We present HoVer-UNet, an approach to distill the knowledge of the multi-branch HoVerNet framework for nuclei instance segmentation and classification in histopathology. We propose a compact, streamlined single UNet network with a Mix Vision Transformer backbone, and equip it with a custom loss function to optimally encode the distilled knowledge of HoVerNet, reducing computational requirements without compromising performances. We show that our model achieved results comparable to HoVerNet on the public PanNuke and Consep datasets with a three-fold reduction in inference time. We make the code of our model publicly available at https://github.com/DIAGNijmegen/HoVer-UNet.

翻译：我们提出HoVer-UNet方法，通过蒸馏多分支HoVerNet框架的知识，实现组织病理学中细胞核实例分割与分类。我们设计了一个紧凑、精简的单一UNet网络，采用Mix Vision Transformer骨干架构，并为其配备定制损失函数以最优方式编码HoVerNet的蒸馏知识，在降低计算需求的同时保持性能不降级。实验表明，我们的模型在公开PanNuke和Consep数据集上取得了与HoVerNet相当的结果，且推理速度提升三倍。模型代码已开源至https://github.com/DIAGNijmegen/HoVer-UNet。