Computational intelligence for microarray data and biomedical image analysis for the early diagnosis of breast cancer
Expert Systems with ApplicationsPublished 9 June 2012
Jesmin Nahar, Tasadduq Imam, Kevin S. Tickle, A. B. M. Shawkat Ali, Yi‐Ping Phoebe Chen
Citations53
SJR quartileQ1
SJR score1.85
SNIP2.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Results indicated SMO as the most potential candidate for the microarray and image dataset considered in this research, and the Naive Bayes algorithm was seen to perform highly in terms of true positive rate (TPR).
Abstract
The objective of this paper was to perform a comparative analysis of the computational intelligence algorithms to identify breast cancer in its early stages. Two types of data representations were considered: microarray based and medical imaging based. In contrast to previous researches, this research also considered the imbalanced nature of these data. It was observed that the SMO algorithm performed better for the majority of the test data, especially for microarray based data when accuracy was used as performance measure. Considering the imbalanced characteristic of the data, the Naive Bayes algorithm was seen to perform highly in terms of true positive rate (TPR). Regarding the influence of SMOTE, a well-known imbalanced data classification technique, it was observed that there was a notable performance improvement for J48, while the performance of SMO remained comparable for the majority of the datasets. Overall, the results indicated SMO as the most potential candidate for the microarray and image dataset considered in this research.
Keywords
Computer ScienceHealth Professions
Journal of Artificial Intelligence ResearchSMOTE: Synthetic Minority Over-sampling Technique
31,194 Citations2002Nitesh V. Chawla, Kevin W. Bowyer +2 more
A combination of the method of oversampling the minority (abnormal) class and under-sampling the majority class can achieve better classifier performance (in ROC space) and a combination of these methods and the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy is evaluated.
Elsevier eBooksData Mining: Practical Machine Learning Tools and Techniques
25,718 Citations2011Ian H. Witten, Eibe Frank
NatureGene expression profiling predicts clinical outcome of breast cancer
9,608 Citations2002Laura van ‘t Veer, Hongyue Dai +14 more
DNA microarray analysis on primary breast tumours of 117 young patients is used and supervised classification is applied to identify a gene expression signature strongly predictive of a short interval to distant metastases (‘poor prognosis’ signature) in patients without tumour cells in local lymph nodes at diagnosis, providing a strategy to select patients who would benefit from adjuvant therapy.
Pattern RecognitionThe use of the area under the ROC curve in the evaluation of machine learning algorithms
7,233 Citations1997Andrew P. Bradley
AUC exhibits a number of desirable properties when compared to overall accuracy: increased sensitivity in Analysis of Variance (ANOVA) tests; a standard error that decreased as both AUC and the number of test samples increased; decision threshold independent; and it is invariant to a priori class probabilities.
NatureGenes that mediate breast cancer metastasis to lung
2,957 Citations2005Andy J. Minn, Gaorav P. Gupta +8 more
A set of genes are identified that marks and mediates breast cancer metastasis to the lungs and serve dual functions, providing growth advantages both in the primary tumour and in the lung microenvironment.
Journal of Neural EngineeringA review of classification algorithms for EEG-based brain–computer interfaces
2,629 Citations2007Fabien Lotte, Marco Congedo +3 more
This paper compares classification algorithms used to design brain–computer interface (BCI) systems based on electroencephalography (EEG) in terms of performance and provides guidelines to choose the suitable classification algorithm(s) for a specific BCI.
NaturePrediction of central nervous system embryonal tumour outcome based on gene expression
2,377 Citations2002Scott L. Pomeroy, Pablo Tamayo +23 more
It is demonstrated that medulloblastomas are molecularly distinct from other brain tumours including primitive neuroectodermal tumours, atypical teratoid/rhabdoid tumours (AT/RTs) and malignant gliomas, and it is shown that the clinical outcome of children with medullOBlastomas is highly predictable on the basis of the gene expression profiles of their tumours at diagnosis.
Lecture notes in computer scienceKnowledge-Based Intelligent Information and Engineering Systems
1,706 Citations2008Rossitza Setchi, Ivan Jordanov +3 more
New England Journal of MedicineConcordance among Gene-Expression–Based Predictors for Breast Cancer
1,342 Citations2006Cheng Fan, Daniel Oh +6 more
Four of the five gene sets used for prognostication in patients with breast cancer showed significant agreement in the outcome predictions for individual patients and are probably tracking a common set of biologic phenotypes.
IEEE Transactions on Biomedical EngineeringBCI Competition 2003—Data Set IIb: Support Vector Machines for the P300 Speller Paradigm
495 Citations2004Matthias Kaper, Peter Meinicke +3 more
An approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines, which is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.
Journal of Neural EngineeringCharacterization of four-class motor imagery EEG data for the BCI-competition 2005
416 Citations2005Alois Schlögl, Felix Lee +2 more
The results of the multi-channel analysis indicate SVM as the most successful classifier, whereas kNN performed worst, while the single-channel results gave rise to topographic maps that revealed the channels with the highest level of separability between classes for each subject.
BioinformaticsClassification of multiple cancer types by multicategory support vector machines using gene expression data
377 Citations2003Yoonkyung Lee, Cheol‐Koo Lee
The Multicategory SVM is introduced, which is a recently proposed extension of the binary SVM, and applied to multiclass cancer diagnosis problems, which renders the MSVM a viable alternative to other classification methods.
Proceedings of the National Academy of SciencesA pathway-based classification of human breast cancer
340 Citations2010Michael L. Gatza, Joseph E. Lucas +9 more
A classification scheme for human breast cancer making use of patterns of pathway activity to build on previous subtype characterizations using intrinsic gene expression signatures, to provide a functional interpretation of the gene expression data that can be linked to therapeutic options.
Journal of the Franklin InstituteA review of computer-aided diagnosis of breast cancer: Toward the detection of subtle signs
337 Citations2006Rangaraj M. Rangayyan, Fábio J. Ayres +1 more
An overview of digital image processing and pattern analysis techniques to address several areas in CAD of breast cancer, including: contrast enhancement, detection and analysis of calcifications, detection of masses and tumors, analysis of bilateral asymmetry, and detection of architectural distortion is presented.
JNCI Journal of the National Cancer InstituteA Three-Gene Model to Robustly Identify Breast Cancer Molecular Subtypes
329 Citations2012Benjamin Haibe‐Kains, Christine Desmedt +5 more
The results suggest that adequate classification of the major and clinically relevant molecular subtypes of breast cancer can be robustly achieved with quantitative measurements of three key genes.
Automated grading of breast cancer histopathology using spectral clusteringwith textural and architectural image features
275 Citations2008Scott Doyle, Shannon C. Agner +3 more
A novel image analysis methodology for automatically distinguishing low and high grades of breast cancer from digitized histopathology is presented and the underlying manifold structure on which the different grades of cancer lie as revealed through spectral clustering is investigated.
Information SystemsCancer classification using gene expression data
270 Citations2003Ying Lü, Jiawei Han
This survey paper presents a comprehensive overview of various proposed cancer classification methods and evaluates them based on their computation time, classification accuracy and ability to reveal biologically meaningful gene information.
Journal of Neural EngineeringMotor imagery classification by means of source analysis for brain–computer interface applications
240 Citations2004Lei Qin, Lei Ding +1 more
The present promising results suggest that the source analysis approach could manifest a clearer picture on the cortical activity, and thus facilitate the classification of MI tasks from scalp EEGs.
CERN Document Server (European Organization for Nuclear Research)The Handbook of Data Mining
216 Citations2003Nong Ye
American Journal of Clinical NutritionDietary fat and breast cancer risk in the European Prospective Investigation into Cancer and Nutrition
187 Citations2008Sabina Sieri, Vittorio Krogh +48 more
Evidence indicates a weak positive association between saturated fat intake and breast cancer risk was found, more pronounced for postmenopausal women who never used hormone therapy and for nonusers of hormone therapy at baseline.
Support Vector Method for Multivariate Density Estimation
177 Citations1999Vladimir Vapnik, Sayan Mukherjee
A new method for multivariate density estimation is developed based on the Support Vector Method (SVM) solution of inverse ill-posed problems that compared favorably to both Parzen's method and the Gaussian Mixture Model method.
Lecture notes in computer scienceAdvances in Knowledge Discovery and Data Mining
146 Citations2010Zaki, Mohammed J., Pudi, Vikram +2 more
Expert Systems with ApplicationsExpert system based on neuro-fuzzy rules for diagnosis breast cancer
145 Citations2010Ali Keleş, Ali Keleş +3 more
An expert system that can be called as an Ex-DBC (Expert system for Diagnosis of Breast Cancer), because differentiating between benign and malignant mammographic findings, however, is quite difficult, is developed.
Cancer ResearchObesity and Breast Cancer: Progress to Understanding the Relationship
131 Citations2009Kristy A. Brown, Evan R. Simpson
Expert Systems with ApplicationsA novel cognitive interpretation of breast cancer thermography with complementary learning fuzzy neural memory structure
118 Citations2006Theresa May Chin Tan, Chai Quek +2 more
Complementary Learning Fuzzy Neural Network (CLFNN), FALCON-AART is proposed as the Computer-Assisted Intervention (CAI) tool for thermogram analysis, a neuroscience-inspired technique that provides intuitive fuzzy rules, human-like reasoning, and good classification performance.
International Journal of CancerBreastfeeding and breast cancer risk in India: A multicenter case‐control study
87 Citations2009Vendhan Gajalakshmi, Aleyamma Mathew +6 more
Health campaign focusing on breastfeeding behavior by appropriately educating women would contribute to reduce breast cancer burden, and a reduction of breast cancer risk with prolonged breastfeeding was shown among premenopausal women.
Cancer EpidemiologyProlonged breastfeeding reduces risk of breast cancer in Sri Lankan women: A case–control study
81 Citations2010Malintha De Silva, Upul Senarath +2 more
Prolonged breastfeeding significantly reduces the risk of breast cancer and this protective effect was supported by a dose-response relationship and risk due to passive smoking should be emphasized in anti-smoking programmes.
International Journal of CancerRisk factors for breast cancer in chinese women of Beijing
80 Citations1988Su‐Chang Tao, Mimi C. Yu +2 more
A self‐administered questionnaire was completed by 497 Chinese women in Beijing with histologically confirmed breast cancer and by an equal number of age‐ and neighborhood matched control women, finding that Nulliparity and late age at first birth were associated with an elevated risk of breast cancer.
Data & Knowledge EngineeringCancer classification by gradient LDA technique using microarray gene expression data
80 Citations2008Alok Sharma, Kuldip K. Paliwal
Gradient LDA technique is used which avoids the singularity problem associated with the within-class scatter matrix and achieves lower misclassification error as compared to several other previous techniques.
Computerized Medical Imaging and GraphicsExperimental investigation on breast tissue classification based on statistical feature extraction of mammograms
78 Citations2006H. S. Sheshadri, A. Kandaswamy
The breast tissue classification obtained is comparatively better than the other normal methods and is a part of developing a computer aided decision (CAD) system for early detection of breast cancer.
NatureGene expression in diagnosis
77 Citations2000Anton Berns
Using DNA microarray technology, it is now possible to screen large numbers of genes for their activity, or lack of it, under various conditions, so that patients with a disease known as diffuse large B-cell lymphoma can be divided into two groups which have markedly different prospects of survival.
Artificial Intelligence in MedicineEvaluation of radiological features for breast tumour classification in clinical screening with machine learning methods
70 Citations2004Tim W. Nattkemper, Bert Arnrich +6 more
It was found that contour and wash-out type (WOT) features determined by the radiologists lead to the best SVM classification results, indicating that the wash- out characteristics might be considered as important for malignant/benign classification of tumours.
Endocrine Related CancerPlasma sex hormone concentrations and breast cancer risk in an ethnically diverse population of postmenopausal women: the Multiethnic Cohort Study
68 Citations2009Christy Woolcott, Yurii B. Shvetsov +8 more
This study provides the best evidence to date that the association between sex hormones and breast cancer risk is generalizable to an ethnically diverse population.
Expert Systems with ApplicationsA GAs based approach for mining breast cancer pattern
68 Citations2005Ta-Cheng Chen, Timothy Hsu
A genetic algorithms (GAs) based approach to assess breast cancer pattern is proposed for extracting the decision rules including the predictors, the corresponding inequality and threshold values simultaneously so as to building a decision-making model with maximum prediction accuracy.
MULTICLASS CANCER CLASSIFICATION USING GENE EXPRESSION PROFILING AND PROBABILISTIC NEURAL NETWORKS
68 Citations2002Daniel Berrar, C. Stephen Downes +1 more
A probabilistic neural network (PNN) model is presented that provides sound statistical confidences for its decisions, and it is able to model asymmetrical misclassification costs, and the results demonstrate the successful application of the PNN model for multiclass cancer classification.
Expert Systems with ApplicationsA sequential feature extraction approach for naïve bayes classification of microarray data
67 Citations2009Liwei Fan, Kim-Leng Poh +1 more
Experimental results on five microarray datasets demonstrate the effectiveness of the proposed approach in improving the performance of naive Bayes classifier in microarray data analysis.
Journal of women's imagingEstimates of the Sizes at Which Breast Cancers Become Detectable on Mammographic and Clinical Grounds
55 Citations2003James Michaelson, Sameer Satija +6 more
Several new methods are proposed for measuring the ability to detect breast cancer, especially the sizes at which these cancers become operationally detectable by screening mammography, and how these aspects of these methods are changed in the absence of screening.
International Journal of Approximate ReasoningMachine learning-based receiver operating characteristic (ROC) curves for crisp and fuzzy classification of DNA microarrays in cancer research
53 Citations2007L. E. Peterson, Matthew A. Coleman
AUC determination in planned microarray experiments without standardization and fuzzification of features will benefit the most if CPSO is used for lower levels of feature significance and LVQ1 for greater levels of significance, and when only standardization of features is performed, studies are likely to benefit most by using CPSO for low level of feature statistical significance.
International Seminars in Surgical OncologyObesity in post menopausal women with a family history of breast cancer: prevalence and risk awareness
52 Citations2009Parvin Begum, Caroline Richardson +1 more
Breast Cancer ResearchFamilial relative risks for breast cancer by pathological subtype: a population-based cohort study
42 Citations2010Nasim Mavaddat, Paul D.P. Pharoah +9 more
FRR for breast cancer was significantly increased for both ER-negative and ER-positive disease, and including receptor status in conjunction with genetic status may aid risk prediction in women with a family history.
Lecture notes in computer scienceKnowledge-Based and Intelligent Information and Engineering Systems
39 Citations2010Rossitza Setchi, Ivan Jordanov +2 more
Non-Extensive Entropy for CAD Systems of Breast Cancer Images
37 Citations2006Jasjit S. Suri, Ruey‐Feng Chang +6 more
This paper proposes the use of non-extensive entropy, also called q-entropy, applied in a CAD system for breast cancer classification in ultrasound of mammographic exams to achieve better performance than the current literature offers.
Application of fuzzy cluster analysis for medical image data mining
35 Citations2006Shuyan Wang, Mingquan Zhou +1 more
The experimental results show that the application of fuzzy cluster analysis for medical image data mining performs quite well in accuracy and therefore reveals the potential of data mining in medical treatment assistance.
PLoS ONEA Prognostic Gene Expression Profile That Predicts Circulating Tumor Cell Presence in Breast Cancer Patients
34 Citations2012Timothy J. Molloy, Paul Roepman +2 more
Diagnostic histopathologyMolecular classification of breast carcinoma
33 Citations2012Michelle Alizart, Jodi M. Saunus +2 more
The introduction of genome-wide microarray-based expression profiling studies has allowed better understanding of the molecular underpinning of several characteristics of breast cancer, including histological grade and metastatic potential.
Engineering Applications of Artificial IntelligenceModel-free visualization of suspicious lesions in breast MRI based on supervised and unsupervised learning
31 Citations2007Thorsten Twellmann, Anke Meyer‐Baese +3 more
Annals of Surgical OncologyMicrometastatic Node-Positive Breast Cancer: Long-Term Outcomes and Identification of High-Risk Subsets in a Large Population-Based Series
25 Citations2010Pauline T. Truong, Mary Lesperance +4 more
The number of positive nodes and the LNR should be considered in conjunction with tumor factors in risk estimates and treatment decisions for patients with nodal micrometastatic breast cancer, which is a heterogeneous population with varying breast cancer mortality risks.
DNA and Cell BiologyMicroarray Data Classification Using Automatic SVM Kernel Selection
24 Citations2007Jesmin Nahar, Shawkat Ali +1 more
This work selected one of the state-of-the-art kernel-based algorithms, the support vector machine (SVM), to classify microarray data and found that the rule-based approach is most useful for automatic kernel selection for SVM to classifymicroarray data.
Breast Cancer ResearchA new gene expression signature, the ClinicoMolecular Triad Classification, may improve prediction and prognostication of breast cancer at the time of diagnosis
23 Citations2011Dong‐Yu Wang, Susan J. Done +4 more
A new gene signature, termed the "ClinicoMolecular Triad Classification" (CMTC), predicted recurrence and treatment response better than all pathological parameters and other prognostic signatures.
The application of ant colony optimization for gene selection in microarray-based cancer classification
23 Citations2008Yu-Min Chiang, Huei-Min Chiang +1 more
Experimental results show that selecting genes by using ACO algorithm can improve the accuracy of BP and SVM classifiers and the optimal number of genes selected for cancer classification should be set according to both the microarray dataset and gene selection methods.
International Congress SeriesPattern classification of breast masses via fractal analysis of their contours
20 Citations2005Rangaraj M. Rangayyan, Thanh Minh Nguyen
Fractal dimension resulted in the classification of mammographic masses as benign or malignant with overall accuracies of up to 0.93 and was able to classify atypical spiculated benign masses more accurately than other shape factors.
Journal of Biomedical InformaticsConstructing the gene regulation-level representation of microarray data for cancer classification
19 Citations2007Hau−San Wong, Hongqiang Wang
Experimental results on real-world microarray datasets show that the regulation-level representation can consistently converge at a solution with three regulation levels, which verifies the existence of the threeregulation levels associated with a particular biological phenotype.
CA A Cancer Journal for CliniciansBreast cancer screening: Successes and challenges
19 Citations2011W. Phil Evans
The decline in breast cancer mortality is due to a combination of factors, but most experts conclude that improvements in screening and treatment are the primary causes.
Computers in Biology and MedicineMicroarray data classification based on ensemble independent component selection
18 Citations2009Kunhong Liu, Bo Li +4 more
AGA is applied to select a set of optimal IC subsets, which are then used to build diverse and accurate base classifiers, and the experimental results show that the ensemble method obtains stable and satisfying classification results when compared with several existing methods.
Expert Systems with ApplicationsThe improvement of breast cancer prognosis accuracy from integrated gene expression and clinical data
17 Citations2011Austin H. Chen, Chenyin Yang
The results indicate that the GASVM model has the potential to better assist physicians in the prognosis of breast cancer through the use of both clinical and microarray data.
Cancer Epidemiology Biomarkers & PreventionIntegrating Tools for Breast Cancer Risk Assessment, Risk Reduction, and Early Detection
13 Citations2010Elizabeth Ward, Robert A. Smith
It is projected that there will be 207,090 diagnoses and 39,840 deaths from breast cancer among women in the United States in 2010, and approximately 10,300 will be diagnosed before the age of 40, the age when the American Cancer Society recommends diagnosis.
Oncology nursing forumInstrumental Relating and Treatment Decision Making Among Older Women With Early-Stage Breast Cancer
12 Citations2011Huibrie C. Pieters, MarySue V. Heilemann +3 more
The findings are the first evidence of the importance of relating as a key factor in decision making from the personal perspective of older women with early-stage breast cancer.
Gene Selection and Classification Using Non-linear Kernel Support Vector Machines Based on Gene Expression Data
9 Citations2007Qizhong Zhang
It is demonstrated experimentally that the proposed method of gene selection and classification by using nonlinear kernel support vector machine(SVM) based on recursive performance elimination (RFE) has better comprehensive performance than other linear classification methods.
Early Breast Cancer Identification: Which Way to Go? Microarray or Image Based Computer Aided Diagnosis!
5 Citations2009Jesmin Nahar, Kevin S. Tickle +2 more
Results suggest the most effective means of breast cancer identification in the early stage is a hybrid approach.
Cold Spring Harbor Symposia on Quantitative BiologyMolecular Approaches to Controlling Cancer
4 Citations2005Derek Stewart, Bruce Stillman
This Symposium is devoted for the first time to molecular approaches to cancer therapy, and several examples now exist of targeted therapy that works in patients that have been profiled based on genetic diagnosis of the patient’s tumor.
Journal of Medical CasesIsolated Colonic Metastasis From Primary Invasive Ductal Breast Carcinoma: Role of Tumor Marker in Early Diagnosis
3 Citations2012Srujitha Murukutla, Abhirami Vivekanandaraja +3 more
Patients presenting with elevated tumor markers must be judiciously investigated for gastrointestinal tract metastasis, as a primary breast tumor with metastasis to colon is a rare finding.
Journal of Medical CasesIsolated Colonic Metastasis From Primary Invasive Ductal Breast Carcinoma: Role of Tumor Marker in Early Diagnosis
2 Citations2012Murukutla
Pattern recognition for biomedical imaging and image-guided diagnosis
1 Citations2009Nikita Orlov, John Delaney +3 more
A two-stage method was employed where several types of derived images were used as inputs for a bank of feature extraction algorithms and a set of image transforms performed significantly better than aSet of image filters.