论文标题
Convnext-Backbone Hovernet用于核分割和分类
ConvNeXt-backbone HoVerNet for nuclei segmentation and classification
论文作者
论文摘要
该手稿简要说明了用于参与Conic Challenge 2022的算法。在提供基线后，我们遵循其中的方法，并用Convnext One替换Resnet基线。此外，我们建议首先将RGB空间转换为血久毒素eosin-DAB（HED）空间，然后使用原始图像的山马久氧化物组成来平滑语义上的一个热标签。之后，探索了火车和有效组的核分布，以选择最终测试阶段提交的训练模型的最佳折叠拆分。验证集的结果表明，即使每个阶段的渠道数字较小，与Convnext微型主链的Hovernet仍然可以将MPQ+提高0.04和Multi R2提高0.0144
This manuscript gives a brief description of the algorithm used to participate in CoNIC Challenge 2022. After the baseline was made available, we follow the method in it and replace the ResNet baseline with ConvNeXt one. Moreover, we propose to first convert RGB space to Haematoxylin-Eosin-DAB(HED) space, then use Haematoxylin composition of origin image to smooth semantic one hot label. Afterwards, nuclei distribution of train and valid set are explored to select the best fold split for training model for final test phase submission. Results on validation set shows that even with channel of each stage smaller in number, HoVerNet with ConvNeXt-tiny backbone still improves the mPQ+ by 0.04 and multi r2 by 0.0144
