Month: October 2025

WCRI 2026: The World Conference on Research Integrity in Vancouver

Posted on by Kim

About WCRI

The World Conference on Research Integrity (WCRI) is one of the leading global forums for advancing responsible research. It unites scientists, publishers, institutions, and policymakers who work to strengthen trust, ethics, and accountability in science. WCRI Conference 2026 will focus on three major themes: Artificial Intelligence, Research Security, and Indigenous Knowledge Systems.

WCRI 2026 Themes

Each edition of the World Conference on Research Integrity focuses on key issues that shape how science evolves. The 2026 conference highlights the following:

Artificial Intelligence and Integrity in Scientific Research

AI now plays a central role in how research is created, verified, and shared. It can expose image or data manipulation that might otherwise go unnoticed, exactly what drives Imagetwin’s mission. At the same time, AI also introduces new risks: fabricated results, biased outputs, and unethical use of generative tools. The conference will explore both sides of this shift – how to use AI responsibly while keeping human judgment and transparency at the heart of science.

Research Security and Openness

Modern research depends on collaboration, but it also faces growing security challenges. Governments and institutions must protect sensitive data, intellectual property, and national interests without limiting the open exchange that fuels discovery. WCRI 2026 will focus on this balance: how to keep science transparent and trustworthy while addressing issues such as restricted partnerships, data access, and foreign influence.

Indigenous Knowledge and Ethical Research

This theme highlights the importance of Indigenous perspectives in global research ethics. It calls for genuine engagement with Indigenous ways of knowing and for a deeper respect for community-based research practices. By bringing these voices into the conversation, WCRI 2026 broadens what integrity means: compliance with global standards, cultural awareness, respect, and shared responsibility in how knowledge is created.

Imagetwin at WCRI 2026

Imagetwin will exhibit at the 9th World Conference on Research Integrity in Vancouver, Canada. WCRI’s mission aligns closely with ours: to promote transparency, accountability, and trust in scientific research.

Our AI-driven technology helps researchers, publishers, and institutions detect image duplication, plagiarism, manipulation, and AI-image fabrication before publication. We help protect research credibility and uphold the ethical standards that WCRI stands for by making image verification fast and reliable

We look forward to joining this global conversation on responsible and ethical research, since it will give our team a chance to connect with integrity leaders, exchange insights, and explore how technology can preserve trust in science. 

Visit us at our booth at WCRI 2026 to discuss potential collaborations to support research integrity worldwide.

WCRI Sign Up & Schedule

The 9th World Conference on Research Integrity (WCRI 2026) will take place from May 3–6, 2026, at The Westin Bayshore Hotel in Vancouver, British Columbia, Canada. It is open to researchers, institutions, and policymakers worldwide. 

For more information, visit the official WCRI Canada website for updates on registration, travel, and the full schedule.

About Imagetwin

Imagetwin uses artificial intelligence to verify the integrity of scientific images. Our platform helps publishers, universities, institutions, researchers detect image integrity issues, prevent fraud, and protect scientific credibility at scale. With a mission to make research more transparent and trustworthy, Imagetwin partners with the global scientific community to ensure that published findings reflect genuine, reproducible work. 

If you’d like to learn how Imagetwin supports research integrity or explore potential collaboration, reach out to our team.

Frequently asked questions

Imagetwin includes automated AI-generated image detection as part of its standard screening. When a manuscript is submitted through an integrated platform such as ScholarOne, Wiley’s Research Exchange, or Editorial Manager, Imagetwin flags figures that show signs of AI fabrication alongside checks for duplication, manipulation, and plagiarism. As generative AI tools become more accessible, this type of automated detection at submission is increasingly essential for maintaining the credibility of published research.

Imagetwin analyzes images for manipulation automatically, covering splice detection, copy-paste forgeries, and cross-publication reuse. For Western blots specifically, it produces a color-coded overlay highlighting suspicious regions, with a false positive rate of 1.7%. For manual review, signals to watch for include images that look suspiciously similar in texture or lighting, low-resolution JPEGs where originals should be high quality, and labels or text obscuring image corners. Automated screening with Imagetwin catches what manual review misses, particularly at scale.

The most frequently detected issues are Western blot splicing (vertical or horizontal cuts that combine bands from different experiments), copy-paste duplication within or across figures, microscopy images reused across multiple papers or disease models, and figures taken from unrelated publications and relabeled. AI-generated figures are an emerging category. In a Radboud university medical center investigation of 608 pre-clinical stroke research papers, approximately 40% of articles contained image-related concerns, predominantly duplicated Western blot panels.

Next Level Western Blot Duplicate Detection

Posted on by Kim

Western Blots are among the most difficult scientific images to analyse for duplication. They often lack distinctive texture or structure, and many look strikingly similar to one another, which can result in a high false positive rate. Our current detection system performs well, but feedback from researchers and editors showed us that some especially challenging cases were slipping through.

Over the past months, our team has been building a stronger system designed specifically to handle these edge cases, and the results are a major step forward.

How We Improved Western Blot Detection

To improve detection, we analysed thousands of Western Blot duplicates identified on PubPeer. These real-world cases helped us understand recurring patterns and highlighted situations where conventional algorithms struggled.

From this foundation, we worked closely with research integrity experts to assemble a large, curated dataset of Western Blot duplicates. This became the basis for training a new machine learning model, purpose-built for this image type.

Key advances in the new system include:

  • Specialised training corpus
    Thousands of confirmed duplicates curated with expert input
  • Next-generation detection model
    Optimised to capture subtle similarities that generic approaches miss
  • Robustness to transformations
    Tested against common transformations such as rotation, scaling, contrast or colour shifts, quality loss, and flipping. These are all areas where the new model shows far stronger performance

What This Means for Users

With this release, duplicate detection between Western blot images has become substantially more accurate, achieving 90% accuracy on 443 verified duplicates collected from PubPeer. Many of the most challenging cases that previously went undetected are now flagged correctly. This reduces the risk of false negatives while giving researchers, editors, and institutions greater confidence in their results.

To demonstrate the impact of this upgrade, we tested the new model against some of the most difficult Western Blot cases shared by researchers and editors, some examples below: 

This means researchers, editors, and institutions can work with greater confidence that duplications will be caught, even in the toughest cases.

Looking Ahead

What we developed is not just a model for Western Blots. We have created a new duplicate detection technology that can be adapted to other use cases. Next, we will extend from duplicate detection between Western Blot images to duplicate detection within single Western Blot subimages. Then, over the coming months, we will roll out the new technology to flow cytometry images, microscopy images, and graphs, strengthening duplicate detection across an even broader range of figures.

By listening to feedback and analyzing real-world cases, we are building ever-stronger tools to support the research community. Western Blot detection is just the latest step in this process, and more improvements are already on the way.

Frequently asked questions

Imagetwin’s manipulation detection model identifies vertical splices, horizontal splices, and copy-paste forgeries in Western blot images. Suspicious regions are highlighted in a color-coded overlay directly in the interface, with brighter areas indicating higher concern. The current false positive rate is 1.7%, and detection rate on splices improved by 14 percentage points with the latest model update.

Both tools detect Western blot manipulation. Imagetwin’s latest model covers vertical splices, horizontal splices, and copy-paste forgeries under a unified detection framework, with a 1.7% false positive rate. Beyond Western blots, Imagetwin also screens for cross-publication image plagiarism against a database of 160M+ published figures, detects AI-generated images, and integrates directly into publisher workflows including ScholarOne and Wiley’s Research Exchange. For publishers and institutions that need both manipulation detection and cross-publication screening in one tool, Imagetwin covers both.

Imagetwin detects manipulation across several categories: splicing (vertical and horizontal cuts), copy-paste forgeries, duplication within and across publications, and AI-generated figures. Western blot detection is currently the most developed, with expansion underway to microscopy images, FACS plots, and light photography. Detection is available via the web application and API.

Imagetwin Expands Reach with Image Integrity Checks in Signals Platform

Posted on by Kim

We’re pleased to share that Imagetwin’s image analysis technology is now powering integrity checks within Signals Manuscript Checks, a leading platform used by publishers to evaluate submissions at scale. The integration enables publishers to automatically detect image duplication, plagiarism, manipulation, and AI-generated figures directly within their existing editorial workflows.

“”Research integrity shouldn’t require editors and publishers to juggle multiple tools and platforms. Our partnership with Imagetwin means our publisher users can now conduct Imagetwin’s image analysis alongside Signals Manuscript Checks—automatically and seamlessly within their existing editorial systems. Imagetwin are leaders in image integrity detection, and we’re excited to bring their capabilities directly into the Signals platform.””

— Tiago Barros, Signals Co-Founder

The volume and complexity of manuscript submissions continue to rise, bringing with them an increased risk of integrity issues that threaten publisher reputation. While editorial teams have long relied on fragmented tools to cover different aspects of review, this can slow down workflows and leave gaps in screening.

Our collaboration with Signals addresses that challenge by bringing image-based analysis into one consolidated system. Publishers can now:

  • Combine Imagetwin’s image integrity analysis with Signals’ author, reference, and full-text checks in a single platform

  • Flag issues such as duplication, plagiarism, manipulation, or AI generation, automatically, and early in the review process

  • Access image checks seamlessly through ScholarOne, Editorial Manager, or Direct Upload

Publishers are already seeing the benefits of a unified approach. Chad McCormick, Director of Research Integrity at FASEB, shared:

“Research integrity and editorial efficiency are priorities for FASEB. Having both evaluations in one place helps us quickly identify any issues so that we can focus on high-quality research.”

Available Now

Image integrity checks powered by Imagetwin are now available to publishers using Signals Manuscript Checks, including those integrated with ScholarOne and Editorial Manager.

This collaboration reflects a broader shift in scholarly publishing: image integrity is no longer a nice-to-have. It’s essential for protecting research quality and preserving trust in scientific communication.

About Signals

Signals is a comprehensive manuscript analysis platform designed to help publishers detect issues and evaluate submissions with greater accuracy and efficiency. By uniting author, reference, and content checks in one solution, Signals streamlines editorial workflows, reduces manual effort, and enhances decision-making across the publication process.

Frequently asked questions

Imagetwin is used by major academic publishers including Wiley, Karger, Sage, ASM, and FASEB, and is integrated into platforms serving thousands of journals globally. It powers image integrity checks within Signals Manuscript Checks, ScholarOne Manuscripts, Wiley’s Research Exchange, Editorial Manager, CACTUS’s Paperpal Preflight, and Rivyr. Publishers described by Signals co-founder Tiago Barros as already seeing benefits include FASEB, whose Director of Research Integrity confirmed the value of having image and manuscript checks unified in one platform.

Yes. Imagetwin is available within Editorial Manager through integrations with both Signals Manuscript Checks and Rivyr. Publishers using Editorial Manager can run automated image integrity checks covering duplication, manipulation, plagiarism, and AI-generated figures as part of their standard submission workflow, without switching platforms or adding manual steps.

Imagetwin is the leading image integrity tool for both systems. It integrates with ScholarOne via its partnership with Silverchair, and with Editorial Manager via Signals and Rivyr. It screens figures against a database of 160M+ published scientific images, achieves 90% accuracy on Western blot duplicate detection, and runs at a 1.7% false positive rate on manipulation detection. It is trusted by Wiley, Karger, Sage, ASM, and FASEB, and is priced per paper rather than per sub-image.