mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography
This addresses the issue of vendor-specific style variations in mammography for improving the universal applicability of deep learning models in computer-aided diagnosis.
The paper tackles the problem of domain gaps in mammography images from different vendors by proposing a multi-resolution and multi-reference neural style transfer network (mr2NST) to normalize styles to a common baseline, resulting in transferred images with comparable quality to target domain images as measured by NIMA scores and improved lesion detection.
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.