Scholarlink

<b>Purpose</b> <p>Due to the relative difficulty in acquiring histopathological images, the generated cell morphology often presents a fixed pattern and lacks diversity. To this end, we propose the first diffusion generation model based on point diffusion, which can capture the changes and diversity of cell morphology in more detail.</p> <b>Methods</b> <p>By gradually updating the information of cell morphology during the generation process, we can effectively guide the diffusion model to generate more diverse and realistic cell images. In addition, we introduce a class mask self-attention module to constrain the cell types generated by the diffusion model.</p> <b>Results</b> <p>We conducted experiments on the public dataset Lizard, and comparative analysis with previous image generation methods showed that our method has excellent performance. Compared with the latest NASDM network, our method achieves a 43.17% improvement in FID and a 46.24% enhancement in IS.</p> <b>Conclusions</b> <p>We proposed a first-of-its-kind diffusion model that combines point diffusion and class mask self-attention mechanisms. The model can effectively generate diverse data while maintaining the high quality of generated images and performs well.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Cell generation with label evolution diffusion and class mask self-attention

  • 期刊论文

  • 发表日期：

    2025年6月6日

查看全文
  • Wen Jing,
  • Zixiang Jin,
  • Yi Zhang,
  • Guoxia Xu,
  • Meng Zhao

摘要

Purpose

Due to the relative difficulty in acquiring histopathological images, the generated cell morphology often presents a fixed pattern and lacks diversity. To this end, we propose the first diffusion generation model based on point diffusion, which can capture the changes and diversity of cell morphology in more detail.

Methods

By gradually updating the information of cell morphology during the generation process, we can effectively guide the diffusion model to generate more diverse and realistic cell images. In addition, we introduce a class mask self-attention module to constrain the cell types generated by the diffusion model.

Results

We conducted experiments on the public dataset Lizard, and comparative analysis with previous image generation methods showed that our method has excellent performance. Compared with the latest NASDM network, our method achieves a 43.17% improvement in FID and a 46.24% enhancement in IS.

Conclusions

We proposed a first-of-its-kind diffusion model that combines point diffusion and class mask self-attention mechanisms. The model can effectively generate diverse data while maintaining the high quality of generated images and performs well.