Subspace-based Domain Adaptation Using Similarity Constraints for Pneumonia Diagnosis within a Small Chest X-ray Image Dataset - Université Toulouse III - Paul Sabatier - Toulouse INP Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Subspace-based Domain Adaptation Using Similarity Constraints for Pneumonia Diagnosis within a Small Chest X-ray Image Dataset

Résumé

Recent advances in deep learning have led to an accurate diagnosis of pneumonia from chest X-ray images. However, these models usually require large labeled training datasets, not always available in practice. Furthermore, combining images from different medical centers does not preserve the accuracy of the results mainly because of differences in image acquisition settings. In this work, we propose an approach aiming to overcome this challenge, consisting of a subspace-based domain adaptation technique to increase pneumonia detection accuracy using a small training dataset. This dataset is augmented with automatically selected images from a large dataset acquired in a different medical center. This is performed by computing a subspace basis of the target domain dataset on which is projected the source dataset to find the most representative images. Augmenting the training set using the proposed method allows achieving an improvement from 90.03% to 96.18% in overall accuracy using the Xception neural network.
Fichier non déposé

Dates et versions

hal-03523366 , version 1 (12-01-2022)

Identifiants

Citer

Karen Sanchez, Carlos Hinojosa, Henry Arguello, Simon Freiss, Nicolas Sans, et al.. Subspace-based Domain Adaptation Using Similarity Constraints for Pneumonia Diagnosis within a Small Chest X-ray Image Dataset. IEEE 18th International Symposium on Biomedical Imaging (ISBI 2021), Apr 2021, Nice, France. pp.1232-1235, ⟨10.1109/ISBI48211.2021.9434173⟩. ⟨hal-03523366⟩
33 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More