Oversampling Methods for Classification of Imbalanced Breast Cancer Malignancy Data

@inproceedings{Krawczyk2012OversamplingMF,
  title={Oversampling Methods for Classification of Imbalanced Breast Cancer Malignancy Data},
  author={B. Krawczyk and L. Jelen and A. Krzyżak and T. Fevens},
  booktitle={ICCVG},
  year={2012}
}
During breast cancer malignancy grading the main problem that has direct influence on the classification is imbalanced number of cases of the malignancy classes. This poses a challenge for pattern recognition algorithms and leads to a significant decrease of the classification accuracy for the minority class. In this paper we present an approach which ameliorates such a problem. We describe and compare several state of the art methods, that are based on the oversampling approach, i.e… Expand
12 Citations
Web–Based Framework For Breast Cancer Classification
  • 12
Computer-aided diagnosis of breast cancer based on fine needle biopsy microscopic images
  • 148
  • PDF
An evaluation of classifier ensembles for class imbalance problems
  • 2
  • PDF
Cost-sensitive decision tree ensembles for effective imbalanced classification
  • 183
  • PDF
An improved ensemble approach for imbalanced classification problems
  • B. Krawczyk, G. Schaefer
  • Computer Science
  • 2013 IEEE 8th International Symposium on Applied Computational Intelligence and Informatics (SACI)
  • 2013
  • 16
  • PDF
How divided is a cell? Eigenphase nuclei for classification of mitotic phase in cancer histology images
  • 3
Population Diversity Maintenance In Brain Storm Optimization Algorithm
  • 40
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 17 REFERENCES
Comparison of Pleomorphic and Structural Features Used for Breast Cancer Malignancy Classification
  • 7
Cost-sensitive boosting for classification of imbalanced data
  • 1,081
  • PDF
SMOTE: Synthetic Minority Over-sampling Technique
  • 10,503
  • PDF
Diversity analysis on imbalanced data sets by using ensemble models
  • S. Wang, X. Yao
  • Computer Science
  • 2009 IEEE Symposium on Computational Intelligence and Data Mining
  • 2009
  • 313
  • PDF
A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches
  • 1,471
  • PDF
SMOTEBoost: Improving Prediction of the Minority Class in Boosting
  • 1,153
  • PDF
ADASYN: Adaptive synthetic sampling approach for imbalanced learning
  • H. He, Yang Bai, E. A. Garcia, S. Li
  • Computer Science
  • 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
  • 2008
  • 1,433
  • PDF
RAMOBoost: Ranked Minority Oversampling in Boosting
  • 147
  • PDF
Combining Diverse One-Class Classifiers
  • 26
...
1
2
...