An Interpretable X-ray Style Transfer via Trainable Local Laplacian Filter
This addresses the need for interpretable and reliable style transfer in medical imaging to support radiologists' diagnostic performance, though it is incremental as it builds on existing LLF methods.
The paper tackled the problem of automatically adjusting X-ray images to match radiologists' preferred visual styles by proposing a trainable Local Laplacian Filter method, achieving a Structural Similarity Index of 0.94 compared to a baseline of 0.82.
Radiologists have preferred visual impressions or 'styles' of X-ray images that are manually adjusted to their needs to support their diagnostic performance. In this work, we propose an automatic and interpretable X-ray style transfer by introducing a trainable version of the Local Laplacian Filter (LLF). From the shape of the LLF's optimized remap function, the characteristics of the style transfer can be inferred and reliability of the algorithm can be ensured. Moreover, we enable the LLF to capture complex X-ray style features by replacing the remap function with a Multi-Layer Perceptron (MLP) and adding a trainable normalization layer. We demonstrate the effectiveness of the proposed method by transforming unprocessed mammographic X-ray images into images that match the style of target mammograms and achieve a Structural Similarity Index (SSIM) of 0.94 compared to 0.82 of the baseline LLF style transfer method from Aubry et al.