Magnification Generalization for Histopathology Image Embedding
This addresses a useful task in histopathology embedding for medical imaging, but it is incremental as it applies an existing domain generalization method to a new problem.
The paper tackles the problem of training histopathology image embeddings that generalize across magnification levels, using a domain generalization technique called MASF based on MAML, and demonstrates its effectiveness on a breast cancer dataset with four magnification levels.
Histopathology image embedding is an active research area in computer vision. Most of the embedding models exclusively concentrate on a specific magnification level. However, a useful task in histopathology embedding is to train an embedding space regardless of the magnification level. Two main approaches for tackling this goal are domain adaptation and domain generalization, where the target magnification levels may or may not be introduced to the model in training, respectively. Although magnification adaptation is a well-studied topic in the literature, this paper, to the best of our knowledge, is the first work on magnification generalization for histopathology image embedding. We use an episodic trainable domain generalization technique for magnification generalization, namely Model Agnostic Learning of Semantic Features (MASF), which works based on the Model Agnostic Meta-Learning (MAML) concept. Our experimental results on a breast cancer histopathology dataset with four different magnification levels show the proposed method's effectiveness for magnification generalization.