Beyond Classification: Structured Regression for Robust Cell Detection Using Convolutional Neural Network

• DOI: 10.1007/978-3-319-24574-4_43
• Publication Date: 2015-09-24T07:03:02Z
• Authors: Yuanpu Xie; Fuyong Xing; Xiangfei Kong; Hai Su; Lin Yang
• Keywords: 03 medical and health sciences; 0302 clinical medicine; Cytological Techniques; 0202 electrical engineering, electronic engineering, information engineering; Regression Analysis; Reproducibility of Results; Neural Networks, Computer; 02 engineering and technology; Sensitivity and Specificity; Algorithms

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.