StainFuser: Controlling Diffusion for Faster Neural Style Transfer in Multi-Gigapixel Histology Images
This addresses inconsistencies in histology image analysis for medical researchers, though it appears incremental as it builds on existing style transfer and diffusion methods.
The paper tackles stain normalization in multi-gigapixel histology images by proposing StainFuser, a Conditional Latent Diffusion approach that outperforms state-of-the-art methods in image quality and downstream performance on the CoNIC dataset.
Stain normalization algorithms aim to transform the color and intensity characteristics of a source multi-gigapixel histology image to match those of a target image, mitigating inconsistencies in the appearance of stains used to highlight cellular components in the images. We propose a new approach, StainFuser, which treats this problem as a style transfer task using a novel Conditional Latent Diffusion architecture, eliminating the need for handcrafted color components. With this method, we curate SPI-2M the largest stain normalization dataset to date of over 2 million histology images with neural style transfer for high-quality transformations. Trained on this data, StainFuser outperforms current state-of-the-art deep learning and handcrafted methods in terms of the quality of normalized images and in terms of downstream model performance on the CoNIC dataset.