Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions

Abstract

Background Computer-aided detection (CADe) systems may improve detection of Barrett’s neoplasia. Most CADe systems are developed with data from expert centers, unrepresentative of heterogeneous imaging conditions in community hospitals, and therefore may underperform in routine practice. We aimed to develop a robust CADe system (CADe 2.0) and compare its performance to a previously published system (CADe 1.0) under heterogeneous imaging conditions representative of real-world clinical practice.

Method CADe 2.0 was improved through a larger and more diverse training dataset, optimized pretraining, data augmentation, ground truth use, and architectural adjustments. CADe systems were evaluated using three prospective test sets. Test set 1 comprised 428 Barrett’s videos (114 patients across five referral centers). Test set 2 addressed endoscopist-dependent variation (e. g. mucosal cleaning and esophageal expansion), with paired subsets of high, moderate, and low quality images (122 patients). Test set 3 addressed endoscopist-independent variation, with 16 paired subsets of 396 images (122 patients), each being based on a different software image-enhancement setting.

Results CADe 2.0 outperformed CADe 1.0 on all three test sets. In test set 1, sensitivity increased significantly from 87 % to 96 % (P = 0.02), while specificity remained comparable (73 % vs. 74 %; P = 0.73). In test set 2, CADe 2.0 consistently surpassed CADe 1.0 across all image quality levels, with the largest performance gains observed on lower quality images (sensitivity 78 % vs. 61 %; specificity 89 % vs. 77 %; area under the curve 89 % vs. 75 %). In test set 3, CADe 2.0 showed improved performance and displayed reduced performance variability across enhancement settings.

Conclusion Based on several key improvements, CADe 2.0 demonstrated increased detection rates and better robustness to data heterogeneity, making it ready for clinical implementation.

^‡ joint first authors

Publication History

Received: 28 January 2025

Accepted after revision: 22 June 2025

Accepted Manuscript online:
25 June 2025

Article published online:
19 August 2025

• References

• 1 Sharma P. Barrett esophagus: a review. JAMA 2022; 328: 663-671
• 2 Weusten BLAM, Bisschops R, Dinis-Ribeiro M. et al. Diagnosis and management of Barrett esophagus: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy 2023; 55: 1124-1146
• 3 chölvinck DW, van der Meulen K, Bergman J. et al. Detection of lesions in dysplastic Barrett's esophagus by community and expert endoscopists. Endoscopy 2017; 49: 113-120
• 4 Beveridge CA, Mittal C, Muthusamy VR. et al. Identification of visible lesions during surveillance endoscopy for Barrett's esophagus: a video-based survey study. Gastrointest Endosc 2023; 97: 241-247.e2
• 5 Sawas T, Majzoub AM, Haddad J. et al. Magnitude and time-trend analysis of postendoscopy esophageal adenocarcinoma: a systematic review and meta-analysis. Clin Gastroenterol Hepatol 2022; 20: e31-e50
• 6 Frazzoni L, Arribas J, Antonelli G. et al. Endoscopists' diagnostic accuracy in detecting upper gastrointestinal neoplasia in the framework of artificial intelligence studies. Endoscopy 2022; 54: 403-411
• 7 Desai D, Srinivasan S, Nutalapati V. et al. Post-endoscopy Barrett’s neoplasia after a negative index endoscopy: a systematic review and proposal for definitions and performance measures in endoscopy. Endoscopy 2022; 54: 881-889
• 8 Abdelrahim M, Saiko M, Maeda N. et al. Development and validation of artificial neural networks model for detection of Barrett’s neoplasia, a multicenter pragmatic non-randomized trial. Gastrointest Endosc 2023; 97: 422-434
• 9 Meinikheim M, Mendel R, Palm C. et al. Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett’s esophagus: a tandem randomized and video trial. Endoscopy 2024; 56: 641-649
• 10 Fockens KN, Jukema JB, Boers T. et al. Towards a robust and compact deep learning system for primary detection of early Barrett's neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set. United European Gastroenterol J 2023; 11: 324-336
• 11 Hussein M, González-Bueno Puyal J, Lines D. et al. A new artificial intelligence system successfully detects and localises early neoplasia in Barrett's esophagus by using convolutional neural networks. United European Gastroenterol J 2022; 10: 528-537
• 12 Fockens N, Jong MR, Jukema JB. et al. A deep learning system for detection of early Barrett's neoplasia: a model development and validation study. Lancet Digit Health 2023; 5: 905-921
• 13 Subbaswamy A, Saria S. From development to deployment: dataset shift, causality, and shift-stable models in health AI. Biostatistics 2020; 21: 345-352
• 14 Finlayson SG, Subbaswamy A, Singh K. et al. The clinician and dataset shift in artificial intelligence. NEJM 2021; 385: 283-286
• 15 De Groof AJ. Artificial intelligence (AI) systems for detection of Barrett’s neoplasia: time to bridge domain gaps and explore human–AI interaction. Endoscopy 2024; 56: 650-652
• 16 Jong MR, Jaspers TJM, Kusters CHJ. et al. Challenges in implementing endoscopic artificial intelligence: the impact of real-world imaging conditions on Barrett's neoplasia detection. United European Gastroenterol J 2025; 13: 929-937
• 17 Jaspers TJM, Boers TGW, Kusters CHJ. et al. Robustness evaluation of deep neural networks for endoscopic image analysis: Insights and strategies. Med Image Anal 2024; 94: 103157
• 18 Jong M, Kusters K, van Bokhorst Q. et al. Domain-specific data augmentation for robust AI systems in endoscopy. Gastrointest Endosc 2024; 99: AB27-AB28
• 19 Antonelli G, Libanio D, De Groof AJ. et al. QUAIDE – Quality assessment of AI preclinical studies in diagnostic endoscopy. Gut 2024; 74: 153-161
• 20 Xie Q, Dai Z, Hovy E. et al. Unsupervised data augmentation for consistency training. arXiv [eprint] 2019;
• 21 Jukema J, Fockens K, Boers T. et al. Domain-specific pretraining of deep learning systems in gastrointestinal endoscopy improves performance over current state-of-the-art pretraining methods. ESGE Days 2023. Endoscopy 2023; 55 (Suppl. 02) S83-S84
• 22 Deng J, Dong W, Socher R. et al. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA: 2009: 248-255
• 23 He K, Girshick R, Dollár P. Rethinking ImageNet pre-training. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea: 2019: 4917-4926
• 24 Zamir AR, Sax A, Shen W. Taskonomy: disentangling task transfer learning. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: 2018: 3712-3722
• 25 Boers TGW, Fockens KN, van der Putten JA. et al. Foundation models in gastrointestinal endoscopic AI: Impact of architecture, pre-training approach and data efficiency. Med Image Anal 2024; 98: 103298
• 26 Caron M, Touvron H, Misra I. et al. Emerging properties in self-supervised vision transformers. arXiv [eprint] 2021;
• 27 Jong MR, Jaspers TJ, Kusters KC. et al. Tu2011 Image quality challenges in AI: improving robustness of a computer aided detection system for Barrett's neoplasia. Gastroenterology 2024; 166: S1491
• 28 Yu W, Luo M, Zhou P. et al. MetaFormer is actually what you need for vision. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA, USA: 2022: 10809-10819
• 29 Yu W, Si C, Zhou P. et al. MetaFormer baselines for vision. IEEE Trans Pattern Anal Mach Intell 2024; 46: 896-912
• 30 Kusters CHJ, Jaspers TJM, Boers TGW. et al. Will Transformers change gastrointestinal endoscopic image analysis? A comparative analysis between CNNs and Transformers, in terms of performance, robustness and generalization. Med Image Anal 2025; 99: 103348
• 31 Jong MR, Kusters CHJ, van Bokhorst QNE. et al. Impact of standard enhancement settings of endoscopy systems on performance of endoscopic artificial intelligence systems. Endoscopy 2025; 57: 602-610
• 32 Kusters CHJ, Boers TGW, Jaspers TJM. et al. Optimizing multi-expert consensus for classification and precise localization of Barrett’s neoplasia. Ali S, van der Sommen F, Papież BW. Cancer Prevention, Detection, and Intervention. Cham, Switzerland: Springer; 2025: 83-92
• 33 Kader R, Hassan C, Lanas Á. et al. Cloud-based artificial intelligence for detection of colorectal neoplasia – a randomized controlled trial (EAGLE Trial). Endoscopy 2025; 57 (Suppl. 02) BA003
• 34 Mori Y. Artificial intelligence for a rare disease. Endoscopy 2024; 57: 310-311
• 35 Jong MR, Jaspers TJM, van Eijck van Heslinga RAH. et al. The development and ex vivo evaluation of a computer-aided quality control system for Barrett's esophagus endoscopy. Endoscopy 2025; 57: 709-716