A Novel Breast Ultrasound Image Augmentation Method Using Advanced Neural Style Transfer: An Efficient and Explainable Approach

TL;DR

This paper introduces an efficient, explainable neural style transfer-based data augmentation method for breast ultrasound images, improving deep learning diagnosis accuracy while addressing data scarcity and computational challenges.

Contribution

The study presents a novel GPU-accelerated neural style transfer augmentation technique with explainability, enhancing breast ultrasound image datasets for better deep learning performance.

Findings

Achieved 92.47% accuracy in breast ultrasound image classification.

Scaled training across 8 GPUs with a 5.09x speedup using Horovod.

Demonstrated improved augmentation effectiveness over existing methods.

Abstract

Clinical diagnosis of breast malignancy (BM) is a challenging problem in the recent era. In particular, Deep learning (DL) models have continued to offer important solutions for early BM diagnosis but their performance experiences overfitting due to the limited volume of breast ultrasound (BUS) image data. Further, large BUS datasets are difficult to manage due to privacy and legal concerns. Hence, image augmentation is a necessary and challenging step to improve the performance of the DL models. However, the current DL-based augmentation models are inadequate and operate as a black box resulting lack of information and justifications about their suitability and efficacy. Additionally, pre and post-augmentation need high-performance computational resources and time to produce the augmented image and evaluate the model performance. Thus, this study aims to develop a novel efficient augmentation approach for BUS images with advanced neural style transfer (NST) and Explainable AI (XAI) harnessing GPU-based parallel infrastructure. We scale and distribute the training of the augmentation model across 8 GPUs using the Horovod framework on a DGX cluster, achieving a 5.09 speedup while maintaining the model's accuracy. The proposed model is evaluated on 800 (348 benign and 452 malignant) BUS images and its performance is analyzed with other progressive techniques, using different quantitative analyses. The result indicates that the proposed approach can successfully augment the BUS images with 92.47% accuracy.