An Extended Genetic Algorithm Based Gene Selection Framework for Cancer Diagnosis

Yan, Ke; Lu, Huijuan

doi:10.1109/itme.2018.00021

Cited by 6 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Fig. 8b, GBDT-MVO reach (22) Also, these results proved that our initial objective was realized-improved diagnosis accuracy with reduced diagnosis variance. As illustrated in Fig.…”

Section: Resultssupporting

confidence: 64%

“…In addition, most of the rules or mathematical equations used by most of the metaheuristic methods have been inspired by the living and survival systems of insects, animals, and birds. Due to the noticeable success of metaheuristic algorithms in solving a lot of optimization problems in a wide range of applications, there are various types of metaheuristic algorithms include Genetic algorithm [21,22], Firefly Algorithm [23], Particle swarm optimization [24,25], Ant Colony Optimization [26], Bat algorithm [27], Whale Optimization Algorithm [28], Artificial fish swarm [29], and Grey wolf optimizer [30] has been extensively reported in recent literature. To classify breast tumors into cancerous and non-cancerous ones, an ensemble learning method was proposed by Vinod Jagannath Kadam et al [17] based on SoftMax Regression and Sparse Autoencoders.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Breast cancer diagnosis using a multi-verse optimizer-based gradient boosting decision tree

Tabrizchi

2020

SN Appl. Sci.

View full text Add to dashboard Cite

Breast cancer is among the most common cancers women got, which can be effectively cured providing that it is diagnosed at the early stages. In the current study, we attempted to classify breast cancer into two groups of malignant and benign by proposing a new ensemble learning method using Multi-Verse Optimizer (MVO) and Gradient Boosting Decision Tree (GBDT). Moreover, the prediction rate of GBDT has been shown to be desirable, its efficiency and classification accuracy are significantly dependent on feature selection and parameter setting. Based on the MVO, we attempted to propose an efficient approach to optimize feature selection and GBDT's parameters at the same time. In other words, the MVO algorithm is able to play the role of a tuner to set the GBDT's main parameters and optimize feature selection results. To implement and test the proposed approach, standard criteria (i.e. accuracy, sensitivity, specificity, etc.) was used for performance evaluation. Also, the datasets of Wisconsin Diagnostic Breast Cancer and Wisconsin Breast Cancer were considered for this purpose. Comparing the results of GBDT-MVO model with other proposed models demonstrated that this model is more precise and has considerably lower variance in the case of a breast cancer diagnosis.

show abstract

Section: Resultssupporting

confidence: 64%

Section: Related Workmentioning

confidence: 99%

Breast cancer diagnosis using a multi-verse optimizer-based gradient boosting decision tree

Tabrizchi

2020

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…Alternatively, some hybrid approaches include genetic algorithms to limit the computational costs while evaluating a broader space of possible solutions, as in [7], [8]. Particularly, MOGA approaches have recently raised an increasing interest in gene expression-based classification or clustering tasks [10]- [13], since gene selection problems can be approached from a multi-objective perspective, typically maximizing a performance measure while minimizing the amount of genes retained.…”

Section: Related Workmentioning

confidence: 99%

“…For intrinsically complex, high and heavily unbalanced dimensionalities, as in gene expression datasets, a fourth category has been emerging: hybrid methods; they combine several feature selection and optimization approaches to speed up and improve gene selection. In this trend, genetic algorithms (GA) have become very popular optimization techniques dealing with gene expression data (e.g., see [7], [8]), particularly Multi-Objective Genetic Algorithms (MOGA) [9]- [13], which can simultaneously optimize conflicting objectives and find a set of relevant solutions. This enables comparing more and different solutions from a wider range of evaluations, without severely impact the computational costs.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Evolutionary Framework for Selection of Genes Predicting Breast Cancer Relapse

Perino

Cascianelli

Masseroli

2020

2020 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Predicting relapse events is still one of the major challenges for breast cancer research. Despite gene expressionbased classifiers may tackle this task, working on thousands of genes and only few samples jeopardizes the performances of a classifier trained without a proper gene selection. We propose a novel hybrid evolutionary gene selection framework, which uses a Multi-Objective Genetic Algorithm (MOGA) to search a wider range of gene selections and handles MOGA results in a whole new way, so as to overcome the limit of the non-easy interpretability of the MOGA broad set of solutions. To a classifier our framework provides a gene signature not only bringing the best cross-validation result, but also having noteworthy and robust performances when tested on unseen samples of an hold-out set. The robustness in hold-out showed the strength of our innovative key element: the final module of the framework, which fully exploits the high variability of MOGA outputs, rather than choosing just one of the solutions, as commonly done in the literature. It combines all MOGA results in more robust and compact gene occurrence-based signatures, under the reasonable assumption that highly recurrent genes have a more crucial biological role, more suitable clinical application and good discriminative power between relapsed and relapse-free patients, as confirmed by the obtained classification results.

show abstract

A Deep Learning Method for Pneumonia Detection Based on Fuzzy Non-Maximum Suppression

Wang

Ping

et al. 2024

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

An Extended Genetic Algorithm Based Gene Selection Framework for Cancer Diagnosis

Cited by 6 publications

References 24 publications

Breast cancer diagnosis using a multi-verse optimizer-based gradient boosting decision tree

Breast cancer diagnosis using a multi-verse optimizer-based gradient boosting decision tree

Hybrid Evolutionary Framework for Selection of Genes Predicting Breast Cancer Relapse

A Deep Learning Method for Pneumonia Detection Based on Fuzzy Non-Maximum Suppression

Contact Info

Product

Resources

About