Bayesian Approach With Hidden Markov Modeling and Mean Field Approximation for Hyperspectral Data Analysis

Bali, Nadia; Mohammad-Djafari, Ali

doi:10.1109/tip.2007.914227

Cited by 60 publications

(46 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The initial objective of this research was to make the diagnosis of the small bowel diseases directly, but the results were disappointing because of the complexity and the multiformity of the lesions. The complicated algorithm (Hidded Markov models, HMM [24,25] or artificial neural network, ANN [26][27][28] ) was of a tryout. Though the diagnosis accuracy could be improved to some extent, the result was not satisfactory to the physicians, and the scanning time of IPS was much longer than that of the readers' performance; therefore, it could not be accepted in the clinical practice.…”

Section: Discussionmentioning

confidence: 99%

A feasibility trial of computer-aided diagnosis for enteric lesions in capsule endoscopy

Gan¹,

Wu²,

Rao³

et al. 2008

WJG

View full text Add to dashboard Cite

images for the rarely-encountered lesions were difficult to differentiate from the normal images. However, the number of the images screened by IPS was 5000 on average, and only 10%-15% of the original images were left behind. As a result, a large number of normal images were excluded, and the reading time decreased from 5 h to 1 h on average. CONCLUSION: Though the total accuracy and specificity rates by the computer-aided screening for the enteric lesions with IPS are much lower than those by the CE readers, the computer-aided screening diagnosis can exclude a large number of the normal images and confine the enteric lesions to 5000 images on average, which can reduce the workload of the readers in the scanning of the images. This computer-aided screening technique can make a correct diagnosis as efficiently as possible in most of the patients. INTRODUCTIONDepiction of the small intestines has still been a challenge because of their length and tortuosity. In the past time when some lesions occurred in an intestinal segment, they were usually difficult to identify because of a shortage of the efficiently used tools [1,2] . When the capsule endoscopy (CE) was introduced to the clinical practice in 2000, it became a revolutionary diagnostic tool in diagnosing small intestinal diseases [3] . Besides, there is growing evidence that CE may be used in diagnosing some diseases occurring in the colon and the esophagus [4,5] . Because of the incapability of its use in the insufflation, affusion, biopsy and therapy, when Abstract AIM: To investigate and evaluate the feasibility of the computer-aided screening diagnosis for enteric lesions in the capsule endoscopy (CE). METHODS: After developing a series of algorithms for the screening diagnosis of the enteric lesions in CE based on their characteristic colors and contours, the normal and abnormal images obtained from 289 patients were respectively scanned and diagnosed by the CE readers and by the computer-aided screening for the enteric lesions with the image-processed software (IPS). The enteric lesions shown by the images included esoenteritis, mucosal ulcer and erosion, bleeding, spaceoccupying lesions, angioectasia, diverticula, parasites, etc. The images for the lesions or the suspected lesions confirmed by the CE readers and the computers were collected, and the effectiveness rate of the screening and the number of the scanned images were evaluated, respectively. RESULTS: Compared with the diagnostic results obtained by the CE readers, the total effectiveness rate (sensitivity) in the screening of the commonlyencountered enteric lesions by IPS varied from 42.9% to 91.2%, with a median of 74.2%, though the specificity and the accuracy rates were still low, and the

show abstract

Section: Discussionmentioning

confidence: 99%

A feasibility trial of computer-aided diagnosis for enteric lesions in capsule endoscopy

Gan¹,

Wu²,

Rao³

et al. 2008

WJG

View full text Add to dashboard Cite

show abstract

“…The machine learning community has widely adopted variational methods, e.g., to solve problems related to graphical models [8,9]. In the signal processing community, the variational methods have been used as an alternative to MCMC methods in various topics such as speech processing [10], identification of non-Gaussian auto-regressive models [11] and for inverse problems applied on hyperspectral imagery [12]. In this paper, we present a new variational Bayesian framework based on the model developed in [6] for HU.…”

Section: Introductionmentioning

confidence: 99%

Variational methods for spectral unmixing of hyperspectral images

Eches¹,

Dobigeon²,

Tourneret³

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper studies a variational Bayesian unmixing algorithm for hyperspectral images based on the standard linear mixing model. Each pixel of the image is modeled as a linear combination of endmembers whose corresponding fractions or abundances are estimated by a Bayesian algorithm. This approach requires to define prior distributions for the parameters of interest and the related hyperparameters. After defining appropriate priors for the abundances (uniform priors on the interval (0, 1)), the joint posterior distribution of the model parameters and hyperparameters is derived. The complexity of this distribution is handled by using variational methods that allow the joint distribution of the unknown parameters and hyperparameter to be approximated. Simulation results conducted on synthetic and real data show similar performances than those obtained with a previously published unmixing algorithm based on Markov chain Monte Carlo methods, with a significantly reduced computational cost.Index Terms-Bayesian inference, variational methods, spectral unmixing, hyperspectral images.

show abstract

“…Selecting the number of components is discussed in [5,10,11], where [5] proposes the Minimum Message Length (MML) for component number selection and [10,11] combine component and feature selection in a Bayesian framework. Bali [8] proposes a joint solution for the number of features and selection of number of components problem, taking into account both the spatial and spectral structures in data. Fauvel et al [13] tackles the problem by fusing morphological information (spatial data properties) and the original hyperspectral data using support vector machines.…”

Section: Introductionmentioning

confidence: 99%

“…Feature selection is also discussed in [4,12], where [12] uses the Principal Component Analysis (PCA) for feature selection. The drawbacks of PCA and other measures with unclear physical interpretation are discussed in [8]. Jimenez [9] describes a preprocessing step for reducing the number of features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Target Segmentation in Scenes with Diverse Background

Grönwall

Tolt

2011

Image Analysis

View full text Add to dashboard Cite

Abstract. We propose a target segmentation approach based on sensor data fusion that can deal with the problem of a diverse background. Features from sensor images, including data from a laser scanner and passive sensors (cameras), are analyzed using Gaussian mixture estimation. The approach tackles some of the difficulties with Gaussian mixtures, e.g., selecting the number of initial components and a good description of data in terms of the number of Gaussian components, and determining the relevant features for the current data set. The feature selection quality is analyzed on-line. We propose a criterion that determines the quality of the resulting clusters in terms of their respective spatial distribution. The output from the analysis is used for object-background segmentation. Segmentation examples of surface-laid mines in outdoor scenes are shown.

show abstract

Bayesian Approach With Hidden Markov Modeling and Mean Field Approximation for Hyperspectral Data Analysis

Cited by 60 publications

References 14 publications

A feasibility trial of computer-aided diagnosis for enteric lesions in capsule endoscopy

A feasibility trial of computer-aided diagnosis for enteric lesions in capsule endoscopy

Variational methods for spectral unmixing of hyperspectral images

Target Segmentation in Scenes with Diverse Background

Contact Info

Product

Resources

About