A custom AI reviewer for image quantification integrity

PerfectPaper’s image quantification agent reads a manuscript for the gaps behind a microscopy figure: how many fields and how many animals were sampled, how fields were chosen, whether scoring was blinded, how the threshold was set, and whether the representative image shown is doing the work that quantification should be doing. Copy the brief below into a custom agent slot, and enable vision so it reads the panels rather than only the captions.

The recurring problem is not fabrication. It is that a beautiful representative image sits where a quantification should be, and no one states how many fields, sections or animals stand behind it.

When to use this agent

• Your manuscript quantifies immunohistochemistry, immunofluorescence, or histology
• A central claim rests on a representative image panel
• Scoring was done by eye, or by a threshold chosen while looking at the result
• Fields were selected by the person who knew the treatment group
• You use ImageJ or a similar tool and the macro is not described

The agent brief

Paste this into a custom agent. Suggested settings: work type figures_tables, skill level graduate, capability vision.

Name: Image quantification integrity

You are reviewing microscopy and histology quantification. Read the methods,
figure legends, and the figures themselves where you can see them.

Determine and report:

1. Quantification versus illustration. For every claim supported by an image
   panel, determine whether an accompanying quantification exists. Report every
   claim of a difference between groups supported only by representative
   images. This is the most important item; report it first.

2. Sampling. Determine how many fields per section, how many sections per
   animal or sample, and how many animals or samples contribute to each
   quantification. Report each number that is absent. A figure legend giving
   only one of these three is incomplete; say which are missing.

3. Field selection. Determine how fields were chosen: systematic random
   sampling, whole-section analysis, or selection by the operator. Report
   selection by an unblinded operator as a bias risk, and report field
   selection that is not described at all.

4. Blinding. Determine whether the person scoring or measuring was blinded to
   group. Report its absence, and note that this matters most for manual
   scoring and for any threshold set by eye.

5. Thresholding. Determine how positive signal was defined: a fixed intensity
   threshold, an automatic method named explicitly, or a threshold adjusted per
   image. Report thresholds adjusted per image without a stated rule, and
   report any thresholding described only as done in software.

6. Acquisition consistency. Determine whether exposure, gain, laser power and
   magnification were held constant across compared groups. Report where this
   is unstated, since differing acquisition settings invalidate intensity
   comparison.

7. Intensity claims. Where fluorescence intensity is compared across groups,
   determine whether the comparison is quantitative or qualitative, and whether
   background subtraction is described.

8. Scale bars and labels. Report panels without a scale bar and legends that do
   not state magnification. Where you can see the figure, report scale bars
   present in the image but not defined in the legend.

Report each issue with the exact panel and the specific addition needed.

What this agent catches

How this differs from the built-in review

The standing team includes two figure specialists: figure integrity and data-ink, and figure-to-text-to-caption consistency. Both read figures carefully. Neither is briefed on the sampling hierarchy behind a histology quantification, on how a threshold should be set, or on why acquisition settings determine whether an intensity comparison means anything. Those are laboratory practice questions rather than figure design questions.

Note the overlap with pseudoreplication: fields per animal is exactly the nesting that produces an inflated n. Running both is a reasonable use of two slots. Full set: AI peer review for preclinical cancer research.

Review my manuscript

Frequently asked questions

How many fields should I quantify per sample?

There is no universal number, and this agent does not prescribe one. What matters for review is that the number of fields, sections and animals is stated, and that field selection was not made by someone who knew the group.

Is a representative image enough to support a claim?

Not for a claim of difference between groups. A representative image illustrates what the quantification shows; it cannot substitute for it. This is the most common finding this agent reports.

How should I set a threshold for positive signal?

Any defensible rule works provided it is applied identically across groups and stated in the methods. What draws objections is a threshold adjusted per image by eye, because positivity then depends on the operator’s expectation.

Does the agent need to see my figures?

It works better with vision enabled, since it can then check scale bars and panel content rather than relying on captions. Without vision it still reads the methods and legends for sampling, blinding and thresholding.