论文标题
C2G-NET：用于图像分类的形态学特性
C2G-Net: Exploiting Morphological Properties for Image Classification
论文作者
论文摘要
在本文中，我们提出了C2G-NET，这是图像分类的管道，利用包含大量相似物体（例如生物细胞）的图像的形态特性。 C2G-NET由两个组件组成：（1）Cell2Grid，一种图像压缩算法，使用分割识别对象并将它们排列在网格上，并且（2）DeepLnino，一种CNN架构，具有少于10,000个可训练参数的CNN体系结构，旨在促进模型的模型。为了测试C2G-NET的性能，我们使用了多重免疫组织化学图像来预测结肠癌的复发风险。与经过原始图像训练的常规CNN体系结构相比，C2G-NET达到了相似的预测准确性，而训练时间则减少了85％，并且其模型更易于解释。
In this paper we propose C2G-Net, a pipeline for image classification that exploits the morphological properties of images containing a large number of similar objects like biological cells. C2G-Net consists of two components: (1) Cell2Grid, an image compression algorithm that identifies objects using segmentation and arranges them on a grid, and (2) DeepLNiNo, a CNN architecture with less than 10,000 trainable parameters aimed at facilitating model interpretability. To test the performance of C2G-Net we used multiplex immunohistochemistry images for predicting relapse risk in colon cancer. Compared to conventional CNN architectures trained on raw images, C2G-Net achieved similar prediction accuracy while training time was reduced by 85% and its model was is easier to interpret.
