# COVID-19 CT Images Segmentation — Data

来源：https://www.kaggle.com/competitions/covid-segmentation/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The data was kindly provided by [medicalsegmentation.com](http://medicalsegmentation.com/covid19/). They are two radiologists from Oslo, who've done plenty of work scraping and segmenting CT images. Also, they have made a [great product](https://www.medseg.ai/), where you can segment CT images in a browser. The magic of their tool is that it has several pretrained Unets that run in offline mode (no user data is going out) and make your work a hundred times faster.
An additional contribution of lung masks was made by Johannes Hofmanninger. His approach on [Github](https://github.com/JoHof/lungmask).

## Dataset consists of two parts:

### Medseg part
This is a dataset of 100 axial CT images from >40 patients with COVID-19 that were converted from openly accessible JPG images found [HERE](https://www.sirm.org/en/). The conversion process is described in detail in the following blogpost: [Covid-19 radiology — data collection and preparation for Artificial Intelligence](https://medium.com/@hbjenssen/covid-19-radiology-data-collection-and-preparation-for-artificial-intelligence-4ecece97bb5b)

**images_medseg.npy**  - training images – 100 slices 512x512 size<br>
**masks_medseg.npy** - training masks – 100 masks with 4 channels: (0 - "ground glass", 1 - "consolidations", 2 - "lungs other", 3 - "background" )<br>
**test_images_medseg.npy** - test images – 10 slices  512x512 size

### Radiopedia part
Segmented 9 axial volumetric CTs from [Radiopaedia](https://radiopaedia.org/articles/covid-19-3).  This dataset includes whole volumes and includes, therefore, both positive and negative slices (373 out of the total of 829 slices have been evaluated by a radiologist as positive and segmented). These volumes are converted and normalized in a similar way as above.

**images_radiopedia.npy** - training images – 829 slices 512x512 size<br>
**masks_radiopedia.npy** - training masks – 829 masks with 4 channels: (0 - "ground glass", 1 - "consolidations", 2 - "lungs other", 3 - "background" )

## Predictions
Participants should predict 10 masks corresponding to test_images_medseg.npy with two classes: 0 - "ground glass", 1 - "consolidations".

## Use of other datasets:
Participants can use any data available if they share it with others via posting a link in Discussion<br>
For example, a good source of labeled COVID-19 CT data is available here: [https://mosmed.ai](https://mosmed.ai)