Magnification Generalization for Histopathology Image Embedding

Abstract

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.

arXiv commentAccepted for presentation at International Symposium on Biomedical Imaging (ISBI'2021)

References in corpus (6)

• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Domain Generalization via Model-Agnostic Learning of Semantic Features
• Meta-Learning: A Survey
• Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
• Recognizing Magnification Levels in Microscopic Snapshots

Cited by in corpus (1)

• Generalizing Nucleus Recognition Model in Multi-source Images via Pruning