Orthogonal subspace projection-based approaches to classification of MR image sequences

Wang, Chuin-Mu; Yang, Shuenn-Chen; Chung, Pau‐Choo; Chang, Chein‐I; Lo, Chun-Chih; Chen, C. C.; Yang, Chih‐Wei; Wen, Chia-Hsin

doi:10.1016/s0895-6111(01)00015-5

Cited by 33 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It results a single component image representing a classification map for the desired object. Wang et al [22] have discussed different versions of OSP to analyze remotely sensed spectral images including MR images. It considers the MR image sequence as a multispectral image cube, and models each pixel vector as a linear mixture of tissue materials.…”

Section: Literature Reviewmentioning

confidence: 99%

Retinal Spectral Image Analysis Methods Using Spectral Reflectance Pattern Recognition

Rahaman

Parkkinen

Hauta-Kasari

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Conventional 3-channel color images have limited information and quality dependency on parametric conditions. Hence, spectral imaging and reproduction is desired in many color applications to record and reproduce the reflectance of objects. Likewise RGB images lack sufficient information to successfully analyze diabetic retinopathy. In this case, spectral imaging may be the alternative solution. In this article, we propose a new supervised technique to detect and classify the abnormal lesions in retinal spectral reflectance images affected by diabetes. The technique employs both stochastic and deterministic spectral similarity measures to match the desired reflectance pattern. At first, it classifies a pixel as normal or abnormal depending on the probabilistic behavior of training spectra. The final decision is made evaluating the geometric similarity. We assessed several multispectral object detection methods developed for other applications. They could not proof to be the solution. The results were interpreted using receiver operating characteristics (ROC) curves analysis.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Retinal Spectral Image Analysis Methods Using Spectral Reflectance Pattern Recognition

Rahaman

Parkkinen

Hauta-Kasari

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…However, because multispectral images provide more information for processing or analysis, multispectral analysis techniques can be used to improve the performance. Hence, several methods have been developed for processing multispectral MRIs, such as orthogonal subspace projection (OSP) 6 and Kalman filter, 7 but both of them require prior knowledge. With these considerations, we have developed a new method called the independent component texture analysis (ICTA) to segment the tumor region in multispectral breast MRIs.…”

Section: Introductionmentioning

confidence: 99%

Tumor segmentation from breast magnetic resonance images using independent component texture analysis

Yang

Huang

Chang

et al. 2013

J. Electron. Imaging

View full text Add to dashboard Cite

Abstract.A new spectral signature analysis method for tumor segmentation in breast magnetic resonance images is presented. The proposed method is called an independent component texture analysis (ICTA), which consists of three techniques including independent component analysis (ICA), entropy-based thresholding, and texture feature registration (TFR). ICTA was mainly developed to resolve the inconsistency in the results of independent components (ICs) due to the random initial projection vector of ICA and then accordingly determine the most likely IC. A series of experiments were conducted to compare and evaluate ICTA with principal component texture analysis, traditional ICA, traditional principal component analysis (PCA), fuzzy c-means, constrained energy minimization, and orthogonal subspace projection methods. The experimental results showed that ICTA had higher efficiency than existing methods. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…The KFLM applies the Kalman filter on the linear spectral mixture model of breast MRIs based on the assumption that breast MRIs contains multiple object signatures (i.e., fatty tissue, glandular tissue, tumor mass and muscle) with their complete knowledge; each MRI pixel is then regarded as a model construed by linear mixing of these object signatures [7][8][9]. The Kalman filter can reflect abrupt changes in signature abundance via an auxiliary equation called the abundance state equation (ASE), which traces, estimates and updates the signature abundance recursively; it then estimates each of these substances by employing the abundance fractions of the substances as a base for classification.…”

Section: Introductionmentioning

confidence: 99%

Contrast enhancement and tissues classification of breast MRI using Kalman filter-based linear mixing method

Yang¹,

Wang²,

Hsu³

et al. 2009

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

Orthogonal subspace projection-based approaches to classification of MR image sequences

Cited by 33 publications

References 25 publications

Retinal Spectral Image Analysis Methods Using Spectral Reflectance Pattern Recognition

Retinal Spectral Image Analysis Methods Using Spectral Reflectance Pattern Recognition

Tumor segmentation from breast magnetic resonance images using independent component texture analysis

Contrast enhancement and tissues classification of breast MRI using Kalman filter-based linear mixing method

Contact Info

Product

Resources

About