PSIGAN: Joint Probabilistic Segmentation and Image Distribution Matching for Unpaired Cross-Modality Adaptation-Based MRI Segmentation

Background: Variations of image segmentation techniques, particularly those used for Brain MRI segmentation, vary in complexity from basic standard Fuzzy C-means (FCM) to more complex and enhanced FCM techniques. Objective: In this paper, a comprehensive review is presented on all thirteen variations of FCM segmentation techniques. In the review process, the concentration is on the use of FCM segmentation techniques for brain tumors. Brain tumor segmentation is a vital step in the process of automatically diagnosing brain tumors. Unlike segmentation of other types of images, brain tumor segmentation is a very challenging task due to the variations in brain anatomy. The low contrast of brain images further complicates this process. Early diagnosis of brain tumors is indeed beneficial to patients, doctors, and medical providers. Results: FCM segmentation works on images obtained from magnetic resonance imaging (MRI) scanners, requiring minor modifications to hospital operations to early diagnose tumors as most, if not all, hospitals rely on MRI machines for brain imaging. In this paper, we critically review and summarize FCM based techniques for brain MRI segmentation.

Download Full-text

Spatial Rough Intuitionistic Fuzzy C-Means Clustering for MRI Segmentation

Neural Processing Letters ◽

10.1007/s11063-021-10441-w ◽

2021 ◽

Vol 53 (2) ◽

pp. 1305-1353

Author(s):

R. Kala ◽

P. Deepa

Keyword(s):

Mri Segmentation ◽

Fuzzy C Means ◽

Intuitionistic Fuzzy ◽

Fuzzy C Means Clustering

Download Full-text

Quality-driven Deep Active Learning Method for 3D Brain MRI Segmentation

Neurocomputing ◽

10.1016/j.neucom.2021.03.050 ◽

2021 ◽

Author(s):

Zhenxi Zhang ◽

Jie Li ◽

Chunna Tian ◽

Zhusi Zhong ◽

Zhicheng Jiao ◽

...

Keyword(s):

Active Learning ◽

Brain Mri ◽

Learning Method ◽

Mri Segmentation ◽

Active Learning Method

Download Full-text

Non-random sampling and association tests on realized returns and risk proxies

Review of Accounting Studies ◽

10.1007/s11142-021-09581-0 ◽

2021 ◽

Author(s):

Frank Ecker ◽

Jennifer Francis ◽

Per Olsson ◽

Katherine Schipper

Keyword(s):

Random Sampling ◽

Reference Sample ◽

Positive Association ◽

Cost Of Equity ◽

Association Tests ◽

Random Samples ◽

Distribution Matching ◽

Matched Samples ◽

Data Requirements ◽

Selection Of

AbstractThis paper investigates how data requirements often encountered in archival accounting research can produce a data-restricted sample that is a non-random selection of observations from the reference sample to which the researcher wishes to generalize results. We illustrate the effects of non-random sampling on results of association tests in a setting with data on one variable of interest for all observations and frequently-missing data on another variable of interest. We develop and validate a resampling approach that uses only observations from the data-restricted sample to construct distribution-matched samples that approximate randomly-drawn samples from the reference sample. Our simulation tests provide evidence that distribution-matched samples yield generalizable results. We demonstrate the effects of non-random sampling in tests of the association between realized returns and five implied cost of equity metrics. In this setting, the reference sample has full information on realized returns, while on average only 16% of reference sample observations have data on cost of equity metrics. Consistent with prior research (e.g., Easton and Monahan The Accounting Review 80, 501–538, 2005), analysis using the unadjusted (non-random) cost of equity sample reveals weak or negative associations between realized returns and cost of equity metrics. In contrast, using distribution-matched samples, we find reliable evidence of the theoretically-predicted positive association. We also conceptually and empirically compare distribution-matching with multiple imputation and selection models, two other approaches to dealing with non-random samples.

Download Full-text