Limits...
Segmental HOG: new descriptor for glomerulus detection in kidney microscopy image.

Kato T, Relator R, Ngouv H, Hirohashi Y, Takaki O, Kakimoto T, Okada K - BMC Bioinformatics (2015)

Bottom Line: Moreover, the novel segmentation technique employed herewith generates high-quality segmentation outputs, and the algorithm is assured to converge to an optimal solution.Consequently, experiments using real-world image data revealed that Segmental HOG achieved significant improvements in detection performance compared to Rectangular HOG.The proposed descriptor for glomeruli detection presents promising results, and it is expected to be useful in pathological evaluation.

View Article: PubMed Central - PubMed

Affiliation: Faculty of Science and Engineering, Gunma University, Kiryu-shi, Gunma, 376-8515, Japan. katotsu@cs.gunma-u.ac.jp.

ABSTRACT

Background: The detection of the glomeruli is a key step in the histopathological evaluation of microscopic images of the kidneys. However, the task of automatic detection of the glomeruli poses challenges owing to the differences in their sizes and shapes in renal sections as well as the extensive variations in their intensities due to heterogeneity in immunohistochemistry staining. Although the rectangular histogram of oriented gradients (Rectangular HOG) is a widely recognized powerful descriptor for general object detection, it shows many false positives owing to the aforementioned difficulties in the context of glomeruli detection.

Results: A new descriptor referred to as Segmental HOG was developed to perform a comprehensive detection of hundreds of glomeruli in images of whole kidney sections. The new descriptor possesses flexible blocks that can be adaptively fitted to input images in order to acquire robustness for the detection of the glomeruli. Moreover, the novel segmentation technique employed herewith generates high-quality segmentation outputs, and the algorithm is assured to converge to an optimal solution. Consequently, experiments using real-world image data revealed that Segmental HOG achieved significant improvements in detection performance compared to Rectangular HOG.

Conclusion: The proposed descriptor for glomeruli detection presents promising results, and it is expected to be useful in pathological evaluation.

No MeSH data available.


Relaxed problems in DCDP. Here, a segmentation problem (1) with (n,m,ς)=(8,12,1) is considered. We use an m-sided polygon to model the boundary of a glomerulus. The vertices are restricted to be on any of the n points lying on the m rays from the center of the glomerulus. The boundary likeliness is computed on each of the n points, and the configuration that maximizes the sum of the boundary likeliness is found, as described in (1). In Panel (a), the sizes of the green circles indicate the quantities of boundary likeliness. As in (1), the feasible configurations of the polygon are restricted to be in , where . Overlapping all feasible configurations yields the gray edges in Panel (a). The optimal polygon is drawn with red edges. DCDP relaxes the feasible region  to get . In Panel (b), the relaxed feasible region  is depicted. The blue polygon is the optimal configuration for the relaxed problem . The proposed algorithm DCDP divides the problem into many sub-problems. The relaxed versions of the four sub-problems with , , , and  are illustrated in Panels (c), (d), (e), and (f). The blue polygons in (c), (d), (e), and (f) are the optimal solutions of the four relaxed problems, respectively. See the main text for details
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4590714&req=5

Fig5: Relaxed problems in DCDP. Here, a segmentation problem (1) with (n,m,ς)=(8,12,1) is considered. We use an m-sided polygon to model the boundary of a glomerulus. The vertices are restricted to be on any of the n points lying on the m rays from the center of the glomerulus. The boundary likeliness is computed on each of the n points, and the configuration that maximizes the sum of the boundary likeliness is found, as described in (1). In Panel (a), the sizes of the green circles indicate the quantities of boundary likeliness. As in (1), the feasible configurations of the polygon are restricted to be in , where . Overlapping all feasible configurations yields the gray edges in Panel (a). The optimal polygon is drawn with red edges. DCDP relaxes the feasible region to get . In Panel (b), the relaxed feasible region is depicted. The blue polygon is the optimal configuration for the relaxed problem . The proposed algorithm DCDP divides the problem into many sub-problems. The relaxed versions of the four sub-problems with , , , and are illustrated in Panels (c), (d), (e), and (f). The blue polygons in (c), (d), (e), and (f) are the optimal solutions of the four relaxed problems, respectively. See the main text for details

Mentions: Adap Split is expected to be the smartest heuristic process among the three splitting schemes. To support this claim, we illustrate the process of DCDP on a small toy problem with (n,m,ς)=(8,12,1), as shown in Fig. 5. The original problem and the relaxed problem are depicted in Fig. 5a and b, respectively. When running , where , it was observed that . Thereby the set is divided into and to produce two new branches and where ℓ1 will be computed via .Fig. 5


Segmental HOG: new descriptor for glomerulus detection in kidney microscopy image.

Kato T, Relator R, Ngouv H, Hirohashi Y, Takaki O, Kakimoto T, Okada K - BMC Bioinformatics (2015)

Relaxed problems in DCDP. Here, a segmentation problem (1) with (n,m,ς)=(8,12,1) is considered. We use an m-sided polygon to model the boundary of a glomerulus. The vertices are restricted to be on any of the n points lying on the m rays from the center of the glomerulus. The boundary likeliness is computed on each of the n points, and the configuration that maximizes the sum of the boundary likeliness is found, as described in (1). In Panel (a), the sizes of the green circles indicate the quantities of boundary likeliness. As in (1), the feasible configurations of the polygon are restricted to be in , where . Overlapping all feasible configurations yields the gray edges in Panel (a). The optimal polygon is drawn with red edges. DCDP relaxes the feasible region  to get . In Panel (b), the relaxed feasible region  is depicted. The blue polygon is the optimal configuration for the relaxed problem . The proposed algorithm DCDP divides the problem into many sub-problems. The relaxed versions of the four sub-problems with , , , and  are illustrated in Panels (c), (d), (e), and (f). The blue polygons in (c), (d), (e), and (f) are the optimal solutions of the four relaxed problems, respectively. See the main text for details
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4590714&req=5

Fig5: Relaxed problems in DCDP. Here, a segmentation problem (1) with (n,m,ς)=(8,12,1) is considered. We use an m-sided polygon to model the boundary of a glomerulus. The vertices are restricted to be on any of the n points lying on the m rays from the center of the glomerulus. The boundary likeliness is computed on each of the n points, and the configuration that maximizes the sum of the boundary likeliness is found, as described in (1). In Panel (a), the sizes of the green circles indicate the quantities of boundary likeliness. As in (1), the feasible configurations of the polygon are restricted to be in , where . Overlapping all feasible configurations yields the gray edges in Panel (a). The optimal polygon is drawn with red edges. DCDP relaxes the feasible region to get . In Panel (b), the relaxed feasible region is depicted. The blue polygon is the optimal configuration for the relaxed problem . The proposed algorithm DCDP divides the problem into many sub-problems. The relaxed versions of the four sub-problems with , , , and are illustrated in Panels (c), (d), (e), and (f). The blue polygons in (c), (d), (e), and (f) are the optimal solutions of the four relaxed problems, respectively. See the main text for details
Mentions: Adap Split is expected to be the smartest heuristic process among the three splitting schemes. To support this claim, we illustrate the process of DCDP on a small toy problem with (n,m,ς)=(8,12,1), as shown in Fig. 5. The original problem and the relaxed problem are depicted in Fig. 5a and b, respectively. When running , where , it was observed that . Thereby the set is divided into and to produce two new branches and where ℓ1 will be computed via .Fig. 5

Bottom Line: Moreover, the novel segmentation technique employed herewith generates high-quality segmentation outputs, and the algorithm is assured to converge to an optimal solution.Consequently, experiments using real-world image data revealed that Segmental HOG achieved significant improvements in detection performance compared to Rectangular HOG.The proposed descriptor for glomeruli detection presents promising results, and it is expected to be useful in pathological evaluation.

View Article: PubMed Central - PubMed

Affiliation: Faculty of Science and Engineering, Gunma University, Kiryu-shi, Gunma, 376-8515, Japan. katotsu@cs.gunma-u.ac.jp.

ABSTRACT

Background: The detection of the glomeruli is a key step in the histopathological evaluation of microscopic images of the kidneys. However, the task of automatic detection of the glomeruli poses challenges owing to the differences in their sizes and shapes in renal sections as well as the extensive variations in their intensities due to heterogeneity in immunohistochemistry staining. Although the rectangular histogram of oriented gradients (Rectangular HOG) is a widely recognized powerful descriptor for general object detection, it shows many false positives owing to the aforementioned difficulties in the context of glomeruli detection.

Results: A new descriptor referred to as Segmental HOG was developed to perform a comprehensive detection of hundreds of glomeruli in images of whole kidney sections. The new descriptor possesses flexible blocks that can be adaptively fitted to input images in order to acquire robustness for the detection of the glomeruli. Moreover, the novel segmentation technique employed herewith generates high-quality segmentation outputs, and the algorithm is assured to converge to an optimal solution. Consequently, experiments using real-world image data revealed that Segmental HOG achieved significant improvements in detection performance compared to Rectangular HOG.

Conclusion: The proposed descriptor for glomeruli detection presents promising results, and it is expected to be useful in pathological evaluation.

No MeSH data available.