Efficient and robust cell detection: A structured regression approach
| Autor: | Xiaoshuang Shi, Xiangfei Kong, Hai Su, Yuanpu Xie, Fuyong Xing, Lin Yang |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0301 basic medicine
Computer science Cytological Techniques Uterine Cervical Neoplasms Bone Marrow Cells Breast Neoplasms Health Informatics CAD Residual Sensitivity and Specificity Convolutional neural network Article 030218 nuclear medicine & medical imaging Image (mathematics) Background noise 03 medical and health sciences Deep Learning 0302 clinical medicine Humans Radiology Nuclear Medicine and imaging Computer vision Diagnosis Computer-Assisted Radiological and Ultrasound Technology business.industry Deep learning Reproducibility of Results Centroid Computer Graphics and Computer-Aided Design Regression Neuroendocrine Tumors 030104 developmental biology Female Neural Networks Computer Computer Vision and Pattern Recognition Artificial intelligence business Algorithms |
| Zdroj: | Medical Image Analysis. 44:245-254 |
| ISSN: | 1361-8415 |
| DOI: | 10.1016/j.media.2017.07.003 |
| Popis: | Efficient and robust cell detection serves as a critical prerequisite for many subsequent biomedical image analysis methods and computer-aided diagnosis (CAD). It remains a challenging task due to touching cells, inhomogeneous background noise, and large variations in cell sizes and shapes. In addition, the ever-increasing amount of available datasets and the high resolution of whole-slice scanned images pose a further demand for efficient processing algorithms. In this paper, we present a novel structured regression model based on a proposed fully residual convolutional neural network for efficient cell detection. For each testing image, our model learns to produce a dense proximity map that exhibits higher responses at locations near cell centers. Our method only requires a few training images with weak annotations (just one dot indicating the cell centroids). We have extensively evaluated our method using four different datasets, covering different microscopy staining methods (e.g., H & E or Ki-67 staining) or image acquisition techniques (e.g., bright-filed image or phase contrast). Experimental results demonstrate the superiority of our method over existing state of the art methods in terms of both detection accuracy and running time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect