Discriminative ensemble learning for few-shot chest x-ray diagnosis

•We design a two-step solution for few-shot diagnosis of chest x-rays.•Our model is composed of a coarse-learner and a saliency-based classifier.•The saliency-based classifier is designed using a novel discriminative autoencoder ensemble.•We introduce a novel intrinsic weight to be assigned to each...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Medical image analysis Jg. 68; S. 101911
Hauptverfasser: Paul, Angshuman, Tang, Yu-Xing, Shen, Thomas C., Summers, Ronald M.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Netherlands Elsevier B.V 01.02.2021
Elsevier BV
Schlagworte:
Algorithms
Autoencoder
Chest
Classifiers
Diagnosis
Discriminative
Ensemble
Ensemble learning
Feature extraction
Few-shot
Humans
Image analysis
Image processing
Learning
Machine Learning
Medical diagnosis
Medical imaging
Radiography
Salience
Tomography, X-Ray Computed
Training
X-ray
X-Rays
Discriminative
Autoencoder
Few-shot
Ensemble
41A10
65D05
65D17
X-ray
41A05
ISSN:1361-8415, 1361-8423, 1361-8423
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•We design a two-step solution for few-shot diagnosis of chest x-rays.•Our model is composed of a coarse-learner and a saliency-based classifier.•The saliency-based classifier is designed using a novel discriminative autoencoder ensemble.•We introduce a novel intrinsic weight to be assigned to each autoencoder for weighted voting during inference.•Our method can be trained with one dataset and can still be effectively applied to similar datasets from different sources. [Display omitted] Few-shot learning is an almost unexplored area in the field of medical image analysis. We propose a method for few-shot diagnosis of diseases and conditions from chest x-rays using discriminative ensemble learning. Our design involves a CNN-based coarse-learner in the first step to learn the general characteristics of chest x-rays. In the second step, we introduce a saliency-based classifier to extract disease-specific salient features from the output of the coarse-learner and classify based on the salient features. We propose a novel discriminative autoencoder ensemble to design the saliency-based classifier. The classification of the diseases is performed based on the salient features. Our algorithm proceeds through meta-training and meta-testing. During the training phase of meta-training, we train the coarse-learner. However, during the training phase of meta-testing, we train only the saliency-based classifier. Thus, our method is first-of-its-kind where the training phase of meta-training and the training phase of meta-testing are architecturally disjoint, making the method modular and easily adaptable to new tasks requiring the training of only the saliency-based classifier. Experiments show as high as ∼19% improvement in terms of F1 score compared to the baseline in the diagnosis of chest x-rays from publicly available datasets.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Angshuman Paul: Conceptualization; Data curation; Formal analysis; Investigation; Methodology; Resources; Software; Validation; Visualization; Writing - original draft; Writing - review & editing.
Thomas C. Shen: Data curation; Resources; Writing - original draft; Writing - review & editing.
Yu-Xing Tang: Data curation; Formal analysis; Resources; Software; Visualization; Writing - original draft; Writing - review & editing.
Ronald M. Summers: Conceptualization; Data curation; Formal analysis; Funding acquisition; Investigation; Methodology; Project administration; Resources; Supervision; Visualization; Writing - original draft; Writing - review & editing.
ISSN:1361-8415
1361-8423
1361-8423
DOI:10.1016/j.media.2020.101911