URCDM: Ultra-Resolution Image Synthesis in Histopathology

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cechnicka, Sarah, Ball, James, Baugh, Matthew, Reynaud, Hadrien, Simmonds, Naomi, Smith, Andrew P. T., Horsfield, Catherine, Roufosse, Candice, Kainz, Bernhard
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913435218870272
author Cechnicka, Sarah
Ball, James
Baugh, Matthew
Reynaud, Hadrien
Simmonds, Naomi
Smith, Andrew P. T.
Horsfield, Catherine
Roufosse, Candice
Kainz, Bernhard
author_facet Cechnicka, Sarah
Ball, James
Baugh, Matthew
Reynaud, Hadrien
Simmonds, Naomi
Smith, Andrew P. T.
Horsfield, Catherine
Roufosse, Candice
Kainz, Bernhard
contents Diagnosing medical conditions from histopathology data requires a thorough analysis across the various resolutions of Whole Slide Images (WSI). However, existing generative methods fail to consistently represent the hierarchical structure of WSIs due to a focus on high-fidelity patches. To tackle this, we propose Ultra-Resolution Cascaded Diffusion Models (URCDMs) which are capable of synthesising entire histopathology images at high resolutions whilst authentically capturing the details of both the underlying anatomy and pathology at all magnification levels. We evaluate our method on three separate datasets, consisting of brain, breast and kidney tissue, and surpass existing state-of-the-art multi-resolution models. Furthermore, an expert evaluation study was conducted, demonstrating that URCDMs consistently generate outputs across various resolutions that trained evaluators cannot distinguish from real images. All code and additional examples can be found on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13277
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle URCDM: Ultra-Resolution Image Synthesis in Histopathology
Cechnicka, Sarah
Ball, James
Baugh, Matthew
Reynaud, Hadrien
Simmonds, Naomi
Smith, Andrew P. T.
Horsfield, Catherine
Roufosse, Candice
Kainz, Bernhard
Image and Video Processing
Computer Vision and Pattern Recognition
Diagnosing medical conditions from histopathology data requires a thorough analysis across the various resolutions of Whole Slide Images (WSI). However, existing generative methods fail to consistently represent the hierarchical structure of WSIs due to a focus on high-fidelity patches. To tackle this, we propose Ultra-Resolution Cascaded Diffusion Models (URCDMs) which are capable of synthesising entire histopathology images at high resolutions whilst authentically capturing the details of both the underlying anatomy and pathology at all magnification levels. We evaluate our method on three separate datasets, consisting of brain, breast and kidney tissue, and surpass existing state-of-the-art multi-resolution models. Furthermore, an expert evaluation study was conducted, demonstrating that URCDMs consistently generate outputs across various resolutions that trained evaluators cannot distinguish from real images. All code and additional examples can be found on GitHub.
title URCDM: Ultra-Resolution Image Synthesis in Histopathology
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13277