Identifying Small Bowel Obstruction on Fluoroscopy

Purpose

Detect small bowel obstruction on fluoroscopy

Tag(s)

 

Panel

Abdominal                        

Define-AI ID

20020015                        

Originator

Zerwa Farooq, Luther Adair II

Panel Chair

Luther Adair II                         

Panel Reviewers

Luther Adair II, Andrew Smith, Scott Potenta

License

Creative Commons 4.0

Status Published
RadElement Set RDES181 

 

Clinical Implementation


Value Proposition

Small bowel obstruction is a common surgical condition accounting for up to 20% of surgical admissions. Evaluation of the presence, severity, cause and complications of small bowel obstruction on cross sectional imaging provides the basis of surgical or conservative management strategies.  In certain cases, when oral contrast does not reach the terminal ileum or was not provided during a CT scan, it is not possible to distinguish a complete from a partial small bowel obstruction or ileus.  This is especially important in a postsurgical patient with a history of recurrent small bowel obstructions.  Additionally, a radiologist often has to disrupt their workflow by assessing the fluoroscopy examination using barium-based or gastrografin contrast material and, in some instances, performing it.  An algorithm evaluating the above mentioned characteristics on fluoroscopy scan and follow up radiographs can expedite management and aid radiologists and technologists in accurately and quickly classifying small bowel obstruction cases by fluoroscopy. 


Narrative(s)

A 49-year-old man presenting with a past surgical history of small bowel obstruction presented with a 2- day history of nausea, vomiting and constipation. Nausea and vomiting have worsened over the past two days. An algorithm evaluates the small bowel follow through images and informs the radiologist and ordering provider regarding the presence or absence of contrast material reaching the colon in order to determine whether this is a recurrent complete small bowel obstruction.


Workflow Description

Images are obtained from the fluoroscopy examination and follow up radiographs that are then sent to PACS and the AI engine. The images are then analyzed by the AI engine and an alert is sent to PACS with the classification information.


Considerations for Dataset Development




Procedure

Small bowel follow through with barium-based or gastrografin contrast material.

Sex at birth

Male, female

Age

0-90

Presence of SBO

Dilated loops of small bowel containing contrast that does not reach the colon in 24 hours.

Degree of

obstruction

Complete obstruction vs partial obstruction (delayed transit of contrast) vs ileus

Transition point

High or low transition point

Cause of

obstruction

Bowel wall/mucosal edema, stricture, mass, adhesions

Variables

Cholecystectomy clips, NG tube, metallic vascular stent, biliary stent, spinal hardware, embolization coils

Technical Specifications



Inputs


DICOM Study

Procedure

Small bowel follow through using barium-based or gastrografin contrast material

Views


Data Type

DICOM

Modality

Fluoroscopy, radiography

Body Region

Abdomen Pelvis

Anatomic Focus

Small bowel


Primary Outputs


Small bowel obstruction

RadElement ID

RDE1253

Definition

Small bowel obstruction

Data Type

Categorical

Value Set

  • SBO absent

  • SBO present

  • Ileus

  • LBO with proximal dilatation of small bowel

  • Undetermined

Units

N/A





 Secondary Outputs



Severity of obstruction

RadElement ID

RDE1254

Definition

Severity of obstruction

Data Type

Categorical

Value Set

  • Complete obstruction

  • Partial obstruction

  • Undetermined

Units

N/A


Small bowel diameter

RadElement ID

RDE1255

Definition

Maximum small bowel diameter

Data Type

Numeric

Value Set

0-100

Units

mm


Location of obstruction

RadElement ID

RDE1256

Definition

Transition point

Data Type

Categorical

Value Set

  • High

  • Low

  • Undetermined

Units

N/A


Status of exam

RadElement ID

RDE1257

Definition

Exam complete or further follow up radiographs required

Data Type

Categorical

Value Set

  • Exam complete - contrast reached large bowel

  • Exam complete - 24 hr follow up obtained

  • Exam incomplete - contrast has not reached large bowel and 24 hr follow not obtained

  • Undetermined

Units

N/A

Future Development Ideas


The algorithm can compare studies with prior established SBO and appropriately assess resolution or worsening of obstruction e.g. interim resolution or worsening of bowel dilation.