Optimizing Multi-expert Consensus for Classification and Precise Localization of Barrett's Neoplasia

Koen Kusters, Tim Boers, Tim J.M. Jaspers, Martijn R. Jong, Rixta A.H. van Eijck van Heslinga, Albert J. (Jeroen) de Groof, Jacques J.G.H.M. Bergman, Fons van der Sommen, Peter H.N. de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Recognition of early neoplasia in Barrett’s Esophagus (BE) is challenging, despite advances in endoscopic technology. Even with correct identification, the subtle nature of lesions leads to significant inter-observer variability in placing targeted biopsy markers and delineation of lesions. Computer-Aided Detection (CADe) systems may assist endoscopists, however, compliance of endoscopists with CADe is often suboptimal, reducing joint performance below CADe stand-alone performance. Improved localization performance of CADe could enhance compliance. These systems often use fused consensus ground-truths (GT), which may not capture subtle neoplasia gradations, affecting classification and localization. This study evaluates five consensus GT strategies from multi-expert segmentation labels and four loss functions for their impact on classification and localization performance. The dataset includes 7,995 non-dysplastic BE images (1,256 patients) and 2,947 neoplastic images (823 patients), with each neoplastic image annotated by two experts. Classification, localization for true positives, and combined detection performance are assessed and compared with 14 independent Barrett’s experts. Results show that using multiple consensus GT masks with a compound Binary Cross-Entropy and Dice loss achieves the best classification sensitivity and near-expert level localization, making it the most effective training strategy. The code is made publicly available at: https://github.com/BONS-AI-VCA-AMC/BE-CADe-GT.
Original languageEnglish
Title of host publicationCancer Prevention, Detection, and Intervention - 3rd MICCAI Workshop, CaPTion 2024, Held in Conjunction with MICCAI 2024, Proceedings
Subtitle of host publicationThird MICCAI Workshop, CaPTion 2024, Held in Conjunction with MICCAI 2024, Marrakesh, Morocco, October 6, 2024, Proceedings
EditorsSharib Ali, Fons van der Sommen, Bartłomiej Władysław Papież, Noha Ghatwary, Yueming Jin, Iris Kolenbrander
Place of PublicationCham
PublisherSpringer
Pages83-92
Number of pages10
ISBN (Electronic)978-3-031-73376-5
ISBN (Print)978-3-031-73375-8
DOIs
Publication statusPublished - 9 Oct 2024
Event3rd International Workshop on Cancer Prevention, detection and intervenTion - Satellite event at MICCAI 2024 - Marrakesh, Morocco
Duration: 6 Oct 202410 Oct 2024

Publication series

NameLecture Notes in Computer Science (LNCS)
Volume15199
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference3rd International Workshop on Cancer Prevention, detection and intervenTion - Satellite event at MICCAI 2024
Country/TerritoryMorocco
CityMarrakesh
Period6/10/2410/10/24

Keywords

  • Barrett’s Esophagus
  • Detection
  • Inter-observer variability

Fingerprint

Dive into the research topics of 'Optimizing Multi-expert Consensus for Classification and Precise Localization of Barrett's Neoplasia'. Together they form a unique fingerprint.

Cite this