Google+ Facebook Twitter Twitter

"No improvements for colonoscopies with AI"

A randomised controlled trial found that colonoscopy assisted by computer-aided detection (CAD) was not associated with improved detection of advanced colorectal neoplasias.

More than 3000 persons with a positive faecal immunochemical test (FIT) were randomly assigned to colonoscopy with or without CAD to evaluate the contribution of CAD to colonoscopic detection of advanced colorectal neoplasias, adenomas, serrated polyps, and non-polypoid and right-sided lesions.

The researchers found no significant difference in advanced colorectal neoplasia detection rate or the mean number of advanced colorectal neoplasias detected per colonoscopy between the two groups.

These findings suggest the need for additional research and more defined detection parameters in CAD.

Image credit | Science-Photo-Library

Related Articles

student studying-CREDIT-shutterstock-717727117

Celebrating IBMS exam success

It is time to celebrate the success of more IBMS members in the Diploma of Expert Practice (DEP) or Advanced Specialist Diploma (ASD) in Histological Dissection and the DEP in Immunocytochemistry exams.


Advanced and consultant practice roles

Sarah May and Chris Ward from the IBMS look at advanced and consultant roles and discuss new developments and qualifications.

Robotic hand with handgun aiming in wrong direction. Fatal AI error - Image credit - Shutterstock-2309476357

Tissue contamination distracts AI

In a new study, scientists trained three AI models to scan microscope slides of placenta tissue to detect blood vessel damage, estimate gestational age and classify macroscopic lesions.

Digital pathology cleared for use-history digital pathology-CREDIT-university of warwick

Digital pathology cleared for use

New research has led to the UK government approving the use of digital pathology to help speed up analysis of cancer screening samples.