Olympus reports stronger colorectal lesion detection with Artificial Intelligence endoscopy

Olympus has published results from the EAGLE trial showing that its cloud-based CADDIE detection system improved colorectal lesion detection during colonoscopy. The study adds peer-reviewed evidence for real-time Artificial Intelligence support in endoscopy while maintaining workflow efficiency and safety.

Olympus has published results from the EAGLE Trial in npj Digital Medicine, presenting new evidence for its cloud-based CADDIE Computer-Aided Detection system in colorectal screening. The multicenter randomized controlled study evaluated whether real-time Artificial Intelligence support can help clinicians detect lesions linked to cancer prevention while maintaining clinical workflow efficiency and safety. The findings emphasize improved identification of lesion types that are often harder to spot, including large adenomas and sessile serrated lesions.

The EAGLE Trial was conducted across eight centers in four European countries, with a primary analysis involving 841 patients and 22 endoscopists performing screening and surveillance colonoscopies. Patients were randomized to undergo either standard colonoscopy or CADDIE-assisted colonoscopy. The results revealed a 7.3 % absolute increase in adenoma detection rate (ADR) when clinicians used the Artificial Intelligence solution, with marked improvements in the detection of clinically significant lesion subtypes: a 93 % relative increase in large (>10 mm) adenomas, 57 % in non-polyploid adenomas and 230 % in sessile serrated lesions (SSLs).

CADDIE is a cloud-based CADe application that operates in real time, providing clinicians with Artificial Intelligence-generated alerts during procedures to indicate potential polyps. It is the first product launched under Olympus’s OLYSENSE Intelligent Endoscopy Ecosystem, and it holds both FDA clearance and CE Mark certification. Olympus said the system’s cloud architecture reduces dependence on on-premises hardware, which can lower adoption barriers for healthcare facilities of varying sizes and support more frequent model updates based on new clinical data.

Investigators involved in the trial described the results as clinically significant because better detection of high-risk lesions may help reduce post-colonoscopy colorectal cancer rates. The publication adds to the case for evidence-based use of Artificial Intelligence in clinical practice and supports Olympus’s broader push to combine endoscopy technology with tools aimed at improving diagnostic accuracy, efficiency and patient care.

58

Impact Score

NVIDIA details DLSS 5 image quality goals

NVIDIA says DLSS 5 is designed to deliver real-time neural rendering while preserving the visual direction developers intended for each frame. The technology combines lighting, material, and temporal improvements to keep enhanced images consistent with game content.

European Union moves to streamline and tighten Artificial Intelligence rules

The European Union is advancing parallel efforts to simplify parts of its Artificial Intelligence rulebook while moving toward tougher restrictions on tools used to create non-consensual sexual content. The latest steps combine broader regulatory streamlining with targeted action against harmful image and audio generation systems.

Y Combinator machine learning startups in 2026

Y Combinator’s 2026 machine learning directory highlights a broad mix of startups spanning infrastructure, robotics, healthcare, developer tools, data systems, and enterprise software. The list shows how deeply Artificial Intelligence and machine learning are being applied across industrial, scientific, and business workflows.

Artificial Intelligence platform choice becomes a board decision

Competition among leading Artificial Intelligence providers is shifting from model benchmarks to control of broader platforms and ecosystems. That change turns large language model selection into a long term strategic decision for boards, not just engineering teams.

Memory makers see shortages easing in late 2028

Memory manufacturers expect shortages to continue until the end of 2028, with supply and demand returning to balance afterward. Producers are also reassessing whether to extend capacity expansion beyond plans already tied to current demand.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.