Cardiomegaly Detection

Purpose

Detect cardiomegaly on posterioranterior and anteroposterior radiographs

Tag(s)

 #Cardiac Size on Chest Radiograph

Panel

 Cardiac

TOUCH-AI ID

 TAI-04180002

Originator

 Jay Nance

Panel Chair

 Carlo De Cecco

Panel Reviewers

 Cardiac Panel

License

 Creative Commons 4.0

Status  Public Commenting
                               

Clinical Implementation


Value Proposition

The chest radiograph is often the first imaging study that is available. It can be used as a quick initial screening tool for cardiomegaly, which in and of itself can be used as a marker for heart disease. A quick visual assessment by a radiologist is sometimes inaccurate. An AI algorithm can be trained to make an accurate assessment of cardiomegaly based on a single-view chest radiograph (anteroposterior [AP] or posterioranterior [PA]). Additionally, the algorithm can indicate which specific chambers contribute most to the enlarged cardiac silhouette.

Narrative(s)

A 60-year-old male with no prior imaging is admitted to the emergency department for shortness of breath. A chest radiograph is obtained as part of the initial workup. The algorithm evaluates the image and determines whether the patient’s heart is enlarged. The radiologist is informed of this categorization at the time of interpretation. Additionally, the algorithm is able to evaluate for enlargement of the left atrium (or other specific chambers).

Workflow Description

The image obtained from the modality is sent to PACS and the AI engine. The image is analyzed by the engine. If the image is a PA view, a simple cardiothoracic ratio (width of heart/width of thorax) is computed. If the image is an AP view, a “modified” cardiothoracic ratio is computed. The system categorizes the heart as enlarged or normal in size based on whether the cardiothoracic ratio is greater than 0.5. If the heart is enlarged, the angle of the carina is measured by the system. If the angle is greater than 100 degrees, the presence of left atrial enlargement is suggested. A message is sent to PACS from the engine with the information.

Considerations for Dataset Development


Procedures(s): X-ray, Chest

View(s): {AP, PA}

 

Sex at Birth: {Male, Female}

Technical Specifications


Inputs

DICOM Study

Procedure

XRAY, Chest

Views

AP, PA

Data Type

DICOM

Modality

XRAY

Body Region

Chest

Anatomic Focus

Heart

 

Primary Outputs

Cardiomegaly Detection

RadElement ID

RDE203 

Definition

Presence of cardiomegaly. If cardiothoracic ratio is greater than 0.5, then suggest cardiomegaly.

Data Type

Categorical

Value Set

0-Unknown

1-Cardiomegaly Present

2-Cardiomegaly Absent

Units

N/A

Public Commenting


Use cases are meant to be a primary vehicle for distributing clinical information to the developer community. They pinpoint precise scenarios within radiology workflows where potential automation could add noticeable value and establish standards for interpreting and passing corresponding common data elements. Implementing effective standards requires the perspective from all stakeholders. So to that end, we encourage your feedback on use cases.

To submit comments, please email DSIUseCases@acr.org with the use case title(s) and relevant comments by January 1, 2019. If more convenient, you may also download this use case and comment directly on the PDF. Just attach the PDF copy on the email.