Classification of fluorescence in situ hybridization images using belief networks

Malka, R.; Lerner, Boaz

doi:10.1016/j.patrec.2004.07.010

Cited by 16 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the cytogenetic domain, all except one of the variables are continuous (see the FISH Signal Representation and Classification section); hence, we quantize the variables, as required by the K2 algorithm, and estimate the distributions using the relative frequencies in the data (Malka and Lerner 2004) (i.e., the maximum likelihood solution [Heckerman 1995]). …”

Section: Investigation Of the K2 Algorithm 81mentioning

confidence: 99%

“…We focused our previous efforts to accomplish this task on learning Bayesian network classifiers (BNCs) (Lerner 2004;Malka and Lerner 2004). One study (Lerner 2004) demonstrated simplicity and accuracy of the naive Bayesian classifier (NBC) in FISH signal classification, however not the expected domain interpretability.…”

Section: Introductionmentioning

confidence: 99%

“…One study (Lerner 2004) demonstrated simplicity and accuracy of the naive Bayesian classifier (NBC) in FISH signal classification, however not the expected domain interpretability. 1 To alleviate the NBC independence restriction that may have weakened interpretability and accuracy, we allowed (Malka and Lerner 2004) the BNC to capture dependencies in the domain. The unrestricted BNC was constructed by using expert knowledge or learned from the data using the K2 algorithm (Cooper and Herskovits 1992), in the latter case, however, with inferior accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigation of the K2 Algorithm in Learning Bayesian Network Classifiers

Lerner

Malka

2011

Applied Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Section: Investigation Of the K2 Algorithm 81mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of the K2 Algorithm in Learning Bayesian Network Classifiers

Lerner

Malka

2011

Applied Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

“…For example, Netten et al, reported the first automated FISH image analysis system that enables to count FISH signals that are neither split nor stringy in a single spectrum [16]. Since then, several other automated FISH image analysis systems and schemes have been developed and tested [3,[17][18][19]. In these schemes, different image processing methods, including the user-defined thresholds [3], artificial neural networks [17], the watershed algorithm [19], and the Isodata algorithm [20], were used to segment interphase cell nuclei.…”

Section: Introductionmentioning

confidence: 99%

FluorescenceIn SituHybridization (FISH) Signal Analysis Using Automated Generated Projection Images

Wang

Chen

et al. 2012

Analytical Cellular Pathology

View full text Add to dashboard Cite

Fluorescencein situhybridization (FISH) tests provide promising molecular imaging biomarkers to more accurately and reliably detect and diagnose cancers and genetic disorders. Since current manual FISH signal analysis is low-efficient and inconsistent, which limits its clinical utility, developing automated FISH image scanning systems and computer-aided detection (CAD) schemes has been attracting research interests. To acquire high-resolution FISH images in a multi-spectral scanning mode, a huge amount of image data with the stack of the multiple three-dimensional (3-D) image slices is generated from a single specimen. Automated preprocessing these scanned images to eliminate the non-useful and redundant data is important to make the automated FISH tests acceptable in clinical applications. In this study, a dual-detector fluorescence image scanning system was applied to scan four specimen slides with FISH-probed chromosome X. A CAD scheme was developed to detect analyzable interphase cells and map the multiple imaging slices recorded FISH-probed signals into the 2-D projection images. CAD scheme was then applied to each projection image to detect analyzable interphase cells using an adaptive multiple-threshold algorithm, identify FISH-probed signals using a top-hat transform, and compute the ratios between the normal and abnormal cells. To assess CAD performance, the FISH-probed signals were also independently visually detected by an observer. The Kappa coefficients for agreement between CAD and observer ranged from 0.69 to 1.0 in detecting/counting FISH signal spots in four testing samples. The study demonstrated the feasibility of automated FISH signal analysis that applying a CAD scheme to the automated generated 2-D projection images.

show abstract

“…The addition of another parent only adds unnecessary complexity and increases the number of network parameters. Consequently, other authors [4,5,6,28,8] have proposed the use of more sophisticated methods to overcome these shortcomings, among which are: the use of the K2 algorithms [6,24,25,26,27,28,10,4], the Genetic Search [7,4], the Greedy Search [11,4], the Annealing Simulated [8,4], the Greedy Hill Climber [7,4] and the Repeated Hill Climber [7,4]. Although these algorithms have actually managed to attain performant classifiers, their application has resulted in the frequently and commonly encountered problem of structure-learning computational complexity owing to the increase in the number of descriptive variables.…”

Section: Introductionmentioning

confidence: 99%

A New Approach for Bayesian Classifier Learning Structure via K2 Algorithm

Bouhamed

Masmoudi

Lecroq

et al. 2012

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. It is a well-known fact that the Bayesian Networks' (BNs) use as classifiers in different fields of application has recently witnessed a noticeable growth. Yet, the Naïve Bayes' application, and even the augmented Naïve Bayes', to classifier-structure learning, has been vulnerable to certain limits, which explains the practitioners' resort to other more sophisticated types of algorithms. Consequently, the use of such algorithms has paved the way for raising the problem of super-exponential increase in computational complexity of the Bayesian classifier learning structure, with the increasing number of descriptive variables. In this context, the present work's major objective lies in setting up a further solution whereby a remedy can be conceived for the intricate algorithmic complexity imposed during the learning of Bayesian classifiers' structure with the use of sophisticated algorithms. Noteworthy, the present paper's framework is organized as follows. We start, in the first place, by to propose a novel approach designed to reduce the algorithmic complexity without engendering any loss of information when learning the structure of a Bayesian classifier. We, then, go on to test our approach on a car diagnosis and a Lymphography diagnosis databases. Ultimately, an exposition of our conducted work's interests will be a closing step to this work.

show abstract

Classification of fluorescence in situ hybridization images using belief networks

Cited by 16 publications

References 11 publications

Investigation of the K2 Algorithm in Learning Bayesian Network Classifiers

Investigation of the K2 Algorithm in Learning Bayesian Network Classifiers

FluorescenceIn SituHybridization (FISH) Signal Analysis Using Automated Generated Projection Images

A New Approach for Bayesian Classifier Learning Structure via K2 Algorithm

Contact Info

Product

Resources

About