FUSION: Fully Unsupervised Test-Time Stain Adaptation via Fused Normalization Statistics
This addresses stain adaptation for histopathology analysis, enabling better diagnosis without requiring labeled target data, though it is incremental as it builds on test-time adaptation techniques.
The paper tackles the problem of stain variation in histopathology slides, which causes distribution shifts and poor model performance, by proposing FUSION, a fully unsupervised test-time adaptation method that adjusts batch normalization statistics; it outperforms existing algorithms on classification and segmentation tasks in experiments on two public datasets.
Staining reveals the micro structure of the aspirate while creating histopathology slides. Stain variation, defined as a chromatic difference between the source and the target, is caused by varying characteristics during staining, resulting in a distribution shift and poor performance on the target. The goal of stain normalization is to match the target's chromatic distribution to that of the source. However, stain normalisation causes the underlying morphology to distort, resulting in an incorrect diagnosis. We propose FUSION, a new method for promoting stain-adaption by adjusting the model to the target in an unsupervised test-time scenario, eliminating the necessity for significant labelling at the target end. FUSION works by altering the target's batch normalization statistics and fusing them with source statistics using a weighting factor. The algorithm reduces to one of two extremes based on the weighting factor. Despite the lack of training or supervision, FUSION surpasses existing equivalent algorithms for classification and dense predictions (segmentation), as demonstrated by comprehensive experiments on two public datasets.