EndoUNet: A Unified Model for Anatomical Site Classification, Lesion Categorization and Segmentation for Upper Gastrointestinal Endoscopy

Endoscopy is one of the most effective methods for diagnosing diseases in the upper GI tract. This paper proposes a unified encoder-decoder model for dealing with three tasks simultaneously: anatomical site classification, lesion classification, and lesion segmentation. In addition, the model can le...

Full description

Saved in:
Bibliographic Details
Main Authors: Manh, Nguyen Duy, Hang, Dao Viet, Long, Dao Van, Hung, Le Quang, Khanh, Pham Cong, Oanh, Nguyen Thi, Thuy, Nguyen Thi, Sang, Dinh Viet
Format: Conference Proceeding
Language:English
Subjects:
Data models
Endoscopes
Gastrointestinal tract
Image segmentation
Knowledge engineering
Multitasking
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Endoscopy is one of the most effective methods for diagnosing diseases in the upper GI tract. This paper proposes a unified encoder-decoder model for dealing with three tasks simultaneously: anatomical site classification, lesion classification, and lesion segmentation. In addition, the model can learn from a training set comprised of data from multiple sources. We report results on our own large dataset of 8207 images obtained during routine upper GI endoscopic examinations. Experiments show that our model performs admirably in terms of classification accuracy and yields competitive segmentation results compared to the single-task model with the same architecture.
ISSN:2694-4804
DOI:10.1109/KSE56063.2022.9953766