Combination of loss functions for robust breast cancer prediction

Abstract Cancer detection can be formulated as a binary classification in a machine learning paradigm. Loss functions are a critical part of almost every machine learning algorithm. While each loss function comes up with its own advantages and disadvantages, in this paper, inspired by ensemble methods, we propose a novel objective function that is a linear combination of single losses. We then integrate the proposed objective function into an Artificial Neural Network (ANN) to diagnose breast cancer. By doing so, both the coefficients of loss functions and weight parameters of the ANN are learned jointly via backpropagation. As the patients’ data are sometimes very noisy, we evaluate our method by doing comprehensive experiments on Wisconsin Breast Cancer Diagnosis (WBCD) dataset at different noise levels. The experiments show its performance declines very slowly (from 0.97 to 0.96) compared to the peer methods with the increase of noise level.

[1]  Zidong Wang,et al.  Machine Learning with Applications in Breast Cancer Diagnosis and Prognosis , 2018 .

[2]  Bartosz Krawczyk,et al.  On the Influence of Class Noise in Medical Data Classification: Treatment Using Noise Filtering Methods , 2016, Appl. Artif. Intell..

[3]  Abdulhamit Subasi,et al.  Normalized Neural Networks for Breast Cancer Classification , 2019 .

[4]  John DeNero,et al.  L1 and L2 regularization for multiclass hinge loss models , 2011, MLSLP.

[5]  Dimitrios I. Fotiadis,et al.  Machine learning applications in cancer prognosis and prediction , 2014, Computational and structural biotechnology journal.

[6]  Shanmugam Veeramani,et al.  Machine Learning Classification Techniques for Breast Cancer Diagnosis , 2019, IOP Conference Series: Materials Science and Engineering.

[7]  Shahaboddin Shamshirband,et al.  Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine, artificial neural network and genetic programming , 2016, Neural Computing and Applications.

[8]  Factors associated with de novo metastatic disease in invasive breast cancer: comparison of artificial neural network and logistic regression models , 2019 .

[9]  Aruna Tiwari,et al.  Breast cancer diagnosis using Genetically Optimized Neural Network model , 2015, Expert Syst. Appl..

[10]  D. Hanahan,et al.  Hallmarks of Cancer: The Next Generation , 2011, Cell.

[11]  Mehrbakhsh Nilashi,et al.  A knowledge-based system for breast cancer classification using fuzzy logic method , 2017, Telematics Informatics.

[12]  Amir Hossein Zaji,et al.  Prediction of scour depth around bridge piers using self-adaptive extreme learning machine , 2017 .

[13]  Khin Mo Mo Tun,et al.  AN APPROACH FOR BREAST CANCER DIAGNOSIS CLASSIFICATION USING NEURAL NETWORK , 2015 .

[14]  Kemal Polat,et al.  A Novel ML Approach to Prediction of Breast Cancer: Combining of mad normalization, KMC based feature weighting and AdaBoostM1 classifier , 2018, 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT).

[15]  Bahram Gharabaghi,et al.  Estimation of the Darcy–Weisbach friction factor for ungauged streams using Gene Expression Programming and Extreme Learning Machines , 2019, Journal of Hydrology.

[16]  Aytug Onan,et al.  A fuzzy-rough nearest neighbor classifier combined with consistency-based subset evaluation and instance selection for automated diagnosis of breast cancer , 2015, Expert Syst. Appl..

[17]  Sang Won Yoon,et al.  Breast cancer diagnosis based on feature extraction using a hybrid of K-means and support vector machine algorithms , 2014, Expert Syst. Appl..

[18]  Babak Bashari Rad,et al.  Early Detection of Breast Cancer Using Machine Learning Techniques , 2018 .

[19]  Kazushi Ikeda,et al.  Minimum Proper Loss Estimators for Parametric Models , 2016, IEEE Transactions on Signal Processing.

[20]  Hana Sahinbegovic,et al.  Using machine learning tool in classification of breast cancer , 2017 .

[21]  Sudha Gupta,et al.  Brain tumor prediction and classification using support vector machine , 2017, 2017 International Conference on Advances in Computing, Communication and Control (ICAC3).

[22]  Deepa Naishadham,et al.  Cancer statistics for Hispanics/Latinos, 2012 , 2012, CA: a cancer journal for clinicians.

[23]  Canlong Zhang,et al.  A New multi-instance multi-label learning approach for image and text classification , 2016, Multimedia Tools and Applications.

[24]  Hajar Mousannif,et al.  Using Machine Learning Algorithms for Breast Cancer Risk Prediction and Diagnosis , 2016, ANT/SEIT.

[25]  Akif Durdu,et al.  Breast Cancer Diagnosis by Different Machine Learning Methods Using Blood Analysis Data , 2018, International Journal of Intelligent Systems and Applications in Engineering.

[26]  Reza Monsefi,et al.  Layered Geometric Learning , 2019, ICAISC.

[27]  Diego Mollá Aliod,et al.  On Extending Neural Networks with Loss Ensembles for Text Classification , 2017, ALTA.

[28]  Ulas Bagci,et al.  Deep learning beyond cats and dogs: recent advances in diagnosing breast cancer with deep neural networks. , 2018, The British journal of radiology.

[29]  Panos M. Pardalos,et al.  Ramp-loss nonparallel support vector regression: Robust, sparse and scalable approximation , 2018, Knowl. Based Syst..