Back to Search Start Over

A data-efficient visual analytics method for human-centered diagnostic systems to endoscopic ultrasonography.

Authors :
Zheng, Hangbin
Bao, Jinsong
Dong, Zhixia
Wan, Xinjian
Source :
Applied Intelligence; Dec2023, Vol. 53 Issue 24, p30822-30842, 21p
Publication Year :
2023

Abstract

Endoscopic ultrasound (EUS) has emerged as a pivotal tool for the screening and diagnosis of submucosal tumors (SMTs). However, the inherently low-quality and highly variable image content presents substantial obstacles to the automation of SMT diagnosis. Deep learning, with its adaptive feature extraction capabilities, offers a potential solution, yet its implementation often requires a vast quantity of high-quality data - a challenging prerequisite in clinical settings. To address this conundrum, this paper proposes a novel data-efficient visual analytics method that integrates human feedback into the model lifecycle, thereby augmenting the practical utility of data. The methodology leverages a two-stage deep learning algorithm, which encompasses self-supervised pre-training and an attention-based network. Comprehensive experimental validation reveals that the proposed approach facilitates the model in deciphering the hierarchical structure information within high-noise EUS images. Moreover, when allied with human-machine interaction, it enhances data utilization, thereby elevating the accuracy and reliability of diagnostic outcomes. The code is available at https://github.com/Zehebi29/LA-RANet.git. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
0924669X
Volume :
53
Issue :
24
Database :
Complementary Index
Journal :
Applied Intelligence
Publication Type :
Academic Journal
Accession number :
174495931
Full Text :
https://doi.org/10.1007/s10489-023-05088-0