Xie Yuanpu, Xing Fuyong, Kong Xiangfei, Su Hai, Yang Lin
J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, FL 32611, USA.
Department of Electrical and Computer Engineering, University of Florida, FL 32611, USA.
Med Image Comput Comput Assist Interv. 2015 Oct;9351:358-365. doi: 10.1007/978-3-319-24574-4_43. Epub 2015 Nov 18.
Robust cell detection serves as a critical prerequisite for many biomedical image analysis applications. In this paper, we present a novel convolutional neural network (CNN) based structured regression model, which is shown to be able to handle touching cells, inhomogeneous background noises, and large variations in sizes and shapes. The proposed method only requires a few training images with weak annotations (just one click near the center of the object). Given an input image patch, instead of providing a single class label like many traditional methods, our algorithm will generate the structured outputs (referred to as proximity patches). These proximity patches, which exhibit higher values for pixels near cell centers, will then be gathered from all testing image patches and fused to obtain the final proximity map, where the maximum positions indicate the cell centroids. The algorithm is tested using three data sets representing different image stains and modalities. The comparative experiments demonstrate the superior performance of this novel method over existing state-of-the-art.
强大的细胞检测是许多生物医学图像分析应用的关键前提。在本文中，我们提出了一种基于卷积神经网络（CNN）的新型结构化回归模型，该模型被证明能够处理相互接触的细胞、不均匀的背景噪声以及大小和形状的巨大变化。所提出的方法仅需要少量带有弱注释的训练图像（只需在对象中心附近点击一下）。给定一个输入图像块，我们的算法不会像许多传统方法那样提供单个类别标签，而是会生成结构化输出（称为邻近块）。这些邻近块在细胞中心附近的像素处具有较高的值，然后将从所有测试图像块中收集并融合，以获得最终的邻近图，其中最大值位置表示细胞质心。该算法使用代表不同图像染色和模态的三个数据集进行了测试。对比实验证明了这种新方法相对于现有最先进方法的优越性能。
