论文标题
颜色空间悬停网络用于核实例分割和分类
Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification
论文作者
论文摘要
核分割和分类是用于许多不同显微镜医学分析应用的第一个也是最关键的步骤。但是，它遭受了许多问题，例如小物体的分割，不平衡和细胞核类型之间的细粒度差异。在本文中，已经做出了多种不同的贡献解决了这些问题。首先，最近发布的“ convnext”被用作悬停网络模型的编码器，因为它利用了使它们表现良好的变压器的关键组件。其次，为了增强核之间的视觉差异，使用多通道颜色空间的方法来帮助该模型提取区分特征。第三，使用统一的局灶性损失（UFL）来解决背景前景不平衡。最后，使用清晰度最小化（SAM）来确保模型的普遍性。总体而言，我们能够在2022年Conic Challenge挑战的初步测试集上胜过当前最新的（SOTA），悬停网络。
Nuclei segmentation and classification is the first and most crucial step that is utilized for many different microscopy medical analysis applications. However, it suffers from many issues such as the segmentation of small objects, imbalance, and fine-grained differences between types of nuclei. In this paper, multiple different contributions were done tackling these problems present. Firstly, the recently released "ConvNeXt" was used as the encoder for HoVer-Net model since it leverages the key components of transformers that make them perform well. Secondly, to enhance the visual differences between nuclei, a multi-channel color space-based approach is used to aid the model in extracting distinguishing features. Thirdly, Unified Focal loss (UFL) was used to tackle the background-foreground imbalance. Finally, Sharpness-Aware Minimization (SAM) was used to ensure generalizability of the model. Overall, we were able to outperform the current state-of-the-art (SOTA), HoVer-Net, on the preliminary test set of the CoNiC Challenge 2022 by 12.489% mPQ+.
