Pneumothorax

Purpose

Detection and quantification of pneumothorax on chest radiograph

Tag(s)

 

Panel

Thoracic 

TOUCH-AI ID

 TAI-08180001

Originator

Thoracic Panel 

Panel Chair

Eric J. Stern 

Panel Reviewers

Thoracic Panel 

License

Creative Commons 4.0 

Status Public Commenting 
                               

Clinical Implementation


Value Proposition

Pneumothorax is a potentially life-threatening but readily treated emergency. AI meeting this use case would help in detecting, quantitating, comparing, and alerting both nonspecialists and radiologists to this potentially life-threatening abnormality. In clinical settings where a radiologist is not readily available, such detection would be of value to nonradiologists. In clinical settings where radiologists are available, such detection could be used to alert the radiologist and prioritize its reporting and notification to the treating physicians. One possible extension to this use case is to track changes in size of previously detected pneumothoraces and those under treatment.

Narrative(s)

A 25-year-old patient presents after a motor vehicle accident, and a chest x-ray (CXR) is taken in the emergency room. An algorithm evaluates the image and categorizes the chest as pneumothorax present, absent, or undetermined. For cases when the algorithm returns pneumothorax present, if a radiologist is not present at the time of imaging, an alert is provided to the ordering physician. If a radiologist is present, the exam is prioritized in the radiologist worklist for urgent interpretation and reporting. Cases of potential pneumothorax without a chest tube should take higher priority in the reading queue compared with cases with a chest tube. Tension-pneumothorax cases also should be highly prioritized for reading.

A 70-year-old patient admitted to the ICU has several physiologic and monitoring interventions that have a risk of pneumothorax as a complication. An algorithm evaluates the image and categorizes the chest as being normal, abnormal, or undetermined. For cases when the algorithm returns pneumothorax present, if a radiologist is not present at the time of imaging, an alert is provided to the ordering physician. If a radiologist is present, the exam is prioritized in the radiologist worklist for urgent interpretation and reporting (particularly for new or enlarging pneumothorax or for possible tension).

Workflow Description

The image is obtained from modality and sent to PACS and the AI engine. The image is analyzed by the engine. The system then detects and estimates pneumothorax size. An alert message is sent to PACS from the engine with the information, identification, and graphic highlighting the pneumothorax.

Considerations for Dataset Development


Procedures(s): {XRAY, Chest; CT, Chest}

View(s): {AP, PA/Lat, inclination e.g., upright, semi-upright, supine}

Clinical Note: Subtle cases of PTX on supine CXRs manifested by “deep sulcus sign” can be overlooked by less experienced radiologists

 

Sex at Birth: {Male, Female}

 

Age: [0,90]

 

Chest Trauma (or intervention): {blunt injury, blast injury, chest wall injury, rib fracture, lung contusions, lacerations, pleural fluid}

 

Comorbidities: {pleural fluid (including air/fluid levels), lung disease (e.g., Pneumonia/lung abscess, bullous emphysema, bronchiectasis), pneumomediastinum, other extrapleural air collections}

 

Lung Tissue Involvement: {Complete Collapse, Partial collapse}

 

Chest Tube: {With one or more chest tubes/drainage catheters, interval placement, or former tubes}

 

Tension Pneumothorax: {Tension pneumothorax (flattening of ipsilateral hemi-diaphragm or contralateral shift of the mediastinum)}

 

Other: {Skin fold artifacts, Pleural fluid}

Clinical Note: Skin fold artifacts are the most common cause of a false positive diagnosis of PTX

Technical Specifications


Inputs

DICOM Study

Procedure

XRAY, Chest

Views

AP, PA/Lat, inclination e.g., upright, semi-upright, supine

Data Type

DICOM

Modality

XRAY

Body Region

Chest

Anatomic Focus

Lung

 

Primary Outputs

Pneumothorax Detection

RadElement ID

RDE250

Definition

Detection of pneumothorax

Data Type

Categorical

Value Set

0–Unknown

1–Pneumothorax present

2–Pneumothorax absent

Units

N/A

Secondary Outputs

Pleural Separation

RadElement ID

RDE251

Definition

Measure pleural separation in mm

Data Type

Numerical

Value Set

 

Units

mm

Max Length

N/A

 

Pneumothorax Side

RadElement ID

RDE252

Definition

Defines the side of pneumothorax when present

Data Type

Categorical

Value Set

0-Right Side Pneumothorax

1-Left Side Pneumothorax

2-Bilateral

Units

N/A

 

Pneumothorax Size

RadElement ID

RDE253

Definition

Classify the size of pneumothorax (or pneumothoraces) as a function of interpleural distance. Launch if pneumothorax is detected.

Data Type

Categorical

Value Set

0–Small pneumothorax

1–Moderate pneumothorax

2–Large pneumothorax

Units

N/A

 

Chest Tube

RadElement ID

RDE254

Definition

Detect the presence of chest tube(s)

Data Type

Categorical

Value Set

0–Unknown

1–Tube(s) present

2–Tube(s) absent

Units

N/A

Future Development Ideas


The algorithm compares prior imaging and returns differences in output elements (pneumothorax detection, pleural separation, and pneumothorax size). By further extension, the algorithm may return percent of total volume of hemithorax or volume of pleural fluid.

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.