Automated Gland Segmentation and Classification for Gleason Grading of Prostate Tissue Images

Nguyen, Kien; Jain, Anil K.; Allen, Ronald L.

doi:10.1109/icpr.2010.370

Cited by 54 publications

(38 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In reference to the results reported in the literature, it is worthy to note the recent contributions by Doyle et al [57], by Huang et al [61], by Khurd, et al [63], and by Nguyen et al [64]. were shown to have nearly the same energy regardless the shift of the input signal.…”

Section: Discussionmentioning

confidence: 88%

Multiridgelets for texture analysis

Yoon

2009

SPIE Proceedings

View full text Add to dashboard Cite

iv Directional wavelets have orientation selectivity and thus are able to efficiently represent highly anisotropic elements such as line segments and edges. Ridgelet transform is a kind of directional multi-resolution transform and has been successful in many image processing and texture analysis applications. The objective of this research is to develop multi-ridgelet transform by applying multiwavelet transform to the Radon transform so as to attain attractive improvements.By adapting the cardinal orthogonal multiwavelets to the ridgelet transform, it is shown that the proposed cardinal multiridgelet transform (CMRT) possesses cardinality, approximate translation invariance, and approximate rotation invariance simultaneously, whereas no single ridgelet transform can hold all these properties at the same time. These properties are beneficial to image texture analysis. This is demonstrated in three studies of texture analysis applications.Firstly a texture database retrieval study taking a portion of the Brodatz texture album as an example has demonstrated that the CMRT-based texture representation for database retrieval performed better than other directional wavelet methods. Secondly the study of the LCD mura defect detection was based upon the classification of simulated abnormalities with a linear support vector machine classifier, the CMRT-based analysis of defects were shown to provide efficient features for superior detection performance than other competitive methods. Lastly and the most importantly, a study on the prostate cancer tissue image classification was conducted.With the CMRT-based texture extraction, Gaussian kernel support vector machines have been The wavelet coefficients of a signal x(n), (a) signal x(n)=δ(n-60), (b) signal x(n)=δ(n-64), (c) real coefficients of (a) using Daubechies-5 discrete wavelet transform, (d) real coefficients of (b) using Daubechies-5 discrete wavelet transform, (e) magnitude of complex coefficients of (a) using the cardinal multiwavelet transform, (f) magnitude of complex coefficients of ( MULTIRIDGELETS FOR TEXTURE ANALYSIS

show abstract

Section: Discussionmentioning

confidence: 88%

Multiridgelets for texture analysis

Yoon

2009

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…All the experiments are conducted on a 2.8 GHz Intel Core i7 machine with 16GB RAM. [12] 0.43 ± 0.12 0.59 ± 0.12 0.39 ± 0.14 0.52 ± 0.15 Naik et al [13] 0.57 ± 0.14 0.72 ± 0.12 0.43 ± 0.14 0.56 ± 0.14 Nguyen et al [14] 0.52 ± 0.12 0.67 ± 0.12 0.35 ± 0.09 0.46 ± 0.09 TGPM 0.78 ± 0.07 0.87 ± 0.05 0.68 ± 0.12 0.77 ± 0.11 RPM 0.82 ± 0.07 0.90 ± 0.05 0.78 ± 0.10 0.85 ± 0.08 a The result is excerpted from [15]. NA means not available.…”

Section: F Comparative Resultsmentioning

confidence: 99%

“…An evident limitation of the framework is that level sets often lead to erroneous segmentation in cases where lumen appears as a complex texture rather than a relatively smooth region such as healthy and adenomatous colon tissues. Nguyen et al [14] employed the prior knowledge about glandular constituents in order to extract glandular regions. Their algorithm first jointly segments nuclei and cytoplasm to form a rough glandular boundary and then uses a region growing algorithm to expand the luminal area.…”

Section: Related Workmentioning

confidence: 99%

“…To compare the performance of the RPM framework against others gland segmentation approaches proposed in the literature, we implemented the methods by Farjam et al [12], Naik et al, Nguyen et al [14], as well as the RPM in Matlab. We did not implement the approach by GunduzDemir et al [15], but carefully followed the protocol given by the authors in order to make a fair comparison for the Bilkent dataset.…”

Section: B Comparative Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

A Stochastic Polygons Model for Glandular Structures in Colon Histology Images

Sirinukunwattana

Snead

Rajpoot

2015

IEEE Trans. Med. Imaging

231

139

View full text Add to dashboard Cite

“…Gland labeling/segmentation, as one subproblem of gland instance segmentation, is a well-studied field where various methods have been explored, such as morphology-based methods [6], [7], [8], [9] and graph-based methods [10], [11]. However, glands must be recognized individually to enable the following morphology analysis.…”

mentioning

confidence: 99%

Gland Instance Segmentation Using Deep Multichannel Neural Networks

Xu,

Li,

Wang

et al. 2017

IEEE Trans. Biomed. Eng.

136

View full text Add to dashboard Cite

Abstract-Objective: A new image instance segmentation method is proposed to segment individual glands (instances) in colon histology images. This process is challenging since the glands not only need to be segmented from a complex background, they must also be individually identified. Methods: We leverage the idea of image-to-image prediction in recent deep learning by designing an algorithm that automatically exploits and fuses complex multichannel information -regional, location and boundary cues -in gland histology images. Our proposed algorithm, a deep multichannel framework, alleviates heavy feature design due to the use of convolutional neural networks and is able to meet multifarious requirements by altering channels. Results: Compared to methods reported in the 2015 MICCAI Gland Segmentation Challenge and other currently prevalent instance segmentation methods, we observe state-ofthe-art results based on the evaluation metrics. Conclusion: The proposed deep multichannel algorithm is an effective method for gland instance segmentation. Significance: The generalization ability of our model not only enable the algorithm to solve gland instance segmentation problems, but the channel is also alternative that can be replaced for a specific task.

show abstract

Automated Gland Segmentation and Classification for Gleason Grading of Prostate Tissue Images

Cited by 54 publications

References 6 publications

Multiridgelets for texture analysis

Multiridgelets for texture analysis

A Stochastic Polygons Model for Glandular Structures in Colon Histology Images

Gland Instance Segmentation Using Deep Multichannel Neural Networks

Contact Info

Product

Resources

About