MRI Bias Field Estimation and Tissue Segmentation Using Multiplicative Intrinsic Component Optimization and Its Extensions

Samad Wali (), Chunming Li () and Lingyan Zhang ()
Additional contact information
Samad Wali: University of Electronic Science and Technology of China, School of Information and Communication Engineering
Chunming Li: University of Electronic Science and Technology of China, School of Information and Communication Engineering
Lingyan Zhang: University of Electronic Science and Technology of China, School of Information and Communication Engineering

Chapter 34 in Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging, 2023, pp 1203-1234 from Springer

Abstract: Abstract In medical image analysis, energy minimization-based optimization approaches are invaluable. This chapter presents a joint optimization method called multiplicative intrinsic component optimization (MICO) for magnetic resonance (MR) images in bias field estimation and segmentation. Due to the intensity inhomogeneity in MR images, there are overlaps between the ranges of the intensities of different tissues, which often causes misclassification of tissues. To overcome this problem, our proposed method MICO can estimate bias field without avoiding intensity inhomogeneity and can benefit to achieve superior tissue segmentation results. We extended MICO formulation by connecting total variation (TV) as a convex regularization. In addition, for the TV-based MICO model, we implemented the alternating direction method of multipliers (ADMM), which can solve the model efficiently and guarantee its convergence. Quantitative evaluations and comparisons with other popular software have shown that MICO and TVMICO outperform them in terms of robustness and accuracy.

Keywords: MRI; Brain segmentation; Intensity inhomogeneity; Bias field estimation; Bias field correction; Energy minimization; Multiplicative intrinsic component optimization; 4D segmentation; Total variation; ADMM (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations: View citations in EconPapers (1)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-98661-2_110

Ordering information: This item can be ordered from
http://www.springer.com/9783030986612

DOI: 10.1007/978-3-030-98661-2_110

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().