CXR Cardiomegaly Detection

Logo for CXR Cardiomegaly Detection

About

Creators:

User Mugshot ecemsogancioglu 

User Mugshot BramVanGinneken 

Contact email:
ecem.sogancioglu@radboudumc.nl
Image Version:
dc28629c-fef1-4ee8-939a-5b80dce20804
Last updated:
May 7, 2020, 12:45 p.m.
Associated publication:
Sogancioglu E, Murphy K, Calli E, Scholten ET, Schalekamp S, Van Ginneken B. Cardiomegaly Detection on Chest Radiographs: Segmentation Versus Classification. IEEE Access. 2020;8:94631-94642.

Interfaces

This algorithm implements all of the following input-output combinations:

Inputs Outputs
1
    Generic Medical Image
    Generic Overlay
    Results JSON File

Model Facts

Summary

The algorithm detects cardiomegaly and computes the cardiothoracic ratio on chest radiographs through the segmentation of the heart and lungs.

Mechanism

Input

The input should be a frontal chest radiograph. The following file formats are supported: .mha, .mhd, .png, .dcm, .jpeg. The algorithm has been trained with posterior-anterior images (regular frontal chest x-rays, not bed-side images).

Publication

This algorithm is described in IEEE Access.

Contact Information

Questions related to this algorithm can be addressed to Ecem Sogancioglu.

Validation and Performance

Uses and Directions

This algorithm was developed for research purposes only.

Warnings

Common Error Messages

Information on this algorithm has been provided by the Algorithm Editors, following the Model Facts labels guidelines from Sendak, M.P., Gao, M., Brajer, N. et al. Presenting machine learning model information to clinical end users with model facts labels. npj Digit. Med. 3, 41 (2020). 10.1038/s41746-020-0253-3