The paper presents a novel convolutional neural network, HoVer-Net, for simultaneous nuclear segmentation and classification in multi-tissue histology images. The network leverages the vertical and horizontal distances of nuclear pixels to their centers of mass to separate clustered nuclei, improving segmentation accuracy, especially in areas with overlapping instances. Each segmented instance is then classified using a dedicated up-sampling branch. The authors introduce a new dataset, CoNSeP, containing 24,319 exhaustively annotated nuclei from colorectal adenocarcinoma images. The proposed method achieves state-of-the-art performance on multiple independent multi-tissue histology image datasets, outperforming other methods in terms of instance segmentation and classification. The evaluation metrics used include Panoptic Quality (PQ), Ensemble Dice (DICE2), and Aggregated Jaccard Index (AJI). The study also includes a generalization study to assess the method's performance on new images from different organs and staining centers.The paper presents a novel convolutional neural network, HoVer-Net, for simultaneous nuclear segmentation and classification in multi-tissue histology images. The network leverages the vertical and horizontal distances of nuclear pixels to their centers of mass to separate clustered nuclei, improving segmentation accuracy, especially in areas with overlapping instances. Each segmented instance is then classified using a dedicated up-sampling branch. The authors introduce a new dataset, CoNSeP, containing 24,319 exhaustively annotated nuclei from colorectal adenocarcinoma images. The proposed method achieves state-of-the-art performance on multiple independent multi-tissue histology image datasets, outperforming other methods in terms of instance segmentation and classification. The evaluation metrics used include Panoptic Quality (PQ), Ensemble Dice (DICE2), and Aggregated Jaccard Index (AJI). The study also includes a generalization study to assess the method's performance on new images from different organs and staining centers.