Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies

This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discriminat...

Full description

Saved in:
Bibliographic Details
Main Authors: Villalvazo-Avila, Elias, Lopez-Tiro, Francisco, Rizo, Mariana, El-Beze, Jonathan, Hubert, Jacques, Gonzalez-Mendoza, Miguel, Ochoa-Ruiz, Gilberto, Daul, Christian
Format: Conference Proceeding
Language:English
Subjects:
attention
Biology
CBAM
Convolutional neural networks
Data mining
Deep learning
Endoscopes
Feature extraction
Multi-view
multimodal classification
Training
ureteroscopy
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. This approach is specifically designed to mimic the morpho-constitutional analysis performed in ex-vivo by biologists to visually identify kidney stones by inspecting both views. The addition of attention mechanisms to the backbone improved the results of single-view extraction backbones by 4% on average. Moreover, in comparison to the state-of-the-art, the fusion of the deep features improved the overall results by up to 11% in terms of kidney stone classification accuracy.
ISSN:1945-8452
DOI:10.1109/ISBI53787.2023.10230794