Bookmark Saya

arXiv Open Access 2025

Multi-Scale Representation of Follicular Lymphoma Pathology Images in a Single Hyperbolic Space

Kei Taguchi Kazumasa Ohara Tatsuya Yokota Hiroaki Miyoshi Noriaki Hashimoto +2 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CV

Penulis (7)

K

Kei Taguchi

K

Kazumasa Ohara

T

Tatsuya Yokota

H

Hiroaki Miyoshi

N

Noriaki Hashimoto

I

Ichiro Takeuchi

H

Hidekata Hontani

Format Sitasi

APA MLA BibTeX
Taguchi, K., Ohara, K., Yokota, T., Miyoshi, H., Hashimoto, N., Takeuchi, I. et al. (2025). Multi-Scale Representation of Follicular Lymphoma Pathology Images in a Single Hyperbolic Space. https://arxiv.org/abs/2506.18523

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓