Wavelet-based scaling indices for breast cancer diagnostics

Roberts, Timothy T.; Newell, Mary S.; Auffermann, William F.; Vidaković, Brani

doi:10.1002/sim.7264

Cited by 11 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference 7 discussed the incorporation of tumor shape assessments into estimation of spatial heterogeneity of tumors using fluoro‐deoxyglucose‐PET data. As discussed above, there are differences in data obtained from PET imaging and mammography and those obtained using the MRI or CT technologies, hence, the methods proposed by Roberts et al 6 and O'Sullivan et al 7 may not be directly applicable to analyzing tumor heterogeneity using CT imaging as in the motivating dataset in this article. Reference 8 discussed issues related to measurement error in biomarker data and approaches for taking into account such errors to reduce misclassification of cancer subtypes.…”

Section: Introductionmentioning

confidence: 98%

“…The proposed measure is based on a distance‐dependent mean deviation from a linear intensity gradation. Reference 6 proposed the use of wavelet‐based scaling indices for prediction of breast cancer diagnosis using mammography imaging. Reference 7 discussed the incorporation of tumor shape assessments into estimation of spatial heterogeneity of tumors using fluoro‐deoxyglucose‐PET data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tumor heterogeneity estimation for radiomics in cancer

Eloyan

Yue

Khachatryan

2020

Statistics in Medicine

View full text Add to dashboard Cite

Radiomics is an emerging field of medical image analysis research where quantitative measurements are obtained from radiological images that can be utilized to predict patient outcomes and inform treatment decisions. Cancer patients routinely undergo radiological evaluations when images of various modalities including computed tomography, positron emission tomography, and magnetic resonance images are collected for diagnosis and for evaluation of disease progression. Tumor characteristics, often referred to as measures of tumor heterogeneity, can be computed using these clinical images and used as predictors of disease progression and patient survival. Several approaches for quantifying tumor heterogeneity have been proposed, including intensity histogram‐based measures, shape and volume‐based features, and texture analysis. Taking into account the topology of the tumors we propose a statistical framework for estimating tumor heterogeneity using clustering based on Markov random field theory. We model the voxel intensities using a Gaussian mixture model using a Gibbs prior to incorporate voxel neighborhood information. We propose a novel approach to choosing the number of mixture components. Subsequently, we show that the proposed procedure outperforms the existing approaches when predicting lung cancer survival.

show abstract

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Tumor heterogeneity estimation for radiomics in cancer

Eloyan

Yue

Khachatryan

2020

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…A comparative overview of machine learning approaches in BC diagnostic can be found in Kourou et al (2015). Only recently has scaling information found in background tissue come into consideration (Hamilton et al, 2011;Nicolis et al, 2011;Ramírez-Cobo and Vidakovic, 2013;Jeon et al, 2014;Roberts et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Robust Wavelet-based Assessment of Scaling with Applications

Hamilton¹,

Jeon²,

Cobo³

et al. 2022

Preprint

View full text Add to dashboard Cite

A number of approaches have dealt with statistical assessment of self-similary, and many of those are based on multiscale concepts. Most rely on certain distributional assumptions which are usually violated by real data traces, often characterized by large temporal or spatial mean level shifts, missing values or extreme observations. A novel, robust approach based on Theil-type weighted regression is proposed for estimating selfsimilarity in two-dimensional data (images). The method is compared to two traditional estimation techniques that use wavelet decompositions; ordinary least squares (OLS) and Abry-Veitch bias correcting estimator (AV). As an application, the suitability of the selfsimilarity estimate resulting from the the robust approach is illustrated as a predictive feature in the classification of digitized mammogram images as cancerous or non-cancerous.The diagnostic employed here is based on the properties of image backgrounds, which is typically an unused modality in breast cancer screening. Classification results show nearly 68% accuracy, varying slightly with the choice of wavelet basis, and the range of multiresolution levels used.

show abstract

“…The literature on assessing the scaling exponents is rich and the monograph Doukhan et al (2003) provides a comprehensive overview. Diagnostics of breast cancer based on scaling measures of mammograms obtained with orthogonal wavelet transform (DWT) and linear regression can be found in Nicolis et al (2011) and Roberts et al (2017). For the same task, multifractal spectral tools have been used in Ramírez and Vidakovic (2013), while the complex wavelets have been utilized by Jeon et al (2015).…”

Section: Introductionmentioning

confidence: 99%

Non-decimated 2D Wavelet Spectrum and Its Use in Breast Cancer Diagnostics

Kang¹,

Auffermann²,

Vidaković³

2022

Preprint

View full text Add to dashboard Cite

To improve diagnostic accuracy of breast cancer detection, several researchers have used the wavelet-based tools, which provide additional insight and information for aiding diagnostic decisions. The accuracy of such diagnoses, however, can be improved. This paper introduces a waveletbased technique, non-decimated wavelet transform (NDWT)-based scaling estimation, that improves scaling parameter estimation over the traditional methods. One distinctive feature of NDWT is that it does not decimate wavelet coefficients at multiscale levels resulting in redundant outputs which are used to lower the variance of scaling estimators. Another interesting feature of the proposed methodology is the freedom of dyadic constraints for inputs, typical for standard wavelet-based approaches.To compare the estimation performance of the NDWT method to a conventional orthogonal wavelet transform-based method, we use simulation to estimate the Hurst exponent in two-dimensional fractional Brownian fields.The results of the simulation show that the proposed method improves the

show abstract

Wavelet-based scaling indices for breast cancer diagnostics

Cited by 11 publications

References 22 publications

Tumor heterogeneity estimation for radiomics in cancer

Tumor heterogeneity estimation for radiomics in cancer

Robust Wavelet-based Assessment of Scaling with Applications

Non-decimated 2D Wavelet Spectrum and Its Use in Breast Cancer Diagnostics

Contact Info

Product

Resources

About