Deep Stacked Ensemble for Breast Cancer Diagnosis

Alaoui, Omar El; Zerouaoui, Hasnae; Idri, Ali

doi:10.1007/978-3-031-04826-5_44

Cited by 5 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the ensembles were clustered using the SK test based on accuracy and the ensembles belonging to the best SK cluster were ranked using the Borda count voting method based on the four performance metrics in order to identify which ensemble outperformed others (RQ3). Finally, to validate the designed DHHtE, we compare them with deep stacked ensembles developed in the study (El Alaoui et al , 2022) using SK test and Borda count voting method (RQ4).…”

Section: Resultsmentioning

confidence: 99%

“…To assist the reader and shorten the names of the designed stacked ensembles, we keep the same abbreviation used in the original paper (El Alaoui et al , 2022).…”

Section: Empirical Designmentioning

confidence: 99%

“…For each MF, apply SK test on the best DHHtE of step 6 and the deep stacking ensembles of the study (El Alaoui et al , 2022) based on accuracy. Apply Borda count voting method on the techniques belonging to the best SK cluster based on the four performance measures.…”

Section: Empirical Designmentioning

confidence: 99%

“…The main contributions of this empirical study are the following:Proposing a new approach of ensemble learning methods by combining deep hybrid architectures as base learners designed using the most recent DL methods for FE and well know ML models for classification with two combination methods (hard and weighted voting).Evaluating whether DHHtE outperforms the hybrid architectures used as base learners.Evaluating whether DHHtE designed using the hard voting outperforms the ones using weighted voting.Evaluating whether the best DHHtE outperforms the best deep stacked ensemble of the study (El Alaoui et al , 2022). Evaluating the performances of the DHHtE using statistical tests such as Scott–Knott (SK) test and Borda count voting methods.…”

Section: Introductionmentioning

confidence: 99%

“…Table I presents the main findings of six selected relevant articles dealing with the use of ensembles in the medical field for BC diagnoses (Ahmed and El Sadig, 2019;Hameed et al, 2020;Idri et al, 2020;Kassani et al, 2020;El Ouassif et al, 2021;Xiao et al, 2017), (El Alaoui et al, 2022). The following are observed:…”

mentioning

confidence: 98%

See 4 more Smart Citations

A new approach for histological classification of breast cancer using deep hybrid heterogenous ensemble

Zerouaoui

Idri

Alaoui³

2022

DTA

Self Cite

View full text Add to dashboard Cite

PurposeHundreds of thousands of deaths each year in the world are caused by breast cancer (BC). An early-stage diagnosis of this disease can positively reduce the morbidity and mortality rate by helping to select the most appropriate treatment options, especially by using histological BC images for the diagnosis.Design/methodology/approachThe present study proposes and evaluates a novel approach which consists of 24 deep hybrid heterogenous ensembles that combine the strength of seven deep learning techniques (DenseNet 201, Inception V3, VGG16, VGG19, Inception-ResNet-V3, MobileNet V2 and ResNet 50) for feature extraction and four well-known classifiers (multi-layer perceptron, support vector machines, K-nearest neighbors and decision tree) by means of hard and weighted voting combination methods for histological classification of BC medical image. Furthermore, the best deep hybrid heterogenous ensembles were compared to the deep stacked ensembles to determine the best strategy to design the deep ensemble methods. The empirical evaluations used four classification performance criteria (accuracy, sensitivity, precision and F1-score), fivefold cross-validation, Scott–Knott (SK) statistical test and Borda count voting method. All empirical evaluations were assessed using four performance measures, including accuracy, precision, recall and F1-score, and were over the histological BreakHis public dataset with four magnification factors (40×, 100×, 200× and 400×). SK statistical test and Borda count were also used to cluster the designed techniques and rank the techniques belonging to the best SK cluster, respectively.FindingsResults showed that the deep hybrid heterogenous ensembles outperformed both their singles and the deep stacked ensembles and reached the accuracy values of 96.3, 95.6, 96.3 and 94 per cent across the four magnification factors 40×, 100×, 200× and 400×, respectively.Originality/valueThe proposed deep hybrid heterogenous ensembles can be applied for the BC diagnosis to assist pathologists in reducing the missed diagnoses and proposing adequate treatments for the patients.

show abstract

Section: Resultsmentioning

confidence: 99%

“…To assist the reader and shorten the names of the designed stacked ensembles, we keep the same abbreviation used in the original paper (El Alaoui et al , 2022).…”

Section: Empirical Designmentioning

confidence: 99%

Section: Empirical Designmentioning

confidence: 99%