Prostate Tissue Texture Feature Extraction for Cancer Recognition in TRUS Images Using Wavelet Decomposition

Li, J.; Mohamed, Samar; Salama, M.M.A.; Freeman, G.H.

doi:10.1007/978-3-540-74260-9_88

Cited by 8 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As another future study, several other texture feature types, such as, features obtained from the segmentation of the histopathology images into chromatin-rich, stromal and unstained regions, wavelet transforms and fractal dimensions will be considered for NNCR and CRCa texture separation (Karacali and Tozeren, 2007;Jafari-Khouzani and Soltanian-Zadeh, 2003;Li et al, 2007;Zhang and Ma, 2007;Shirazi et al, 2000). In addition, the proposed framework will also be applied to several other differential histopathology cases in colorectal or other tissue sections.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Onder¹,

Sarıoğlu²,

Karaçali³

2013

Micron

View full text Add to dashboard Cite

a b s t r a c tQuasi-supervised learning is a statistical learning algorithm that contrasts two datasets by computing estimate for the posterior probability of each sample in either dataset. This method has not been applied to histopathological images before. The purpose of this study is to evaluate the performance of the method to identify colorectal tissues with or without adenocarcinoma. Light microscopic digital images from histopathological sections were obtained from 30 colorectal radical surgery materials including adenocarcinoma and non-neoplastic regions. The texture features were extracted by using local histograms and co-occurrence matrices. The quasi-supervised learning algorithm operates on two datasets, one containing samples of normal tissues labelled only indirectly, and the other containing an unlabeled collection of samples of both normal and cancer tissues. As such, the algorithm eliminates the need for manually labelled samples of normal and cancer tissues for conventional supervised learning and significantly reduces the expert intervention. Several texture feature vector datasets corresponding to different extraction parameters were tested within the proposed framework. The Independent Component Analysis dimensionality reduction approach was also identified as the one improving the labelling performance evaluated in this series. In this series, the proposed method was applied to the dataset of 22,080 vectors with reduced dimensionality 119 from 132. Regions containing cancer tissue could be identified accurately having false and true positive rates up to 19% and 88% respectively without using manually labelled ground-truth datasets in a quasi-supervised strategy. The resulting labelling performances were compared to that of a conventional powerful supervised classifier using manually labelled ground-truth data. The supervised classifier results were calculated as 3.5% and 95% for the same case. The results in this series in comparison with the benchmark classifier, suggest that quasi-supervised image texture labelling may be a useful method in the analysis and classification of pathological slides but further study is required to improve the results.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Onder¹,

Sarıoğlu²,

Karaçali³

2013

Micron

View full text Add to dashboard Cite

show abstract

“…Discrete wavelet transform (DWT) based textural features are used to classify the cancerous cells [13]. DWT is inefficient for providing the phase information.…”

Section: Introductionmentioning

confidence: 99%

Complex wavelet based texture features of cancer cytology images

Niwas

Palanisamy

Sujathan

2010

2010 5th International Conference on Industrial and Information Systems

View full text Add to dashboard Cite

Breast cancer is the most frequently diagnosed cancer and the most common cause of cancer death among women. In developing countries, testing for detection of this cancer involves visual microscopic test of cytology samples such as Fine Needle Aspiration Cytology (FNAC) taken from the patient's breast. The result of analysis on this sample by Cyto-pathologist is crucial for breast cancer patient. The wavelet transform has become an important tool for many biomedical image and signal application, which at the detection and analysis of image features. In this paper, clusters of nucleus in the sub-band images of FNAC samples is investigated after decomposition by means of the Complex Discrete Wavelet Transform (CDWT) and a new method is developed to compute the variability and other nucleus statistical textural features. The experimental data are taken from FNAC samples of benign and malignant cases. The calculated variance parameters and texture features permit the characterization of nucleus clusters variable and distinguish malignant samples from benign in cytological breast fine needle aspirate images. Keywords-Microscopic image, complex wavelet transform, texture analysis, benign and malignant breast cells. I.978-1-4244-6653-5/10/$26.00

show abstract

“…Such techniques include edge and texture-based segmentation [8]- [10], deformable-model-based segmentation [11], [12], and ellipsoid fitting [13], [14]. Among these techniques, one method that has seen increasing success in medical image segmentation and that we will use is the statistical shape model (SSM) based segmentation [15], lately applied to prostate segmentation [8], [9], [16].…”

mentioning

confidence: 99%

A Comparison of US- Versus MR-Based 3-D Prostate Shapes Using Radial Basis Function Interpolation and Statistical Shape Models

Tao

Tavakoli

Sloboda³

et al. 2015

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

This paper presents a comparison of three-dimensional (3-D) segmentations of the prostate, based on two-dimensional (2-D) manually segmented contours, obtained using ultrasound (US) and magnetic resonance (MR) imaging data collected from 40 patients diagnosed with localized prostate cancer and scheduled to receive brachytherapy treatment. The approach we propose here for 3-D prostate segmentation first uses radial basis function interpolation to construct a 3-D point distribution model for each prostate. Next, a modified principal axis transformation is utilized for rigid registration of the US and MR images of the same prostate in preparation for the following shape comparison. Then, statistical shape models are used to capture the segmented 3-D prostate geometries for the subsequent cross-modality comparison. Our study includes not only cross-modality geometric comparisons in terms of prostate volumes and dimensions, but also an investigation of interchangeability of the two imaging modalities in terms of automatic contour segmentation at the pre-implant planning stage of prostate brachytherapy treatment. By developing a new scheme to compare the two imaging modalities in terms of the segmented 3-D shapes, we have taken a first step necessary for building coupled US-MR segmentation strategies for prostate brachytherapy pre-implant planning, which at present is predominantly informed by US images only.

show abstract

Prostate Tissue Texture Feature Extraction for Cancer Recognition in TRUS Images Using Wavelet Decomposition

Cited by 8 publications

References 13 publications

Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Complex wavelet based texture features of cancer cytology images

A Comparison of US- Versus MR-Based 3-D Prostate Shapes Using Radial Basis Function Interpolation and Statistical Shape Models

Contact Info

Product

Resources

About