Abstract:Abstract-In this paper, we propose a new model for active contours to detect objects in a given image, based on techniques of curve evolution, Mumford-Shah functional for segmentation and level sets. Our model can detect objects whose boundaries are not necessarily defined by gradient. We minimize an energy which can be seen as a particular case of the minimal partition problem. In the level set formulation, the problem becomes a "mean-curvature flow"-like evolving the active contour, which will stop on the de… Show more
“…Several methods based on morphological filters and watershed algorithm were proposed to detect cells or cell nuclei in fluorescence images [28][29][30][31][32]. The active contour models [33][34][35][36][37][38][39][40][41][42][43] became popular for automatic cell/nuclei segmentation at the beginning of this century when the classical CV model [33] was proposed. THG images, with Raman and other nonlinear microscopy images, differ from labeled-fluorescence images in their complexity, inherent to their high information density [5,6,20,21,24,25,[44][45][46][47]62].…”
Third harmonic generation (THG) microscopy is a label-free imaging technique that shows great potential for rapid pathology of brain tissue during brain tumor surgery. However, the interpretation of THG brain images should be quantitatively linked to images of more standard imaging techniques, which so far has been done qualitatively only. We establish here such a quantitative link between THG images of mouse brain tissue and all-nuclei-highlighted fluorescence images, acquired simultaneously from the same tissue area. For quantitative comparison of a substantial pair of images, we present here a segmentation workflow that is applicable for both THG and fluorescence images, with a precision of 91.3 % and 95.8 % achieved respectively. We find that the correspondence between the main features of the two imaging modalities amounts to 88.9 %, providing quantitative evidence of the interpretation of dark holes as brain cells. Moreover, 80 % bright objects in THG images overlap with nuclei highlighted in the fluorescence images, and they are 2 times smaller than the dark holes, showing that cells of different morphologies can be recognized in THG images. We expect that the described quantitative comparison is applicable to other types of brain tissue and with more specific staining experiments for cell type identification.
“…Several methods based on morphological filters and watershed algorithm were proposed to detect cells or cell nuclei in fluorescence images [28][29][30][31][32]. The active contour models [33][34][35][36][37][38][39][40][41][42][43] became popular for automatic cell/nuclei segmentation at the beginning of this century when the classical CV model [33] was proposed. THG images, with Raman and other nonlinear microscopy images, differ from labeled-fluorescence images in their complexity, inherent to their high information density [5,6,20,21,24,25,[44][45][46][47]62].…”
Third harmonic generation (THG) microscopy is a label-free imaging technique that shows great potential for rapid pathology of brain tissue during brain tumor surgery. However, the interpretation of THG brain images should be quantitatively linked to images of more standard imaging techniques, which so far has been done qualitatively only. We establish here such a quantitative link between THG images of mouse brain tissue and all-nuclei-highlighted fluorescence images, acquired simultaneously from the same tissue area. For quantitative comparison of a substantial pair of images, we present here a segmentation workflow that is applicable for both THG and fluorescence images, with a precision of 91.3 % and 95.8 % achieved respectively. We find that the correspondence between the main features of the two imaging modalities amounts to 88.9 %, providing quantitative evidence of the interpretation of dark holes as brain cells. Moreover, 80 % bright objects in THG images overlap with nuclei highlighted in the fluorescence images, and they are 2 times smaller than the dark holes, showing that cells of different morphologies can be recognized in THG images. We expect that the described quantitative comparison is applicable to other types of brain tissue and with more specific staining experiments for cell type identification.
“…10 and 11. Related level set based active contours are, in particular, edge based geodesic active contours (12,13) and region based active contours, as introduced by Chan and Vese (14) and Paragios and Deriche (15).…”
Section: Segmentation Methodsmentioning
confidence: 99%
“…H0(/) is the derivative of a smoothed version of the Heaviside function (14). After 200 iterations with s 5 0.5, one obtains the sought contour separating the muscle fibers from the connective tissue (see Fig.…”
Background: Measurement of muscle fiber size and determination of size distribution is important in the assessment of neuromuscular disease. Fiber size estimation by simple inspection is inaccurate and subjective. Manual segmentation and measurement are time-consuming and tedious. We therefore propose an automated image analysis method for objective, reproducible, and time-saving measurement of muscle fibers in routinely hematoxylineosin stained cryostat sections. Methods: The proposed segmentation technique makes use of recent advances in level set based segmentation, where classical edge based active contours are extended by region based cues, such as color and texture. Segmentation and measurement are performed fully automatically. Multiple morphometric parameters, i.e., cross sectional area, lesser diameter, and perimeter are assessed in a single pass.
“…The proposed method itself is applicable to all kinds of active contour regardless of its force balance formulation, but the group size is a parameter that needs to be adjusted when the formulation or numerical implementation of active contour is changed because the extent of fluctuation of the contour at the desired boundary is changed. Although the proposed metric shows good potential to be applied to other variations of active contours (e.g., geodesic active contours [6], the balloons [22], and region-based active contours [23]), its comparative performance (compared with other metrics) in those applications remains to be studied. This paper only compares the termination methods using 2D active contour, not active surface in 3D.…”
Section: Limitations Of the Studymentioning
confidence: 99%
“…Geodesic active contour uses level set methods to find the locations of final contours. It is more suitable for segmentation of multiple structures in an image due to its robustness in merging and splitting the contours during evolution [6]. For both types of active contours, terminating the contour evolution in a fast and accurate manner has been a challenge that requires further research attention.…”
This paper presents a termination criterion for active contour that does not involve alteration of the energy functional. The criterion is based on the area difference of the contour during evolution. In this criterion, the evolution of the contour terminates when the area difference fluctuates around a constant. The termination criterion is tested using parametric gradient vector flow active contour with contour resampling and normal force selection. The usefulness of the criterion is shown through its trend, speed, accuracy, shape insensitivity, and insensitivity to contour resampling. The metric used in the proposed criterion demonstrated a steadily decreasing trend. For automatic implementation in which different shapes need to be segmented, the proposed criterion demonstrated almost 50% and 60% total time reduction while achieving similar accuracy as compared with the pixel movement-based method in the segmentation of synthetic and real medical images, respectively. Our results also show that the proposed termination criterion is insensitive to shape variation and contour resampling. The criterion also possesses potential to be used for other kinds of snakes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.