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.

该研究提出了一种名为 C2G-Net 的图像分类管道，旨在利用具有大量类似物体（如生物细胞）的图像的形态特性。C2G-Net 包括两个组成部分：(1) Cell2Grid，一种通过细胞分割并将其排列在网格上的图像压缩算法；(2) DeepLNiNo，一个具有不到 10,000 个可训练参数的 CNN 体系结构，旨在简化模型的可解释性。与在原始图像上训练的传统 CNN 架构相比，C2G-Net 在预测结肠癌复发风险方面的准确率相似，但训练时间缩短了 85％，其模型更易于解释。