跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-09AI 評分54

BigCell 生成十億像素級全切片病理影像

BigCell: Generating Gigapixel Whole-Slide Images

AI 導讀

BigCell 提出生成原生十億像素級全切片病理影像的方法,可產生最高 32,768×32,768 像素的連貫影像。模型以 2048×2048 像素訓練,使用超過 120,000 張公開全切片影像;自適應排程令生成速度提升逾 3 倍,品質下降有限。另一個模型根據病理文字報告生成 8k 影像;加入合成樣本後,切片級 few-shot 分類表現較以真實資料訓練的基線最高提升 18%。

正文

Published on Oct 9

Authors:

,

,

,

,

,

,

,

,

,

,

,

Abstract

Whole-slide images (WSIs) are gigapixel-scale digital scans of histopathology tissue and serve as the primary basis for cancer diagnosis. Existing histopathology generative models operate at the patch scale, producing fixed-size tiles of at most 1024times1024 pixels which encompass only a small fraction of the WSI. In contrast, text reports for clinical diagnoses and slide-level diagnostic labels -- the supervision that exists at scale -- operate at the whole-slide level. We present BigCell, the first approach to generate coherent whole-slide histopathology images at native gigapixel resolution. BigCell trains a flow-matching transformer at 2048times2048 pixels on over 120,000 publicly available WSIs spanning multiple organ types. Conditioning on embeddings from pathology foundation models and using an inference-time sliding-window pipeline, BigCell generates coherent images of up to 32,768times32,768 pixels, outperforming prior tile generators on both tile-level and slide-level fidelity metrics. To make gigapixel synthesis practical, we introduce an adaptive scheduling strategy that prioritizes important slide regions, speeding up image generation by over 3\ttimes with minimal quality degradation. Furthermore, we propose the first text-to-image synthesis at 8k resolution by training a separate model that produces dense conditioning grids directly from pathology text reports. We demonstrate that augmenting with synthetic samples improves slide-level few-shot classification performance by up to 18 % over baselines trained on real data.

View arXiv page View PDF Project page Add to collection

Get this paper in your agent:

hf papers read 2610.14261

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

StonyBrook-CVLab/BigCell

Updated about 16 hours ago

•

1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.14261 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.14261 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co