Evidence map›Paper›PMID 39354052›Full record

ArticleNature biomedical engineering2025

Accurate prediction of disease-risk factors from volumetric medical scans by a deep vision model pre-trained with 2D scans.

Oren Avram, Berkin Durmus, Nadav Rakocz, Giulia Corradetti, Ulzee An, Muneeswar G Nittala, Prerit Terway, Akos Rudas, Zeyuan Johnson Chen, Yu Wakatsuki and 23 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Nature biomedical engineering, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 6 papers.

0numbers the graph read from it
0cells of the map it votes in
6citing 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

6 citing papers in PubMed.

  1. Trial
  2. Article
  3. Article
  4. Article
  5. Review
  6. Article
4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

33 authors.

Oren Avram *Department of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA. orenavram@gmail.com.ORCID http://orcid.org/0000-0003-1984-2139
Berkin Durmus *Department of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA.ORCID http://orcid.org/0000-0002-8137-4439
Nadav RakoczDepartment of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA.ORCID http://orcid.org/0000-0001-5437-9691
Giulia CorradettiDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Ulzee AnDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.ORCID http://orcid.org/0000-0001-8066-7291
Muneeswar G NittalaDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Prerit TerwayDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.
Akos RudasDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.ORCID http://orcid.org/0000-0003-4346-8239
Zeyuan Johnson ChenDepartment of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA.
Yu WakatsukiDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Kazutaka HirabayashiDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Swetha VelagaDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Liran TiosanoDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Federico CorviDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.ORCID http://orcid.org/0000-0002-2661-5500
Aditya VermaDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Ayesha KaramatDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Sophiana LindenbergDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Deniz OncelDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Louay AlmidaniDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Victoria HullDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Sohaib Fasih-AhmadDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Houri EsmaeilkhanianDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA.
Maxime CannessonDepartment of Anesthesiology and Perioperative Medicine, University of California, Los Angeles, Los Angeles, CA, USA.
Charles C WykoffRetina Consultants of Texas, Retina Consultants of America, Houston, TX, USA.ORCID http://orcid.org/0000-0001-7756-5091
Elior RahmaniDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.
Corey W ArnoldDepartment of Radiology, University of California, Los Angeles, Los Angeles, CA, USA.
Bolei ZhouDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.
Noah ZaitlenDepartment of Neurology, University of California, Los Angeles, Los Angeles, CA, USA.
Ilan GronauSchool of Computer Science, Reichman University, Herzliya, Israel.
Sriram SankararamanDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.
Jeffrey N ChiangDepartment of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, USA.ORCID http://orcid.org/0000-0002-6843-1355
Srinivas R SaddaDoheny Eye Institute, University of California, Los Angeles, Pasadena, CA, USA. ssadda@doheny.org.ORCID http://orcid.org/0000-0002-4939-3306
Eran HalperinDepartment of Computer Science, University of California, Los Angeles, Los Angeles, CA, USA. ehalperin@cs.ucla.edu.ORCID http://orcid.org/0000-0002-2373-3691

Funding

Epidemiology of Biomarkers of AMD ProgressionR01EY030614 · NEI · DOHENY EYE INSTITUTE · 2023 to 2025
$1.2M
Computational Genomics Summer Institute and Mentoring NetworkR25GM135043 · NIGMS · UNIVERSITY OF CALIFORNIA LOS ANGELES · 2022 to 2025
$622k
Personalized Risk Prediction for Prevention and Early Detection of Postoperative Failure to RescueR01EB035028 · UNIVERSITY OF CALIFORNIA LOS ANGELES · 2025 to 2025
$611k
NEI NIH HHS R01 EY023164NEI NIH HHS R01 EY030614NIBIB NIH HHS R01 EB035028NIGMS NIH HHS R25 GM135043
6 · The paper itself

Abstract

The application of machine learning to tasks involving volumetric biomedical imaging is constrained by the limited availability of annotated datasets of three-dimensional (3D) scans for model training. Here we report a deep-learning model pre-trained on 2D scans (for which annotated data are relatively abundant) that accurately predicts disease-risk factors from 3D medical-scan modalities. The model, which we named SLIViT (for 'slice integration by vision transformer'), preprocesses a given volumetric scan into 2D images, extracts their feature map and integrates it into a single prediction. We evaluated the model in eight different learning tasks, including classification and regression for six datasets involving four volumetric imaging modalities (computed tomography, magnetic resonance imaging, optical coherence tomography and ultrasound). SLIViT consistently outperformed domain-specific state-of-the-art models and was typically as accurate as clinical specialists who had spent considerable time manually annotating the analysed scans. Automating diagnosis tasks involving volumetric scans may save valuable clinician hours, reduce data acquisition costs and duration, and help expedite medical research and clinical applications.

Indexed as

Deep LearningImaging, Three-DimensionalAlgorithmsHumansMachine LearningMagnetic Resonance ImagingRisk FactorsTomography, Optical CoherenceTomography, X-Ray ComputedUltrasonography

Identifiers

PMID39354052
PMCPMC12695137

What Socratic holds

Textmetadata
LicenceTDM
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.