Template-driven segmentation of confocal microscopy images
Introduction
High quality 3D visualization of anatomic structures can facilitate diagnosis, surgical planning, biomedical inspection, structural understanding, etc. The raw data acquired from conventional imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI) and confocal microscopy are sequential 2D images. A volume dataset can be obtained by stacking up these images. Many rendering software packages provide 3D visualization of the volume dataset, but they cannot segment the different anatomic structures. An automatic segmentation process is necessary for practical applications.
Since a volume dataset can be obtained by stacking up sequential parallel 2D images, segmentation of the confocal microscopy images can be performed in 2D or 3D manner. For 3D segmentation, atlas-based and simplex-mesh-based approaches are two of the most popular methods. Atlas-based segmentation methods [1], [2], [3], [4], [5] find the transformation relationship between the atlas and the target data set by linear or nonlinear registration, and then warp a pre-segmented atlas to the target data set to perform segmentation or labeling. Nonlinear registration usually provides better segmentation result than linear registration, but it is very time-consuming and more sensitive to noise. For confocal microscopy images, noise is introduced during the specimen preparation process, such as the procedure of penetration or staining. Some regions of the images are of low contrast and have weak edges, which makes nonlinear local registration less reliable. Simplex-mesh-based methods [6], [7], [8] perform segmentation by capturing the features in the volume data with a closed spline surface. This kind of methods can provide smooth segmentation results in 3D, but cannot preserve sharp-features. In order to overcome this problem, a complex manual procedure for parameter assignment is necessary. When we have to preserve sharp-features, like in the Drosophila mushroom bodies, simplex-mesh-based methods are not favorable.
For 2D segmentation, the methods based on active contour models are the most popular. They are also known as the snake models [9], [10], [11], [12], [13], [14]. Energy-minimizing spline curves are found to capture the image features. When the edges are not connected, these approaches can still provide smooth and closed contours without the requirement of edge-linking. The initial contours affect the converged results of the active contour models, and they should be close to the object boundary to ensure correct convergence. The approach also encounters obstacles while dealing with confocal microscopy images. Some contour segments cannot capture the correct edges in regions of low contrast. Although the converged contours are still smooth curves, the reconstructed surface model of the segmentation result may have rugged surfaces.
This paper presents a specific segmentation algorithm for confocal microscopy images. It segments the confocal scans in 2.5D manner. The atlas-based segmentation with linear registration is adopted to provide a rough segmentation result. After model slicing, the resulting contours are regarded as the initial contours of the active contour models. The converged active contours are locally refined by parametric bicubic surfaces when contour segments are converged in regions of low contrast. The process of contour refinement can alleviate the problem of incorrect convergence. The proposed approach can increase the accuracy of the snake algorithm owing to better initial contours. It can also provide a better segmentation result for smoother surface reconstruction.
Section snippets
Confocal microscopy images and subjects
Fly brains (Canton S strain) served as subjects in this study. The brains were stained with the membrane probe, DiD. The fluorescent signals were recorded by a Carl Zeiss LSM 510 confocal microscope using a C-Apochomat water immersion objective lens. DiD was excited by a HeNe2 laser at a wavelength of 633 nm. The emission was selected by a 650 long-pass filter and quantized with a resolution of 8 bits. The field of view was about 600 μm × 600 μm and was sampled to 1024 × 1024 pixels. The optical
Implementation and experimental results
The performance of the proposed algorithm is measured on a desktop computer with the AMD Athlon™ 64 X2 Dual-Core 3600+ CPU and 1 GB of main memory. We use Microsoft Visual C++ 6.0 to implement the proposed system under the operating system of Microsoft Windows XP Professional. The total computation time, excluding the time required for preparation of template, is about 300 s for typical data size (512 × 512 × 120). Fig. 5(a) shows one slice of the original confocal microscopy images. When we zoom in
Conclusions
For confocal microscopy images, the noise introduced during the specimen preparation process may cause confocal images to be of low contrast in some regions. In this paper, we present a hybrid method that is suitable for segmentation of confocal microscopy images. It is faster than atlas-based methods with non-linear registration. Owing to the better initial contours it is more accurate than traditional snake algorithm. With the contour refinement procedure, the proposed method can also provide
Acknowledgements
This work was supported by the Brain Research Center of the University System of Taiwan and the National Center for High-performance Computing.
References (23)
- et al.
Segmentation of brain 3D MR images using level sets and dense registration
Med. Image Anal.
(2001) - et al.
Automatic 3-D model-based neuroanatomical segmentation
Hum. Brain Mapp.
(1995) - et al.
Segmentation of three-dimensional images using non-rigid registration: methods and validation with application to confocal microscopy images of bee brains
- et al.
Volumetric transformation of brain anatomy
IEEE Trans. Med. Imag.
(1997) - et al.
Automated hippocampal segmentation by regional fluid registration of serial MRI: validation and application in Alzheimer's disease
Neuroimage
(2001) - H. Delingette, Simplex meshes: a general representation for 3D shape reconstruction, Technical Report 2214, INRIA,...
General object reconstruction based on simplex meshes
Int. J. Comput. Vis.
(1999)- et al.
Volumetric medical image segmentation using shape constrained deformable models
- et al.
Snakes: active contour models
Int. J. Comput. Vis.
(1988) - et al.
Segmentation of confocal microscopic image of insect brain
Global minimum for active contour models: a minimal path approach
Int. J. Comput. Vis.
Cited by (8)
Segmentation of center brains and optic lobes in 3D confocal images of adult fruit fly brains
2010, MethodsCitation Excerpt :Xu et al. [10], Pham et al. [11], Shapiro and Stockman [12], and Kolmogorov and Rother [13] provide comprehensive reviews on segmentation using different methods. There are also a few reports on segmenting brain structures for display from microscopy images [14,15]. Nevertheless, these methods do not fit our purpose.
Nanoparticle shapes: Quantification by elongation, convexity and circularity measures
2019, Journal of Electrical EngineeringVisualizing structures in confocal microscopy datasets through clusterization: A case study on bile ducts
2019, Proceedings - IEEE Symposium on Computer-Based Medical SystemsSemi-automated enhanced breast tumor segmentation for CT image
2017, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBSEnhancing the visualization of the microvasculature of extrahepatic bile ducts obtained from confocal microscopy images
2017, Proceedings - 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images, SIBGRAPI 2016