Choledocholithiasis Detection on CT

Purpose	To detect choledocholithiasis on CT
Tag(s)
Panel	Abdominal
Define-AI ID	20020009
Originator	Luther B. Adair, II
Lead	Luther B. Adair, II
Panel Chair	Arun Krishnaraj
Panel Reviewers	Abdominal Panel
License	Creative Commons 4.0
Status	Public Comment
RadElement Set	RDES161

                

Clinical Implementation

Value Proposition

Choledocholithiasis is a potentially life-threatening but treatable emergency. AI meeting this use case would help in detecting, quantitating, 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 a CT 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 choledocholithiasis on CT and assess the need for further evaluation with MRCP.

Narrative(s)

A 44-year old patient presents with constant right upper quadrant pain and is taken to the emergency room at which time a CT scan is ordered.

A 67-year old patient presents to an outpatient clinic with jaundice and right upper quadrant pain and is sent to the emergency room, at which time a CT scan is ordered.

Workflow Description

The relevant images are obtained from modality and sent to PACS and the AI engine based on anatomic landmarks. The images are analyzed by the engine. The system then detects the relevant outputs providing associated categorical data and measurements. An alert message is sent to PACS from the engine with the information, identification, and graphics highlighting the common bile duct stone, the measurement of the stone, whether there is biliary ductal dilatation and measurement of the common bile duct, whether there is periductal fluid present, and whether there is gallbladder distention.

An algorithm evaluates the CT scan and categorizes whether a common bile duct stone is present, absent, or undetermined. If present, it then measures the maximal size of the stone; assesses whether biliary ductal dilatation is present, absent, or undetermined with a measurement of the common bile duct; assesses whether periductal fluid is present, absent, or undetermined; assesses whether the gallbladder is distended or not distended with a measurement of the gallbladder lumen from wall to wall. For cases where the algorithm returns a common bile duct stone present, the recommendation for gastroenterology consult, MRCP, or ERCP is made. For cases returned where the algorithm returns a stone absent or undetermined, but there are any secondary output elements present (biliary ductal dilatation, periductal fluid, or a distended gallbladder) an alert is provided to the ordering physician to order an ultrasound. If a radiologist is present, these exams are prioritized in the radiologist worklist for urgent interpretation and reporting.

Considerations for Dataset Development

Procedures	{CT Abdomen, with contrast, without contrast, CT Abdomen and pelvis}
View(s)	{Axial, Coronal, Sagittal}
Age	[0,90]
Sex at Birth	{Male, Female}
Other	{pneumobilia, vicarious excretion, reflux of oral contrast into the biliary tree, soft tissue mass anywhere in the biliary tree, streak artifact from cholecystectomy clips, choldechocal cysts, sclerosing cholangitis, hepaticojejunostomy/Whipple/etc}

Technical Specifications

Inputs

DICOM Study

Primary Outputs

Choledocholithiasis Detection

Gallstone Measurement

Secondary Outputs

Biliary Ductal Dilation Measurement 

Biliary Ductal Dilation Detection

Periductal Fluid Detection

Gallbladder Lumen Distention Measurement

Future Development Ideas

• In the case of biliary ductal dilatation without a radiopaque stone, soft tissue mass obstruction within the common bile duct, ampulla, or pancreas should be considered. 

• In the case of periductal fluid and ductal wall thickening, perhaps cholangitis should be considered.

Related Datasets

The Cancer Imaging Archive (TCIA)

• C4KC-KiTS 

Know of more related datasets? Please let us know