Attention-Enhanced Multi-Task Deep Learning Model for Classification and Segmentation of Esophageal Lesions
Open Access
- 4 March 2025
- journal article
- Published by American Chemical Society (ACS) in ACS Omega
- Vol. 10 (10) , 10468-10479
Abstract
Accurate detection and segmentation of esophageal lesions are crucial for diagnosing and treating gastrointestinal diseases. However, early detection of esophageal cancer remains challenging, contributing to a reduced five-year survival rate among patients. This paper introduces a novel multitask deep learning model for automatic diagnosis that integrates classification and segmentation tasks to assist endoscopists effectively. Our approach leverages the MobileNetV2 deep learning architecture enhanced with a mutual attention module, significantly improving the model's performance in determining the locations of esophageal lesions. Unlike traditional models, the proposed model is designed not to replace endoscopists but to empower them to correct false predictions when provided with additional Supporting Information. We evaluated the proposed model on three well-known data sets: Early Esophageal Cancer (EEC), CVC-ClinicDB, and KVASIR. The experimental results demonstrate promising performance, achieving high classification accuracies of 98.72% (F1-score: 98.08%) on CVC-ClinicDB, 98.95% (F1-score: 98.32%) on KVASIR, and 99.12% (F1-score: 99.00%) on our generated EEC data set. Compared to state-of-the-art models, our classification results show significant improvement. For the segmentation task, the model attained a Dice coefficient of 92.73% and an Intersection over Union (IoU) of 91.54%. These findings suggest that the proposed multitask deep learning model can effectively assist endoscopists in evaluating esophageal lesions, thereby alleviating their workload and enhancing diagnostic precision.Keywords
Funding Information
- National Natural Science Foundation of China (82472998, 82473228)
- Henan Provincial Science and Technology Research Project (23ZX007, 242102311082)
- Central Plains Science and Technology Innovation Leading Talents (224200510015)
This publication has 55 references indexed in Scilit:
- Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)Computers in Human Behavior, 2024
- Technological advancements in cancer diagnostics: Improvements and limitationsCancer Reports, 2023
- HSNet: A hybrid semantic network for polyp segmentationComputers in Biology and Medicine, 2022
- FCN-Transformer Feature Fusion for Polyp Segmentation2022
- Application of artificial intelligence using convolutional neural networks in determining the invasion depth of esophageal squamous cell carcinomaEsophagus, 2020
- Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagusEsophagus, 2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physiciansComputerized Medical Imaging and Graphics, 2015
- Esophagus Segmentation by Spatially-Constrained Shape Interpolation2008
- Multitask Learning: A Knowledge-Based Source of Inductive Bias1993