Salvato in:
Dettagli Bibliografici
Autori principali: Taguchi, Kei, Ohara, Kazumasa, Yokota, Tatsuya, Miyoshi, Hiroaki, Hashimoto, Noriaki, Takeuchi, Ichiro, Hontani, Hidekata
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.18523
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911019027136512
author Taguchi, Kei
Ohara, Kazumasa
Yokota, Tatsuya
Miyoshi, Hiroaki
Hashimoto, Noriaki
Takeuchi, Ichiro
Hontani, Hidekata
author_facet Taguchi, Kei
Ohara, Kazumasa
Yokota, Tatsuya
Miyoshi, Hiroaki
Hashimoto, Noriaki
Takeuchi, Ichiro
Hontani, Hidekata
contents We propose a method for representing malignant lymphoma pathology images, from high-resolution cell nuclei to low-resolution tissue images, within a single hyperbolic space using self-supervised learning. To capture morphological changes that occur across scales during disease progression, our approach embeds tissue and corresponding nucleus images close to each other based on inclusion relationships. Using the Poincaré ball as the feature space enables effective encoding of this hierarchical structure. The learned representations capture both disease state and cell type variations.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18523
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Scale Representation of Follicular Lymphoma Pathology Images in a Single Hyperbolic Space
Taguchi, Kei
Ohara, Kazumasa
Yokota, Tatsuya
Miyoshi, Hiroaki
Hashimoto, Noriaki
Takeuchi, Ichiro
Hontani, Hidekata
Computer Vision and Pattern Recognition
We propose a method for representing malignant lymphoma pathology images, from high-resolution cell nuclei to low-resolution tissue images, within a single hyperbolic space using self-supervised learning. To capture morphological changes that occur across scales during disease progression, our approach embeds tissue and corresponding nucleus images close to each other based on inclusion relationships. Using the Poincaré ball as the feature space enables effective encoding of this hierarchical structure. The learned representations capture both disease state and cell type variations.
title Multi-Scale Representation of Follicular Lymphoma Pathology Images in a Single Hyperbolic Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.18523