Loading
Life sciences · Preprint
arXiv · August 19, 2026
Posted before peer review. The findings may change or fail to hold.
This preprint proposes NEAR, a neural-anchor-based framework designed to improve brain-to-image retrieval when only one or few stimulus repetitions are available, by anchoring both noisy neural queries and image gallery representations to a high-repetition center. The method shows consistent improvements in retrieval accuracy across four neuroimaging datasets (EEG, MEG, fMRI), with gains of 5.7 and 9.3 percentage points on THINGS-EEG2 for one and four repetitions respectively. However, as an unreviewed computational study without clinical endpoints or prospective validation, it cannot yet inform clinical practice or establish real-world utility.
Computational methods validation study on retrospective neuroimaging datasets. Subjects and recordings from four existing neuroimaging datasets (EEG, MEG, fMRI); specific inclusion criteria, sample sizes, and participant demographics not stated.. Intervention: NEAR framework: neural-anchor-based retrieval using a denoiser for query alignment and a predictor for gallery image alignment, anchored to high-repetition center representations.. Compared with: Trial averaging (baseline approach using repeated stimulus presentations up to 80 repetitions per image).
On THINGS-EEG2, NEAR improved 200-way Top-1 accuracy by 5.7 percentage points when averaging one repetition On THINGS-EEG2, NEAR improved 200-way Top-1 accuracy by 9.3 percentage points when averaging four repetitions Consistent improvement in few-repetition retrieval reported across four datasets spanning EEG, MEG, and fMRI modalities
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unreviewed preprint presenting a novel computational method for brain-to-image retrieval with consistent improvements across multiple neuroimaging datasets, but lacking peer review and clinical validation.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulus presentation that increases latency, cost, and user burden. When only one or a few repetitions are available, the retrieval accuracy drops sharply. This drop is commonly attributed to query noise because averaging suppresses noise and increases signal stability. However, we find a non-transitive alignment pattern: the low-repetition query signal and the image representation each align with the high-repetition center, but not directly with each other. This pattern shows that query noise is only part of the problem and that gallery placement also affects retrieval. We therefore propose a neural-anchor-based retrieval (NEAR) framework that treats the high-repetition center as an anchor and approaches it from both sides: a denoiser pulls the noisy query toward the true anchor, and a small network predicts each candidate's pseudo anchor from its image and pulls the image toward it. Across four datasets spanning EEG, MEG and fMRI, NEAR consistently improved retrieval in the few-repetition regime. On THINGS-EEG2, it improved 200-way Top-1 accuracy by 5.7 and 9.3 percentage points respectively, when averaging one and four repetitions. By anchoring neural and visual representations, NEAR reduces reliance on repeated acquisition and brings neural retrieval closer to real-world deployment.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.