Evidence map›Paper›PMID 40437217›Full record

ArticleNature methods2025

InterpolAI: deep learning-based optical flow interpolation and restoration of biomedical images for improved 3D tissue mapping.

Saurabh Joshi, André Forjaz, Kyu Sang Han, Yu Shen, Vasco Queiroga, Florin A Selaru, Marie Gérard, Daniel Xenes, Jordan Matelsky, Brock Wester and 4 more

Abstract read
In one paragraph

Article in Nature methods, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.

0numbers the graph read from it
0cells of the map it votes in
14citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

14 citing papers in PubMed.

  1. Review
  2. Article
  3. Article
  4. Review
  5. Fault-tolerant 3D reconstruction from 2D spatial proteomics sections.bioRxiv : the preprint server for biology · 2026
    Article
  6. Article
  7. Article
  8. Article
  9. Article
  10. Review
  11. Review
  12. Article
  13. Article
  14. Article
4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

14 authors.

Saurabh Joshi *Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.
André Forjaz *Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.ORCID http://orcid.org/0009-0002-5115-2293
Kyu Sang HanDepartment of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.ORCID http://orcid.org/0000-0001-7677-8386
Yu ShenDepartment of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.
Vasco QueirogaDepartment of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.ORCID http://orcid.org/0009-0004-7812-0472
Florin A SelaruDepartment of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
Marie GérardScenario, Covina, CA, USA.
Daniel XenesResearch and Exploratory Development Department, Johns Hopkins Applied Physics Laboratory, Laurel, MD, USA.ORCID http://orcid.org/0009-0008-4812-0120
Jordan MatelskyResearch and Exploratory Development Department, Johns Hopkins Applied Physics Laboratory, Laurel, MD, USA.
Brock WesterResearch and Exploratory Development Department, Johns Hopkins Applied Physics Laboratory, Laurel, MD, USA.ORCID http://orcid.org/0000-0002-1500-2143
Arrate Muñoz BarrutiaBioengineering Department, Universidad Carlos III de Madrid and Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain.ORCID http://orcid.org/0000-0002-1573-1661
Ashley L KiemenDepartment of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.ORCID http://orcid.org/0000-0002-6281-2616
Pei-Hsun WuDepartment of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA.ORCID http://orcid.org/0000-0002-7371-2960
Denis WirtzDepartment of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA. wirtz@jhu.edu.ORCID http://orcid.org/0000-0001-6147-3045

Funding

Tech Core 2U54CA268083 · NCI · JOHNS HOPKINS UNIVERSITY · PI Andrew Josef Ewald · 2022 to 2026
$10.2M
Boss: A cloud-based data archive for electron microscopy and x-ray microtomographyR24MH114785 · NIMH · JOHNS HOPKINS UNIVERSITY · PI BROCK A. WESTER · 2018 to 2026
$6.9M
Three-dimensional maps of senescence in the human pancreasUH3CA275681 · NCI · JOHNS HOPKINS UNIVERSITY · PI WU, PEI-HSUN · 2024 to 2025
$1.7M
Three-dimensional maps of senescence in the human pancreasUG3CA275681 · NCI · JOHNS HOPKINS UNIVERSITY · PI WU, PEI-HSUN · 2022 to 2023
$1.1M
Organ Specific ProjectU54AR081774 · NIAMS · JOHNS HOPKINS UNIVERSITY · PI REDDY, SASHANK K, WIRTZ, DENIS · 2022 to 2023
$1.1M
NCI NIH HHS U54 CA268083NCI NIH HHS UG3 CA275681NCI NIH HHS UH3 CA275681NIAMS NIH HHS U54 AR081774NIMH NIH HHS R24 MH114785U.S. Department of Health & Human Services | NIH | National Cancer Institute (NCI) U54CA268083U.S. Department of Health & Human Services | NIH | National Institute of Allergy and Infectious Diseases (NIAID) U54AR081774U.S. Department of Health & Human Services | NIH | National Institute of Allergy and Infectious Diseases (NIAID) UG3CA275681U.S. Department of Health & Human Services | NIH | National Institute of Mental Health (NIMH) R24MH114785
6 · The paper itself

Abstract

Recent advances in imaging and computation have enabled analysis of large three-dimensional (3D) biological datasets, revealing spatial composition, morphology, cellular interactions and rare events. However, the accuracy of these analyses is limited by image quality, which can be compromised by missing data, tissue damage or low resolution due to mechanical, temporal or financial constraints. Here, we introduce InterpolAI, a method for interpolation of synthetic images between pairs of authentic images in a stack of images, by leveraging frame interpolation for large image motion, an optical flow-based artificial intelligence (AI) model. InterpolAI outperforms both linear interpolation and state-of-the-art optical flow-based method XVFI, preserving microanatomical features and cell counts, and image contrast, variance and luminance. InterpolAI repairs tissue damages and reduces stitching artifacts. We validated InterpolAI across multiple imaging modalities, species, staining techniques and pixel resolutions. This work demonstrates the potential of AI in improving the resolution, throughput and quality of image datasets to enable improved 3D imaging.

Indexed as

Deep LearningImage Processing, Computer-AssistedImaging, Three-DimensionalAlgorithmsAnimalsHumansMice

Identifiers

PMID40437217
PMCPMC12240858

What Socratic holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.