Cholecystitis on US


Purpose

Detection of cholecystitis on ultrasound

Tag(s)


Panel

Abdominal

Define-AI ID

19020004

Originator

Luther B. Adair, II, MD

Lead

Luther B. Adair, II, MD

Panel Chair

Arun Krishnaraj, MD

Panel Reviewers

Abdominal Panel

License

Creative Commons 4.0

Status

Public Comment


Clinical Implementation


Value Proposition

Cholecystitis is a potentially life-threatening emergency, particularly if the gallbladder is perforated. AI meeting this use case would help in detecting 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 non-radiologists such as technologists who would perform an ultrasound for this disease entity. 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 detect cholecystitis on ultrasound and assess the need for further evaluation or intervention.


Narrative(s)

A 40-year old patient presents with constant right upper quadrant pain and is taken to the emergency room at which time ultrasound of the right upper quadrant abdomen is performed.
A 67-year old patient in the ICU with a history of diabetes presents with fever, but is intubated and is a poor candidate for an ultrasound. He is taken to the radiology department and an ultrasound of the right upper quadrant abdomen is performed.

Workflow Description

An algorithm evaluates the ultrasound and categorizes whether cholecystitis is present, equivocal, or complicated. If present, it then assesses whether a gallstone is present, absent, or undetermined; assesses whether pericholecystic fluid is present, absent, or undetermined; assesses whether the gallbladder wall is thickened or not thickened with a measurement; assesses whether there is a Sonographic Murphy’s sign which would require input from the technologist. For cases returned where the algorithm returns cholecystitis, the radiologist is made aware of the need for further evaluation or intervention. If the radiologist is not available, the non-radiologist is made aware of the need for further evaluation or intervention.

Considerations for Dataset Development


Procedure(s): {Ultrasound limited; Ultrasound of the abdomen complete, Ultrasound of the right upper quadrant}

View(s): {transverse, long}
Clinical Note: Subtle gallbladder wall thickening can be overlooked

Sex at Birth: {Male, Female}

Age: [0,90]

Abdominal pain: {right upper quadrant pain}

Comorbidities: {female, over 40 years of age, diabetes, sickle cell anemia, obesity}

Cholecystostomy Tube: { percutaneous drainage tube}

Other: {adenomyomatosis, cholesterol crystals, gallbladder carcinoma}

Technical Specifications


Inputs

DICOM Study

Procedure

ultrasound limited, abdominal ultrasound complete, right upper quadrant ultrasound

Views


Data Type

DICOM

Modality

Ultrasound

Body Region

Abdomen

Anatomic Focus

Gallbladder

Pharmaceutical


Scenario




Primary Outputs

Cholecystitis Detection

RadElement ID


Definition

Presence of cholecystitis

Data Type

Categorical

Value Set

0-no evidence of cholecystitis

1- acute cholecystitis

2- equivocal

3- complicated

Units





Gallstone Detection

RadElement ID


Definition

Detect if there is a Gallstone

Data Type

Categorical

Value Set

0-absent

1-present

2-undetermined

Units



Secondary Outputs


Sconographic Murphy’s sign detection

RadElement ID


Definition

Detect if Sonographic Murphy’s sign is present.

Data Type

Categorical

Value Set

0-absent

1-present

2-undetermined

Units



Gallbladder wall thickness measurement

RadElement ID


Definition

Gallbladder wall thickness

Data Type

Measurement

Value Set


Units

millimeters


Pericholecystic fluid detection

RadElement ID


Definition

Detect if pericholecystic fluid is present.

Data Type

Categorical

Value Set

0-absent

1-present

2-undetermined

Units


Future Development Ideas


  • Consider corroborating CT and ultrasound data

  • Considering providing a scale of certainty based on findings that coincide with existing data to suggest a spectrum of specificity (i.e. presence of gallstones and sonographic Murphy’s sign are the most specific findings in cholecystitis).