Robust Cell Detection and Segmentation in Histopathological Images Using Sparse Reconstruction and Stacked Denoising Aut
Computer-aided diagnosis (CAD) is a promising tool for accurate and consistent diagnosis and prognosis. Cell detection and segmentation are essential steps for CAD. These tasks are challenging due to variations in cell shapes, touching cells, and cluttere
- PDF / 1,451,850 Bytes
- 8 Pages / 439.363 x 666.131 pts Page_size
- 16 Downloads / 182 Views
J. Crayton Pruitt Family Dept. of Biomedical Engineering, University of Florida, FL 32611 2 Department of Electrical and Computer Engineering, University of Florida, FL 32611 3 Department of Computer Science, University of North Carolina at Charlotte, NC 28223
Abstract. Computer-aided diagnosis (CAD) is a promising tool for accurate and consistent diagnosis and prognosis. Cell detection and segmentation are essential steps for CAD. These tasks are challenging due to variations in cell shapes, touching cells, and cluttered background. In this paper, we present a cell detection and segmentation algorithm using the sparse reconstruction with trivial templates and a stacked denoising autoencoder (sDAE). The sparse reconstruction handles the shape variations by representing a testing patch as a linear combination of shapes in the learned dictionary. Trivial templates are used to model the touching parts. The sDAE, trained with the original data and their structured labels, is used for cell segmentation. To the best of our knowledge, this is the first study to apply sparse reconstruction and sDAE with structured labels for cell detection and segmentation. The proposed method is extensively tested on two data sets containing more than 3000 cells obtained from brain tumor and lung cancer images. Our algorithm achieves the best performance compared with other state of the arts.
1
Introduction
Reproducible and accurate analysis of digitized histopathological specimens plays a critical role in successful diagnosis and prognosis, treatment outcome prediction, and therapy planning. Manual analysis of histopathological slides is not only laborious, but also subject to inter-observer variability. Computer-aided diagnosis (CAD) is a promising solution. In CAD, cell detection and segmentation are often prerequisite steps for critical morphological analysis [10,16]. The major challenges in cell detection and segmentation are: 1) large variations of cell shapes and inhomogeneous intensity, 2) touching cells, and 3) background clutters. In order to handle touching cells, radial voting based detection c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part III, LNCS 9351, pp. 383–390, 2015. DOI: 10.1007/978-3-319-24574-4_46
384
H. Su et al. Cell detection
(c) Similar template patches
(e) The detection result
Trivial templates
(a) A testing image
z
gT '
A sample patch
(b) Representative cell patches
Sparse reconstruction with trivial templates
(d) The probability map
LH ( z, x)
y
gT '
fT
~x
fT
x
Gradient maps
Labels
(i) The segmentation result
(f) A denoising autoencoder trained with structural labels
sDAE Training
Cell Segmentation
(h) The reconstructed cell boundary
(g) The gradient map
Testing
Fig. 1. An overview of the proposed algorithm.
method achieves robust performance with an assumption that most of the cells have round shapes [7]. In [14], an active contour algorithm is applied for cell segmentation. Recently, shape prior model is proposed to improve th
Data Loading...
