Ultrasound Image Classification using ACGAN with Small Training Dataset

TL;DR

This paper proposes using ACGAN to improve ultrasound image classification with small datasets by combining data augmentation and transfer learning, demonstrated on breast ultrasound images.

Contribution

Introducing an ACGAN-based method to enhance ultrasound image classification with limited data, integrating data augmentation and transfer learning.

Findings

ACGAN effectively generates realistic ultrasound images.

Improved classification accuracy with small datasets.

Demonstrated on breast ultrasound images.

Abstract

B-mode ultrasound imaging is a popular medical imaging technique. Like other image processing tasks, deep learning has been used for analysis of B-mode ultrasound images in the last few years. However, training deep learning models requires large labeled datasets, which is often unavailable for ultrasound images. The lack of large labeled data is a bottleneck for the use of deep learning in ultrasound image analysis. To overcome this challenge, in this work we exploit Auxiliary Classifier Generative Adversarial Network (ACGAN) that combines the benefits of data augmentation and transfer learning in the same framework. We conduct experiment on a dataset of breast ultrasound images that shows the effectiveness of the proposed approach.