Histopathology serves as the gold standard for medical diagnosis but faces application limitations due to the shortage of medical resources. Leveraging deep learning, computer-aided diagnosis has the potential to alleviate the pathologist scarcity and provide timely clinical analysis. However, developing a reliable model generally necessitates substantial data for training, which is challenging in pathological field. In response, we propose an adaptive depth-controlled bidirectional diffusion (ADBD) network for image data generation. The domain migration approach can work with small trainset and overcome the diffusion overfitting by source information guidance. Specifically, we developed a hybrid attention strategy to blend global and local attention priorities, which guides the bidirectional diffusion and ensures the migration success. In addition, we developed the adaptive depth-controlled strategy to simulate physiological transformations, capable of yielding unlimited cross-domain intermediate images with corresponding soft labels. ADBD is effective for overcoming pathological image data deficiency and supportable for further pathology-related research.

翻译：组织病理学是医学诊断的金标准，但因医疗资源短缺面临应用局限。利用深度学习的计算机辅助诊断有望缓解病理学家人手不足问题，并提供及时的临床分析。然而，开发可靠模型通常需要大量训练数据，这在病理领域颇具挑战。为此，我们提出自适应深度控制双向扩散（ADBD）网络用于图像数据生成。该域迁移方法可通过源信息引导，在小型训练集上工作并克服扩散过拟合。具体而言，我们设计了混合注意力策略来融合全局与局部注意力优先级，以引导双向扩散并确保迁移成功。此外，我们开发了自适应深度控制策略来模拟生理转化过程，能够生成具有相应软标签的无限跨域中间图像。ADBD可有效克服病理图像数据匮乏问题，并支持后续病理相关研究。