EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Polyp characterization using deep learning and a publicly accessible polyp video database

Rawen Kader iD, Anton Cid-Mejias, Patrick Brandao, Shahraz Islam, Sanjith Hebbar, Juana González-Bueno Puyal, Omer F Ahmad, Mohamed Hussein, Daniel Toth, Peter Mountney, Ed Seward, Roser Vega und 2 weitere

Digestive Endoscopy · 2023-07 · 35 (5) · 645-655

DOI: 10.1111/den.14500 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digestive Endoscopy, online erschienen am 18.01.2023. Verfasst von Rawen Kader und 13 weiteren Autor:innen. Beteiligte Einrichtung: Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK. Hauptthemen laut MEDLINE: Colonic Polyps, Colorectal Neoplasms, Deep Learning, Adenoma. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, Innovate UK.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Convolutional neural networks (CNN) for computer‐aided diagnosis of polyps are often trained using high‐quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow‐band imaging (NBI) and NBI‐near focus (NBI‐NF) and created a publicly accessible polyp video database.

Methods

We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test‐sets. Test‐set I consists of 14,320 frames (157 polyps, 111 diminutive). Test‐set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists.

Results

Sensitivity for adenoma characterization was 91.6% in test‐set I and 89.7% in test‐set II. Specificity was 91.9% and 88.5%. Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI‐NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)‐1 and PIVI‐2 thresholds for each test‐set. In the benchmarking of test‐set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2–23.6], P = 0.01) with no significant difference with experts.

Conclusions

A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI‐NF. A publicly accessible NBI polyp video database was created and benchmarked.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colonic PolypsColorectal NeoplasmsDeep LearningAdenomaHumansColonoscopyNarrow Band Imaging

Stichwörter der Autor:innen

artificial intelligencecolonic polypcolonoscopycolorectal neoplasmdeep learning

Autor:innen und Institutionen

  • Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK.
  • Division of Surgery and Interventional Sciences, University College London, London, UK.
  • Gastrointestinal Services, University College London Hospital, London, UK.
  • Odin Vision Ltd, London, UK.

ORCID-Profile: Rawen Kader

Förderung

  • Wellcome Trust
  • Innovate UK

Zitieren

APA

Kader, R., Cid-Mejias, A., Brandao, P., Islam, S., Hebbar, S., Puyal, J. G., Ahmad, O. F., Hussein, M., Toth, D., Mountney, P., Seward, E., Vega, R., Stoyanov, D., & Lovat, L. B. (2023). Polyp characterization using deep learning and a publicly accessible polyp video database. Digestive Endoscopy, 35(5), 645-655. https://doi.org/10.1111/den.14500

Vancouver

Kader R, Cid-Mejias A, Brandao P, Islam S, Hebbar S, Puyal JG, et al. Polyp characterization using deep learning and a publicly accessible polyp video database. Digestive Endoscopy. 2023;35(5):645-655. doi:10.1111/den.14500

BibTeX
@article{Kader2023,
  author = {Kader, Rawen and Cid-Mejias, Anton and Brandao, Patrick and Islam, Shahraz and Hebbar, Sanjith and Puyal, Juana González-Bueno and Ahmad, Omer F and Hussein, Mohamed and Toth, Daniel and Mountney, Peter and Seward, Ed and Vega, Roser and Stoyanov, Danail and Lovat, Laurence B},
  title = {Polyp characterization using deep learning and a publicly accessible polyp video database},
  journal = {Digestive Endoscopy},
  year = {2023},
  volume = {35},
  number = {5},
  pages = {645--655},
  doi = {10.1111/den.14500}
}
Kostenlos starten →