mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography

TL;DR

This paper introduces mr2NST, a neural style transfer method that normalizes mammogram images from different vendors to improve diagnostic consistency and aid lesion detection.

Contribution

The study proposes a multi-resolution, multi-reference neural style transfer network specifically designed for mammography images, addressing vendor style variability.

Findings

High-quality style normalization across vendors

Improved lesion detection performance

Comparable image quality to original images

Abstract

Computer-aided diagnosis with deep learning techniques has been shown to be helpful for the diagnosis of the mammography in many clinical studies. However, the image styles of different vendors are very distinctive, and there may exist domain gap among different vendors that could potentially compromise the universal applicability of one deep learning model. In this study, we explicitly address style variety issue with the proposed multi-resolution and multi-reference neural style transfer (mr2NST) network. The mr2NST can normalize the styles from different vendors to the same style baseline with very high resolution. We illustrate that the image quality of the transferred images is comparable to the quality of original images of the target domain (vendor) in terms of NIMA scores. Meanwhile, the mr2NST results are also shown to be helpful for the lesion detection in mammograms.