On estimation of bias field in MRI images: polynomial vs Gaussian surface fitting method

Kahali, Sayan; Adhikari, Sudip Kumar; Sing, Jamuna Kanta

doi:10.1002/cem.2825

Cited by 12 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of radiomic features on MRI is also dependent on common sources of acquisition variance between sites, including voxel resolutions, image reconstruction methods, magnetic field strengths, scanner hardware, and sequence parameters (echo times, repetition times, and slice thicknesses), as well as acquisition artifacts, such as bias field, 18 noise, 19 and intensity drift. 20 When benchmarking radiomic features on MRI, it may thus be critical to first account for these sources of variance between different sites and scanners.…”

Section: Introductionmentioning

confidence: 99%

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

et al. 2019

View full text Add to dashboard Cite

Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1-or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary based on differing acquisition protocols between institutions. We present the first empirical study of benchmarking five different radiomic feature families in terms of both reproducibility and discriminability in a multisite setting, specifically, for identifying prostate tumors in the peripheral zone on MRI. Our cohort comprised 147 patient T2-weighted MRI datasets from four different sites, all of which are first preprocessed to correct for acquisition-related artifacts such as bias field, differing voxel resolutions, and intensity drift (nonstandardness). About 406 three-dimensional voxelwise radiomic features from five different families (gray, Haralick, gradient, Laws, and Gabor) were evaluated in a cross-site setting to determine (a) how reproducible they are within a relatively homogeneous nontumor tissue region and (b) how well they could discriminate tumor regions from nontumor regions. Our results demonstrate that a majority of the popular Haralick features are reproducible in over 99% of all cross-site comparisons, as well as achieve excellent cross-site discriminability (classification accuracy of ≈0.8). By contrast, a majority of Laws features are highly variable across sites (reproducible in <75% of all cross-site comparisons) as well as resulting in low cross-site classifier accuracies (<0.6), likely due to a large number of noisy filter responses that can be extracted. These trends suggest that only a subset of radiomic features and associated parameters may be both reproducible and discriminable enough for use within machine learning classifier schemes.

show abstract

Section: Introductionmentioning

confidence: 99%

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

et al. 2019

View full text Add to dashboard Cite

show abstract

“…So, the matrix created by testing the combinations of independent variable values can represent the dependent variable values as a surface that corresponds to all coordinates of experimental design. The coefficients of the surface polynomial are calculated by least squares method to meet the dependent variable values measured in the experiment (Bu‐Qing & Ding‐Yuan, ; Kahali, Adhikari, & Sing, ). In the following Equations (Equations 1, 2 and 3) and Figure , how a surface polynomial model can be obtained is shown as both numerically and representative.…”

Section: Methodsmentioning

confidence: 99%

“…this matrix are the values of independent variables while the values in the cells are corresponding the values of dependent variable. So, the matrix created by testing the combinations of independent variable values can represent the dependent variable values as a surface that corresponds to all coordinates of experimental design.The coefficients of the surface polynomial are calculated by least squares method to meet the dependent variable values measured in the experiment(Bu-Qing & Ding-Yuan, 2014;Kahali, Adhikari, & Sing, 2016). In the following Equations (Equations 1, 2 and 3) and…”

mentioning

confidence: 99%

Polynomial surface fitting and artificial neural networks‐based analysis of the storage days and garlic extract supplementation dependent microbial growths in minced raw chicken meat

Külcü

Kalkan

Akben

2019

J Food Process Preserv

View full text Add to dashboard Cite

In this study, effects of garlic extract on microbial growth occurred in minced chicken were measured. Microbial growths modeled were the yeast‐mold, Staphylococcus aureus, total coliform group bacteria, total mesophilic aerobic bacteria and total psychrophilic bacteria (TPB). Garlic extracts were added in concentrations of 0.5, 1, 1.5, and 2% and measurements were done at 1st, 3rd, 5th, 7th and 10th days of storage for each garlic extract. The polynomial surface fitting (PSF) and artificial neural networks (ANN) were used as modeling methods. It was found that the garlic extract has modelable effects to inhibit the microbial growth occurs in minced raw chicken meat. The fits of models were between 97 and 99%. Although the ANN provided better fit about 1–1.5%, the use of both models together was suggested due to some disadvantages of ANN. Finally, the garlic extract concentration that promises the best microbial growth inhibition was suggested using ANN and PSF models. Practical applications Garlic extract supplementation can completely prevent along first storage day all microbial growths in minced chicken meat stored at refrigerator temperature. The microbial growth can also be inhibited in later days, under same conditions. Thus, the shelf life of minced chicken meat stored at refrigerator temperature can be extended up to 1 day by means of garlic supplementation. In addition, the proposed models provide the possibility to calculate the microbial growth values as the function of storage day and garlic extract concentration.

show abstract

“…Active contours are retrospective methods suitable for both image segmentation and bias correction [10–12, 16–18]. The first active contour method was proposed in [19] in order to segment an image by evolving a curve towards the boundary of an object contained in the image.…”

Section: Introductionmentioning

confidence: 99%

Active contours driven by local and global fitted image models for image segmentation robust to intensity inhomogeneity

2017

View full text Add to dashboard Cite

This paper presents a region-based active contour method for the segmentation of intensity inhomogeneous images using an energy functional based on local and global fitted images. A square image fitted model is defined by using both local and global fitted differences. Moreover, local and global signed pressure force functions are introduced in the solution of the energy functional to stabilize the gradient descent flow. In the final gradient descent solution, the local fitted term helps extract regions with intensity inhomogeneity, whereas the global fitted term targets homogeneous regions. A Gaussian kernel is applied to regularize the contour at each step, which not only smoothes it but also avoids the computationally expensive re-initialization. Intensity inhomogeneous images contain undesired smooth intensity variations (bias field) that alter the results of intensity-based segmentation methods. The bias field is approximated with a Gaussian distribution and the bias of intensity inhomogeneous regions is corrected by dividing the original image by the approximated bias field. In this paper, a two-phase model is first derived and then extended to a four-phase model to segment brain magnetic resonance (MR) images into the desired regions of interest. Experimental results with both synthetic and real brain MR images are used for a quantitative and qualitative comparison with state-of-the-art active contour methods to show the advantages of the proposed segmentation technique in practical terms.

show abstract

On estimation of bias field in MRI images: polynomial vs Gaussian surface fitting method

Cited by 12 publications

References 22 publications

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

Polynomial surface fitting and artificial neural networks‐based analysis of the storage days and garlic extract supplementation dependent microbial growths in minced raw chicken meat

Active contours driven by local and global fitted image models for image segmentation robust to intensity inhomogeneity

Contact Info

Product

Resources

About