Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guan, Xianchao, Fan, Zhiyuan, Wang, Yifeng, Chen, Fuqiang, Zhou, Yanjiang, Che, Zengyang, Meng, Hongxue, Li, Xin, Wang, Yaowei, Wang, Hongpeng, Zhang, Min, Shen, Heng Tao, Zhang, Zheng, Zhang, Yongbing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.13164
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909964514099200
author Guan, Xianchao
Fan, Zhiyuan
Wang, Yifeng
Chen, Fuqiang
Zhou, Yanjiang
Che, Zengyang
Meng, Hongxue
Li, Xin
Wang, Yaowei
Wang, Hongpeng
Zhang, Min
Shen, Heng Tao
Zhang, Zheng
Zhang, Yongbing
author_facet Guan, Xianchao
Fan, Zhiyuan
Wang, Yifeng
Chen, Fuqiang
Zhou, Yanjiang
Che, Zengyang
Meng, Hongxue
Li, Xin
Wang, Yaowei
Wang, Hongpeng
Zhang, Min
Shen, Heng Tao
Zhang, Zheng
Zhang, Yongbing
contents The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instability and morphological hallucinations that compromise diagnostic reliability. To address this challenge, we introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS), the first generative foundation model for pathology-specific text-to-image synthesis. By leveraging a dual-stage training strategy on approximately 2.8 million image-caption pairs, CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy. This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations. Furthermore, CRAFTS-augmented datasets enhance the performance across various clinical tasks, including classification, cross-modal retrieval, self-supervised learning, and visual question answering. In addition, coupling CRAFTS with ControlNet enables precise control over tissue architecture from inputs such as nuclear segmentation masks and fluorescence images. By overcoming the critical barriers of data scarcity and privacy concerns, CRAFTS provides a limitless source of diverse, annotated histology data, effectively unlocking the creation of robust diagnostic tools for rare and complex cancer phenotypes.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13164
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis
Guan, Xianchao
Fan, Zhiyuan
Wang, Yifeng
Chen, Fuqiang
Zhou, Yanjiang
Che, Zengyang
Meng, Hongxue
Li, Xin
Wang, Yaowei
Wang, Hongpeng
Zhang, Min
Shen, Heng Tao
Zhang, Zheng
Zhang, Yongbing
Computer Vision and Pattern Recognition
Artificial Intelligence
The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instability and morphological hallucinations that compromise diagnostic reliability. To address this challenge, we introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS), the first generative foundation model for pathology-specific text-to-image synthesis. By leveraging a dual-stage training strategy on approximately 2.8 million image-caption pairs, CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy. This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations. Furthermore, CRAFTS-augmented datasets enhance the performance across various clinical tasks, including classification, cross-modal retrieval, self-supervised learning, and visual question answering. In addition, coupling CRAFTS with ControlNet enables precise control over tissue architecture from inputs such as nuclear segmentation masks and fluorescence images. By overcoming the critical barriers of data scarcity and privacy concerns, CRAFTS provides a limitless source of diverse, annotated histology data, effectively unlocking the creation of robust diagnostic tools for rare and complex cancer phenotypes.
title A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.13164