step 2* as described.

Funding Agency: 
National Natural Science Foundation
Grant Number: 
91959127