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：我们提出了“HoVer-UNet”，一种用于组织病理学中细胞核实例分割与分类的多分支HoVerNet框架知识蒸馏方法。我们设计了一个紧凑、精简的单一UNet网络，以Mix Vision Transformer为主干，并为其配备了自定义损失函数，以优化编码HoVerNet的蒸馏知识，从而在保持性能的同时降低计算需求。实验表明，我们的模型在公共PanNuke和Consep数据集上取得了与HoVerNet相当的结果，同时推理时间减少了三倍。我们已在https://github.com/DIAGNijmegen/HoVer-UNet上公开提供模型代码。