Proofig AI expands beyond image integrity: meet Octym, the complete manuscript review →

Seamlessly Integrating Image Integrity Checks into Automated Publishing Systems: A Guide for Researchers and Publishers

Abstract illustration of scientific image integrity with microscopy patterns and molecular visuals in cool tones.

Proofig AI integrates with automated publishing systems, including through its partnership with Aries Systems, to run image integrity screening at the point of manuscript submission. This benefits publishers managing rising submission volumes and researchers who want to catch suspected issues before they reach an editor, reducing the risk of rejection, correction, or retraction.

Why Can’t Manual Screening Keep Up?

Image integrity problems in scientific manuscripts are well documented and widespread. Industry analyses and integrity experts indicate that a substantial proportion of life-science manuscripts submitted to journals, potentially 20–35%, are flagged for potential image-related issues. Many of these are unintentional, arising from figure preparation errors, mislabeling, or workflow mistakes involving multiple collaborators.

The scale of the problem extends into the published literature as well. Systematic screening of life-science publications has documented significant rates of image and data duplication, reinforcing the need for stronger pre-publication review. Meanwhile, approximately 0.2% of articles published in 2022 are now retracted, roughly triple the rate from a decade earlier.

Manual figure review by editors and reviewers cannot keep pace with these volumes. A peer-reviewed study at the University of Split found that researchers correctly identified only 32.4% of image duplications when reviewing figures by eye, and medical students fared no better at 29.4%. This is not a criticism of reviewers. It reflects the limits of unaided human visual inspection when applied to thousands of submissions per year.

The operational reality is clear: publishers need automated screening, and researchers benefit from it too.

What Does “Integration” Actually Mean?

There is an important difference between a standalone tool and an integrated system. A standalone tool requires a researcher to manually upload files, review results, and act on them independently. An integrated system embeds image integrity screening directly into an existing workflow, so checks run automatically at defined trigger points.

For publishers, integration means that when a manuscript is submitted through an editorial management system, image integrity screening is triggered without manual intervention from editorial staff. Flagged items surface in the editorial dashboard for human review. No one needs to remember to run a separate check.

For researchers, integration can take two forms. First, a researcher submitting to a journal that uses integrated screening benefits from automated checks as part of the submission process. Second, a researcher can use Proofig AI’s image integrity capabilities before submission, during manuscript preparation, to catch suspected issues early.

Both approaches serve the same goal: surfacing potential problems before they become published errors.

How Does the Aries Systems Integration Work?

Proofig AI’s partnership with Aries Systems is a concrete example of publisher-side integration. Aries Systems provides workflow management solutions used by scholarly publishers worldwide. Through this partnership, Proofig AI’s integration with Aries Systems enables automated image integrity screening at scale within the editorial workflow.

Operationally, this means:

  • When a manuscript is submitted, image screening is triggered automatically.
  • Proofig AI analyzes all figures in the manuscript, automatically or on editorial trigger, depending on journal configuration, without requiring separate manual uploads by staff.
  • Suspected issues are flagged and surfaced for human review within the editorial workflow.
  • Editorial teams can act on flagged items earlier in the review process, before peer review or publication.

This integration does not replace human judgment. It supports editorial teams by identifying suspected issues that warrant closer inspection. The tool surfaces items for review. Editors and integrity officers make the decisions.

What Does Proofig AI Check in an Integrated Workflow?

When Proofig AI runs within an integrated submission system, five core capabilities are applied to every manuscript:

Capability What It Detects
Image Manipulation Detection Alteration within a single sub-image, including cloning, editing, deletion, splicing, and content-aware edits
Duplication & Reuse Analysis Duplication or reuse within a manuscript, including scaling, rotation, flipping, and partial overlap
AI-Generated Image Identification Images created by generative AI across microscopy, histology, Western blots, medical scans, and other modalities
Image Plagiarism (PubMed Source) Reuse of sub-images from previously published manuscripts, checked against PubMed’s database of tens of millions of images
Self-Plagiarism Control (My Database) Reuse of a researcher’s own previously published images, checked against a personalized repository

These checks cover the major scientific image types: all forms of microscopy (confocal, light, electron), Western blots and gels, FACS, histology, cell plates, animal imaging, medical scans, and more. Nature has reported on the rise of AI-generated images in scientific manuscripts, making the AI-generated image detection capability increasingly relevant.

This is not a surface-level check. It is substantive screening across the full range of integrity risks that affect scientific figures.

Why Does Integration Matter for Researchers?

Researchers benefit from automated screening even when they are not managing a journal. Image integrity issues can enter a manuscript through complex workflows involving collaborators, students, junior team members, and shared data handling. Even researchers who uphold the highest ethical standards may unknowingly submit problematic images because of errors introduced by others in the workflow.

Nature has reported on the personal and career stress researchers face when retracting papers, often due to honest mistakes that pre-submission screening could have caught. The consequences of a flagged or retracted paper, including significant financial and reputational impacts, fall on the corresponding author regardless of who introduced the error.

Using Proofig AI for pre-submission screening allows researchers to catch suspected issues before they reach an editor. This is a proactive step to protect your work, your name, and your lab.

Does Automated Screening Create More Noise Than Signal?

A reasonable concern about any automated check is whether it generates excessive false alarms that waste editorial time. Proofig AI is validated on hundreds of thousands of real images and produces very few false positives, so editorial teams and researchers are not buried in noise and can focus on items that genuinely warrant human review.

How Early Can Integrity Checks Move in the Research Lifecycle?

Proofig AI’s partnership with LabArchives signals that integrity checks can move earlier than the submission stage. LabArchives provides electronic lab notebook solutions, and the partnership with Proofig AI supports bringing integrity-minded practices closer to research creation and preparation. This means potential issues can be identified during data collection and figure assembly, not just at the point of journal submission.

For publishers seeking a broader quality assurance workflow, Proofig also offers PubShield, an institutional manuscript quality assurance hub. PubShield brings Proofig AI’s image screening together with third-party partner tools, covering text similarity, reference integrity, AI-generated text detection, and data compliance, in a single dashboard.

What Should Researchers and Publishers Do Now?

For publishers: Evaluate whether your current submission system supports integration with automated image integrity tools. If you use Aries Systems or a comparable editorial management platform, explore what automated screening would look like operationally. The goal is to surface suspected issues for human review earlier in the editorial process, before peer review and publication.

For researchers: Use Proofig AI before submission to screen your manuscript’s figures for suspected duplication, manipulation, AI-generated content, and reuse. This is especially important if your work involves multiple collaborators or shared data handling, where issues can be introduced without your knowledge. Catching suspected problems before submission reduces the risk of rejection, correction, or retraction, and protects the credibility of your research.

The goal is not to assume wrongdoing, but to support human review by surfacing suspected issues early. Integration makes that possible at scale.

Related Items