Improving cell localization with attention-guided diffusion models

Cell localization plays a crucial role in pathology image analysis and is traditionally accomplished through density map regression. However, the use of broad Gaussian kernels in generating ground truth density maps often leads to susceptibility to background noise, resulting in density loss. Narrowing the Gaussian kernel could alleviate this issue, but current methods struggle with density maps generated using narrow kernels. To address this challenge, the diffusion model presents a viable solution by modeling complex distributions and maintaining stability during density map training. In this work, we explore the use of the diffusion model to recover density maps from fully Gaussian noise and present the first Diffusion model for Cell localization. Additionally, we design an Attention map Guidance mechanism that enables the diffusion model to generate higher-quality samples with a moderate guidance scale. Given the noise present at intermediate steps of the diffusion process, we also incorporate a regression branch to estimate cell counts during training. We conduct extensive experiments on several public datasets to validate the effectiveness of the proposed method. The experimental results demonstrate that the proposed method achieves notable improvements in localization and counting performance across multiple datasets.

Authors

• Wei Liu Amazon AGI
• Chao Xu Zhejiang University
• Ying Yuan
• Wenqi Ye
• Huan Xiong Jilin University Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
• Wenqiao Qiu
• Lili Guo School of Computer Science and Technology, China University of Mining and Technology Mine Digitization Engineering Research Center of Ministry of Education of the People’s Republic of China
• Xinda Li
• Xulong Li
• Ruxiang Xu

Keywords

• Cell localization
• Location map
• Diffusion models