Development and Validation of a CT-based Diagnostic Models Using Artificial Intelligence for Detection of Small Bowel Obstruction

Active, not recruiting

• Conditions: Small Bowel Obstruction

• Registration Number: NCT05566158
• Lead Sponsor: Fondation Hôpital Saint-Joseph

Brief Summary

Small bowel obstruction (SBO) is a common non-traumatic surgical emergency. All guidelines recommend computed tomography (CT) as the first-line imaging test for patients with suspected SBO. The objectives of CT are multiple: (i) to confirm or refute the diagnosis of GI obstruction, defined as distension of the digestive tracts greater than 25 mm, and, when SBO is present, (ii) to confirm the mechanism (mechanical vs. functional), (iii) to localize the site of obstruction, i.e., the transition zone (TZ), (iv) to identify the cause, and (v) to look for complications such as strangulation or perforation, influencing management.

Given the exponential increase in the number of scans being performed, especially in the setting of emergency management, methods to assist the radiologist would be useful to:

1. Sort the scans performed, allowing prioritization of the analysis of scans with a higher probability of pathology (occlusion in our case)

2. Help the radiologist to diagnose occlusion and its type (functional or mechanical), and to identify signs of severity.

3. To help the emergency physician and the digestive surgeon to make a decision on the management of the disease (surgical or medical).

Machine learning has developed rapidly over the last decades, first thanks to the increase in data storage capacities, then thanks to the arrival of parallel processing hardware based on graphic processing units, in the context of radiological diagnostic assistance. Consequently, the number of studies on deep neural networks in medical imaging is increasing rapidly. However, few teams focus on SBO. The only published classification models have been produced for standard abdominal radiographs. No studies have used CT or 3D models, apart from our preliminary study on ZTs, despite the recognized advantages of CT for the diagnosis of SBO and the likely contribution of 3D models, which may be comparable to that of multiplanar reconstruction for the analysis of images in multiple planes of space.

Detailed Description

Not available

Study Timeline

• Study Start: 2022-08-09
• Status Verified: 2022-09
• Primary Completion: 2022-09-09
• Study First Submitted: 2022-09-30
• Study First Submitted QC: 2022-09-30
• Last Update Submitted: 2022-09-30
• Study First Posted: 2022-10-04
• Last Update Posted: 2022-10-04
• Study Completion: 2023-12-31

Recruitment & Eligibility

• Status: ACTIVE_NOT_RECRUITING
• Sex: All
• Target Recruitment: 8000

Inclusion Criteria

• Patient whose age ≥ 18 years
• Patient who has had a CT scan with at least one abdominal-pelvic acquisition performed within the Saint Joseph Hospital Group
• Report containing the terms "occlusion" or "occlusive", "vomiting" or "ileus"
• French-speaking patient

Exclusion Criteria

• Imaging not usable
• Absence of abdomino-pelvic volume on CT acquisitions
• Patient under guardianship or curatorship
• Patient deprived of liberty
• Patient under court protection
• Patient objecting to the use of his data for this research

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Automated detection of digestive occlusions	Year 1	This outcome corresponds to the ability of the model to identify the presence or absence of occlusion: sensitivity, specificity and predictive values.

Secondary Outcome Measures

Name	Time	Method
Analysis via radiomics of junction zones	Year 1	This outcome corresponds to the analysis via radiomics of the junction zones of mechanical digestive occlusions (the junction zones are the zones where the dilation-flat transition is located, thus the zone where the obstruction is located): * Adhesions vs. flanges: new radiological signs?; * Improved performance of surgery prediction.
Automatic differentiation of functional vs. mechanical occlusions	Year 1	This outcome corresponds to the detection of functional vs. mechanical occlusions.
Algorithm for surgical indication	Year 1	This outcome corresponds to the performance of the clinical-radio-biological algorithm for prediction of surgery.
Automated detection of junction areas	Year 1	This outcome corresponds to the performance of automatic detection in identifying the junction zones of mechanical digestive obstructions.

Trial Locations

Locations (2)

Groupe Hospitalier Paris Saint-Joseph; 🇫🇷 Paris, France

Central for Visual Computing - OPIS Inria group; 🇫🇷 Gif-sur-Yvette, France