Evidence map›Paper›PMID 35521666›Full record

ArticleUnited European gastroenterology journal2022

A new artificial intelligence system successfully detects and localises early neoplasia in Barrett's esophagus by using convolutional neural networks.

Mohamed Hussein, Juana González-Bueno Puyal, David Lines, Vinay Sehgal, Daniel Toth, Omer F Ahmad, Rawen Kader, Martin Everson, Gideon Lipman, Jacobo Ortiz Fernandez-Sordo and 9 more

Open access · hybridAbstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in United European gastroenterology journal, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 33 papers.

0numbers the graph read from it
0cells of the map it votes in
33citing papers in PubMed
9.8field-weighted citation impact, top 1% of its field
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

33 citing papers in PubMed, 49 citations in OpenAlex.

  1. Artificial Intelligence for Esophageal Precancerous Lesions and Esophageal Cancer.The Korean journal of helicobacter and upper gastrointestinal research · 2026
    Review
  2. Review
  3. Review
  4. Article
  5. Article
  6. Review
  7. Review
  8. Article
  9. Review
  10. Article
  11. Article
  12. Article
  13. Article
  14. Review
  15. Review
  16. Review
  17. Article
  18. Review
  19. Article
  20. Review
4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

19 authors at 8 institutions in 5 countries.

Mohamed HusseinDivision of Surgery and Interventional Sciences, University College London, London, UK.ORCID 0000-0001-9529-3528
Juana González-Bueno PuyalWellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK.
David LinesOdin Vision, London, UK.
Vinay SehgalDepartment of Gastroenterology, University College London Hospital, London, UK.
Daniel TothOdin Vision, London, UK.
Omer F AhmadWellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK.
Rawen KaderWellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK.ORCID 0000-0001-9133-0838
Martin EversonDivision of Surgery and Interventional Sciences, University College London, London, UK.
Gideon LipmanDivision of Surgery and Interventional Sciences, University College London, London, UK.
Jacobo Ortiz Fernandez-SordoNIHR Nottingham Digestive Diseases Biomedical Research Centre, Nottingham, UK.
Krish RagunathNIHR Nottingham Digestive Diseases Biomedical Research Centre, Nottingham, UK.
Jose Miguel EstebanClínico San Carlos, Madrid, Spain.
Raf BisschopsUZ Leuven, Leuven, Belgium.ORCID 0000-0002-9994-8226
Matthew BanksDepartment of Gastroenterology, University College London Hospital, London, UK.
Michael HaefnerSt Elisabeth Hospital, Vienna, Austria.
Peter MountneyOdin Vision, London, UK.
Danail StoyanovWellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK.
Laurence B LovatDivision of Surgery and Interventional Sciences, University College London, London, UK.
Rehan HaidryDivision of Surgery and Interventional Sciences, University College London, London, UK.
University College Hospital · GBLondon Vision Clinic · GBWellcome / EPSRC Centre for Interventional and Surgical Sciences · GBNIHR Nottingham Digestive Diseases Biomedical Research Unit · GBUniversity College London · GBHospital Clínico San Carlos · ESSt. Elisabeth Hospital · CWUniversitair Ziekenhuis Leuven · BE

Funding

Cancer Research UKDepartment of HealthWellcome TrustWellcome Trust 203145Z/16/Z
6 · The paper itself

Abstract

BACKGROUND AND

aimsSeattle protocol biopsies for Barrett's Esophagus (BE) surveillance are labour intensive with low compliance. Dysplasia detection rates vary, leading to missed lesions. This can potentially be offset with computer aided detection. We have developed convolutional neural networks (CNNs) to identify areas of dysplasia and where to target biopsy.

methods119 Videos were collected in high-definition white light and optical chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and non-dysplastic BE (NDBE). We trained an indirectly supervised CNN to classify images as dysplastic/non-dysplastic using whole video annotations to minimise selection bias and maximise accuracy. The CNN was trained using 148,936 video frames (31 dysplastic patients, 31 NDBE, two normal esophagus), validated on 25,161 images from 11 patient videos and tested on 264 iscan-1 images from 28 dysplastic and 16 NDBE patients which included expert delineations. To localise targeted biopsies/delineations, a second directly supervised CNN was generated based on expert delineations of 94 dysplastic images from 30 patients. This was tested on 86 i-scan one images from 28 dysplastic patients.

findingsThe indirectly supervised CNN achieved a per image sensitivity in the test set of 91%, specificity 79%, area under receiver operator curve of 93% to detect dysplasia. Per-lesion sensitivity was 100%. Mean assessment speed was 48 frames per second (fps). 97% of targeted biopsy predictions matched expert and histological assessment at 56 fps. The artificial intelligence system performed better than six endoscopists.

interpretationOur CNNs classify and localise dysplastic Barrett's Esophagus potentially supporting endoscopists during surveillance.

Indexed as

Barrett EsophagusEsophageal NeoplasmsArtificial IntelligenceBiopsyHumansNeural Networks, ComputerAIartificial intelligenceBarrett's EsophagusCADCNNcomputer aided detectionconvolutional neural networksearly detectionearly neoplasianeoplasia

Identifiers

PMID35521666
PMCPMC9278593
OpenAlexW4229016815

What OpenQuestion holds

Textmetadata
LicenceCC BY
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 OpenQuestion graph.