Optimization of Deep Learning Network Parameters Using Uniform Experimental Design for Breast Cancer Histopathological Image Classification

Breast cancer, a common cancer type, is a major health concern in women. Recently, researchers used convolutional neural networks (CNNs) for medical image analysis and demonstrated classification performance for breast cancer diagnosis from within histopathological image datasets. However, the parameter settings of a CNN model are complicated, and using Breast Cancer Histopathological Database data for the classification is time-consuming. To overcome these problems, this study used a uniform experimental design (UED) and optimized the CNN parameters of breast cancer histopathological image classification. In UED, regression analysis was used to optimize the parameters. The experimental results indicated that the proposed method with UED parameter optimization provided 84.41% classification accuracy rate. In conclusion, the proposed method can improve the classification accuracy effectively, with results superior to those of other similar methods.

[1]  Mahua Bhattacharya,et al.  Classification of breast tumors as benign and malignant using textural feature descriptor , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[2]  Madhu S. Nair,et al.  Automatic mitosis detection in breast histopathology images using Convolutional Neural Network based deep transfer learning , 2019, Biocybernetics and Biomedical Engineering.

[3]  David Gur,et al.  Association Between Changes in Mammographic Image Features and Risk for Near-Term Breast Cancer Development , 2016, IEEE Transactions on Medical Imaging.

[4]  John Moody,et al.  Learning rate schedules for faster stochastic gradient search , 1992, Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop.

[5]  Matthias Hein,et al.  Variants of RMSProp and Adagrad with Logarithmic Regret Bounds , 2017, ICML.

[6]  Data on the optimization of the formula of Xiaokeyinshui extract combination treating diabetes mellitus using uniform experimental design in mice , 2020, Data in brief.

[7]  Junxian Yun,et al.  Optimizational production of phenyllactic acid by a Lactobacillus buchneri strain via uniform design with overlay sampling methodology , 2019, Chinese Journal of Chemical Engineering.

[8]  Yinan Kong,et al.  Histopathological Breast-Image Classification Using Local and Frequency Domains by Convolutional Neural Network , 2018, Inf..

[9]  Luiz Eduardo Soares de Oliveira,et al.  A Dataset for Breast Cancer Histopathological Image Classification , 2016, IEEE Transactions on Biomedical Engineering.

[10]  Francisco Herrera,et al.  BreakHis based breast cancer automatic diagnosis using deep learning: Taxonomy, survey and insights , 2020, Neurocomputing.

[11]  Rajesh Mehra,et al.  Breast cancer histology images classification: Training from scratch or transfer learning? , 2018, ICT Express.

[12]  Yunjiang Yu,et al.  Rapid and simultaneous analysis of tetrabromobisphenol A and hexabromocyclododecane in water by direct immersion solid phase microextraction: Uniform design to explore factors. , 2019, Ecotoxicology and environmental safety.

[13]  Gang Xu,et al.  Level permutation method for constructing uniform designs under the wrap-around L2-discrepancy , 2014, J. Complex..

[14]  Xiaoli Yang,et al.  An efficient uniform design for Kriging-based response surface method and its application , 2019, Computers and Geotechnics.

[15]  George Lee,et al.  Image analysis and machine learning in digital pathology: Challenges and opportunities , 2016, Medical Image Anal..

[16]  R. Balkrishnan,et al.  A cost-effectiveness analysis of trastuzumab-containing treatment sequences for HER-2 positive metastatic breast cancer patients in Taiwan , 2019, Breast.

[17]  Ehsan Kazemi,et al.  Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images , 2017, bioRxiv.

[18]  Some properties of double designs in terms of lee discrepancy , 2017 .

[19]  Lilly Suriani Affendey,et al.  Classification of Histopathology Images of Breast into Benign and Malignant using a Single-layer Convolutional Neural Network , 2017, ICISPC 2017.

[20]  Zhengnong Li,et al.  Wind tunnel test study on wind load coefficients variation law of heliostat based on uniform design method , 2019, Solar Energy.

[21]  Arun Kumar Sangaiah,et al.  Deep feature learning for histopathological image classification of canine mammary tumors and human breast cancer , 2020, Inf. Sci..

[22]  Yanan Xu,et al.  Background classification method based on deep learning for intelligent automotive radar target detection , 2019, Future Gener. Comput. Syst..

[23]  Yu-Yen Ou,et al.  iMotor-CNN: Identifying molecular functions of cytoskeleton motor proteins using 2D convolutional neural network via Chou's 5-step rule. , 2019, Analytical biochemistry.

[24]  Cheng-Jian Lin,et al.  Using Feature Fusion and Parameter Optimization of Dual-input Convolutional Neural Network for Face Gender Recognition , 2020 .

[25]  Zafer Cömert,et al.  BreastNet: A novel convolutional neural network model through histopathological images for the diagnosis of breast cancer , 2020 .

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Subaji Mohan,et al.  NROI based feature learning for automated tumor stage classification of pulmonary lung nodules using deep convolutional neural networks , 2019, Journal of King Saud University - Computer and Information Sciences.

[28]  Dinggang Shen,et al.  Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation , 2017, Comput. Medical Imaging Graph..

[29]  Philip Davies,et al.  Uniform design for the optimization of Al2O3 nanofilms produced by electrophoretic deposition , 2016 .

[31]  Hongfei Lin,et al.  Application of uniform design experimental method in waste cooking oil (WCO) co-hydroprocessing parameter optimization and reaction route investigation , 2017 .