COVID-19 - CT segmentation dataset

This is a dataset of 100 axial CT images.

Description 

This is a dataset of 100 axial CT images from the Italian Society of Medical and Interventional Radiology’s excellent collection of about 60 patients with Covid-19 that were converted from openly accessible JPG images.

Data type

The database contains 60 cases with example CXRs and single slice CT-images. A simple download from these cases resulted in 110 usable, axial CT-images of confirmed COVID-19 cases.

The images were segmented by a radiologist using 3 labels: ground-glass (mask value =1), consolidation (=2) and pleural effusion (=3). Then they trained a 2d multilabel U-Net model, which you can find and apply in MedSeg. 10 images were left out for validation/testing.

The conversion process is described in detail in the following post: Covid-19 radiology — data collection and preparation for Artificial Intelligence

Publications

Post: https://medium.com/@hbjenssen/covid-19-radiology-data-collection-and-preparation-for-artificial-intelligence-4ecece97bb5b

Sites

Italian Society of Medical and Interventional Radiology’s (https://www.sirm.org/category/senza-categoria/covid-19/)

Dataset size estimation

Platform statistics

Subjects	Sessions	Modalities
110	110	110 CT + 110 segmentations (masks)