Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Image Classification in Small and Unbalanced Datasets through Synthetic Data Augmentation

Neil De La Fuente, Mireia Majó, Irina Luzko, Henry Córdova, Gloria Fernández-Esparrach, Jorge Bernal

TL;DR

This approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities by generating realistic, varied synthetic data that fills feature space gaps to address issues of data scarcity and class imbalance.

Abstract

Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision.

Enhancing Image Classification in Small and Unbalanced Datasets through Synthetic Data Augmentation

TL;DR

This approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities by generating realistic, varied synthetic data that fills feature space gaps to address issues of data scarcity and class imbalance.

Abstract

Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision.
Paper Structure (10 sections, 2 equations, 4 figures, 1 table)

This paper contains 10 sections, 2 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Experimental Setup
  5. Dataset
  6. Metrics
  7. Implementation Details
  8. Results
  9. Conclusions and Future Work
  10. Disclosure of Interests.

Figures (4)

  • Figure 1: The encoding and decoding process in VAEs for synthetic image generation via latent vector interpolation.
  • Figure 2: Sample image for each of the classes, labelled according to Barcelona scale.
  • Figure 3: Comparison of Class 1 Accuracy Across Different Augmentation Techniques and Classifiers. Improvement points are with respect to the Real No Augmentation bar for each model.
  • Figure 4: Expansion of feature space for each EGD image class post-augmentation. X and Y axes represent PCA features 1 and 2 respectively.