Computer-aided characterization of early cancer in Barrett’s esophagus on i-scan magnification imaging: a multicenter international study

Hussein, Mohamed; Lines, David; Puyal, Juana González‐Bueno; Kader, Rawen; Bowman, Nicola; Sehgal, Vinay; Tóth, Dániel; Ahmad, Omer F.; Everson, Martin; Esteban, José M.; Bisschops, Raf; Banks, Matthew; Haefner, Michael; Mountney, Peter; Stoyanov, Danail; Lovat, Laurence; Haidry, Rehan

doi:10.1016/j.gie.2022.11.020

Cited by 6 publications

(1 citation statement)

References 19 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 Advances in artificial intelligence will only further improve diagnostic accuracy and targeted sampling, and neural networks have already been trained to accurately classify Barrett's images as dysplastic or non-dysplastic. 10 These strategies need to be measured in relation to their sustainability benefit in a systematic manner.…”

Section: Professional Mattersmentioning

confidence: 99%

Unmet research needs in sustainable luminal gastroenterology practice

Dhar,

Haboubi,

Selinger

et al. 2024

Frontline Gastroenterol

View full text Add to dashboard Cite

While it is now well recognised that gastroenterology, hepatology and endoscopy are major contributors to climate change on account of the amount of greenhouse gases (GHGs) that are generated in these specialties, systematic research that measures the exact amount of GHGs generated by different aspects of clinical care in the specialty is lacking. Similarly, while there are a number of publications highlighting the potential strategies for the reduction of GHGs, interventional studies assessing the impact of change are only beginning to be carried out. As such, there are a number of unmet research needs in this field and this mini review is aimed at discussing some of these.

show abstract

Section: Professional Mattersmentioning

confidence: 99%

Unmet research needs in sustainable luminal gastroenterology practice

Dhar,

Haboubi,

Selinger

et al. 2024

Frontline Gastroenterol

View full text Add to dashboard Cite

show abstract

Exploring vision transformers for classifying early Barrett's dysplasia in endoscopic images: A pilot study on white‐light and narrow‐band imaging

Tan,

Pitawela,

Chinnaratha

et al. 2024

JGH Open

View full text Add to dashboard Cite

Background and AimVarious deep learning models, based on convolutional neural network (CNN), have been shown to improve the detection of early esophageal neoplasia in Barrett's esophagus. Vision transformer (ViT), derived from natural language processing, has emerged as the new state‐of‐the‐art for image recognition, outperforming predecessors such as CNN. This pilot study explores the use of ViT to classify the presence or absence of early esophageal neoplasia in endoscopic images of Barrett's esophagus.MethodsA BO dataset of 1918 images of Barrett's esophagus from 267 unique patients was used. The images were classified as dysplastic (D‐BO) or non‐dysplastic (ND‐BO). A pretrained vision transformer model, ViTBase16, was used to develop our classifier models. Three ViT models were developed for comparison based on imaging modality: white‐light imaging (WLI), narrow‐band imaging (NBI), and combined modalities. Performance of each model was evaluated based on accuracy, sensitivity, specificity, confusion matrices, and receiver operating characteristic curves.ResultsThe ViT models demonstrated the following performance: WLI‐ViT (Accuracy: 92%, Sensitivity: 82%, Specificity: 95%), NBI‐ViT (Accuracy: 99%, Sensitivity: 97%, Specificity: 99%), and combined modalities‐ViT (Accuracy: 93%, Sensitivity: 87%, Specificity: 95%). Combined modalities‐ViT showed greater accuracy (94% vs 90%) and sensitivity (80% vs 70%) compared with WLI‐ViT when classifying WLI images on a subgroup testing set.ConclusionViT exhibited high accuracy in classifying the presence or absence of EON in endoscopic images of Barrett's esophagus. ViT has the potential to be widely applicable to other endoscopic diagnoses of gastrointestinal diseases.

show abstract

Advancement of artificial intelligence systems for surveillance endoscopy of Barrett's esophagus

Jong,

de Groof

2024

Digestive and Liver Disease

View full text Add to dashboard Cite

Computer-aided characterization of early cancer in Barrett’s esophagus on i-scan magnification imaging: a multicenter international study

Cited by 6 publications

References 19 publications

Unmet research needs in sustainable luminal gastroenterology practice

Unmet research needs in sustainable luminal gastroenterology practice

Exploring vision transformers for classifying early Barrett's dysplasia in endoscopic images: A pilot study on white‐light and narrow‐band imaging

Advancement of artificial intelligence systems for surveillance endoscopy of Barrett's esophagus

Contact Info

Product

Resources

About