SIIM-ACR Pneumothorax Segmentation 2019

Introduction #

Released 2019-01-25 ·Anna Zawacki, Carol Wu, George Shihet al.

SIIM-ACR Pneumothorax Segmentation 2019 is a dataset for SIIM-ACR Pneumothorax Segmentation Challenge. It is a critical competition focused on detecting pneumothorax in chest radiographic images. Pneumothorax, the accumulation of air between the lung and chest wall, can be life-threatening. This challenge aims to develop AI algorithms that classify and segment pneumothorax. Organized by the Society for Imaging Informatics in Medicine (SIIM), it seeks to improve early diagnosis using chest X-rays.

Pneumothorax, a condition where air accumulates in the space between the lung and chest wall, can be caused by various factors, including injuries, underlying lung diseases, or even seemingly inexplicable events. In some cases, it can pose life-threatening risks.

This challenge aims to harness the power of artificial intelligence to aid in the early and accurate diagnosis of pneumothorax, which is typically confirmed by radiologists through chest X-rays. Detecting pneumothorax can be challenging, and an effective AI algorithm could have widespread clinical applications. It could help prioritize the interpretation of chest radiographs, provide more confident diagnoses, and potentially save lives.

Authors are striving to achieve two primary objectives: firstly, to forecast the presence of pneumothorax within test images, and secondly, to delineate both the precise location and the extent of this medical condition through the use of masks.

Expand

Homepage

Summary #

SIIM-ACR Pneumothorax Segmentation 2019 is a dataset for semantic segmentation and classification tasks. It is used in the medical industry.

The dataset consists of 12047 images with 2669 labeled objects belonging to 1 single class (pneumothorax).

Images in the SIIM-ACR Pneumothorax Segmentation 2019 dataset have pixel-level semantic segmentation annotations. There are 9378 (78% of the total) unlabeled images (i.e. without annotations). There are 2 splits in the dataset: train (10675 images) and test (1372 images). Alternatively, the dataset could be split into 2 classification image sets: pneumo_negative (9378 images) and pneumo_positive (2669 images). Also, the dataset contains image id and pneumo_positive, pneumo_negative tags. The dataset was released in 2019 by the The Society for Imaging Informatics in Medicine (SIIM).

Explore #

SIIM-ACR Pneumothorax Segmentation 2019 dataset has 12047 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.

Sample annotation mask from SIIM-ACR Pneumothorax Segmentation 2019

Sample image from SIIM-ACR Pneumothorax Segmentation 2019

👀

Have a look at 12047 images

Because of dataset's license preview is limited to 12 images

View images along with annotations and tags, search and filter by various parameters

Class balance #

There are 1 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.

Rows 1-1 of 1

Class ㅤ	Images ㅤ	Objects ㅤ	Count on image average	Area on image average
pneumothorax➔ mask	2669	2669	1	1.37%

Images #

Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.

Object distribution #

Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.

Class sizes #

The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.

Rows 1-1 of 1

Class	Object count	Avg area	Max area	Min area	Min height	Min height	Max height	Max height	Avg height	Avg height	Min width	Min width	Max width	Max width
pneumothorax mask	2669	1.37%	15.39%	0.01%	5px	0.49%	987px	96.39%	268px	26.17%	10px	0.98%	861px	84.08%

Spatial Heatmap #

The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.

Objects #

Table contains all 2669 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.

Rows 1-10 of 2669

Object ID ㅤ	Class ㅤ	Image name click row to open	Image size height x width	Height ㅤ	Height ㅤ	Width ㅤ	Width ㅤ	Area ㅤ
1➔	pneumothorax mask	274_train_1_.png	1024 x 1024	541px	52.83%	307px	29.98%	0.86%
2➔	pneumothorax mask	2478_train_1_.png	1024 x 1024	635px	62.01%	310px	30.27%	1.7%
3➔	pneumothorax mask	1360_train_1_.png	1024 x 1024	308px	30.08%	189px	18.46%	0.72%
4➔	pneumothorax mask	149_train_1_.png	1024 x 1024	107px	10.45%	129px	12.6%	0.62%
5➔	pneumothorax mask	8_train_1_.png	1024 x 1024	104px	10.16%	181px	17.68%	0.5%
6➔	pneumothorax mask	30_train_1_.png	1024 x 1024	105px	10.25%	215px	21%	1.54%
7➔	pneumothorax mask	2196_train_1_.png	1024 x 1024	552px	53.91%	317px	30.96%	2.59%
8➔	pneumothorax mask	7890_train_1_.png	1024 x 1024	108px	10.55%	147px	14.36%	0.18%
9➔	pneumothorax mask	8504_train_1_.png	1024 x 1024	95px	9.28%	98px	9.57%	0.34%
10➔	pneumothorax mask	168_train_1_.png	1024 x 1024	195px	19.04%	176px	17.19%	1.14%

License #

COMPETITION DATA.

“Competition Data” means the data or datasets available from or referenced by the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on or referenced by the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants.

A. Data Access and Use. Participant may access and use the Competition Data for any purpose, whether commercial or non-commercial, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.

B. Data Security. Participant agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. Participant agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. Participant agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.

C. External Data. Participant may use data other than the Competition Data (“External Data”) to develop and test your models and Submissions. However, participant will ensure the External Data is available to use by all participants of the competition for purposes of the competition at no cost to the other participants and post such access to the External Data for the participants to the official competition forum prior to the Entry Deadline.

Source

Citation #

If you make use of the SIIM-ACR Pneumothorax Segmentation 2019 data, please cite the following reference:

@dataset{SIIM-ACR Pneumothorax Segmentation 2019,
  author={Anna Zawacki and Carol Wu and George Shih and Julia Elliott and Mikhail Fomitchev and Mohannad Hussain and Paras Lakhani and Phil Culliton and Shunxing Bao},
  title={SIIM-ACR Pneumothorax Segmentation 2019},
  year={2019},
  url={https://www.kaggle.com/competitions/siim-acr-pneumothorax-segmentation/}
}

Source

If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:

@misc{ visualization-tools-for-siim-acr-pneumothorax-segmentation-dataset,
  title = { Visualization Tools for SIIM-ACR Pneumothorax Segmentation 2019 Dataset },
  type = { Computer Vision Tools },
  author = { Dataset Ninja },
  howpublished = { \url{ https://datasetninja.com/siim-acr-pneumothorax-segmentation } },
  url = { https://datasetninja.com/siim-acr-pneumothorax-segmentation },
  journal = { Dataset Ninja },
  publisher = { Dataset Ninja },
  year = { 2024 },
  month = { nov },
  note = { visited on 2024-11-21 },
}

Download #

Please visit dataset homepage to download the data.

. . .

Disclaimer #

Our gal from the legal dep told us we need to post this:

Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.

You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.