Breast Cancer Image Classification based on CNN and Bit-Plane slicing

In this paper we propose a CNN classifier base on image bit-plane slicing. The purpose is to improve recognition accuracy when we apply it to breast cancer images classification. Each texture image is decomposed into eight bit-plane images. Different bit-planes provide different levels and detail of image texture feature. At the same time, we have also tested feature classification performance by each bit-plane respectively and the fusion of all bit-planes. CNN classifier is used for classification and recognition. The simulation results on the breast cancer image datasets show that the proposed method on some bit-plane can greatly improve recognition rate and promote classification performance.

[1]  Jing Zhao,et al.  Image classification toward breast cancer using deeply-learned quality features , 2019, J. Vis. Commun. Image Represent..

[2]  Şaban Öztürk,et al.  HIC-net: A deep convolutional neural network model for classification of histopathological breast images , 2019, Comput. Electr. Eng..

[3]  Bhargab B. Bhattacharya,et al.  Stacked Euler Vector (SERVE): A Gray-Tone Image Feature Based on Bit-Plane Augmentation , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Therry Z. Lee,et al.  Face and palmprint multimodal biometric system based on bit-plane decomposition approach , 2016, 2016 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW).

[5]  Shuli Wang,et al.  Texture classification by multifractal spectrum and barycentric coordinates of bit planes of wavelet coefficients , 2017, IET Image Process..

[6]  Sung-Jea Ko,et al.  Eigen directional bit-planes for robust face recognition , 2014, IEEE Transactions on Consumer Electronics.

[7]  Khaled F. Hussain,et al.  The achievement of higher flexibility in multiple-choice-based tests using image classification techniques , 2019, International Journal on Document Analysis and Recognition (IJDAR).

[8]  Muhammad Hussain,et al.  Deep Learning based Computer-Aided Diagnosis Systems for Diabetic Retinopathy: A Survey , 2018, Artif. Intell. Medicine.

[9]  Haodong Wang,et al.  Image classification toward lung cancer recognition by learning deep quality model , 2019, J. Vis. Commun. Image Represent..

[10]  B. K. Tripathy,et al.  A novel fuzzy c-means approach with bit plane algorithm for classification of medical images , 2013, 2013 IEEE International Conference ON Emerging Trends in Computing, Communication and Nanotechnology (ICECCN).

[11]  Yu Gan,et al.  Fully Automated Postlumpectomy Breast Margin Assessment Utilizing Convolutional Neural Network Based Optical Coherence Tomography Image Classification Method. , 2020, Academic radiology.

[12]  K. Rhee.  Forensic Detection Using Bit-Planes Slicing of Median Filtering Image , 2019, IEEE Access.

[13]  Leonardo Vidal Batista,et al.  Information Theory-Based Detection of Noisy Bit Planes in Medical Images , 2016, 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI).

[14]  Chong-Sze Tong,et al.  Statistical Properties of Bit-Plane Probability Model and Its Application in Supervised Texture Classification , 2008, IEEE Transactions on Image Processing.

[15]  Nitin Khanna,et al.  First Steps Toward CNN based Source Classification of Document Images Shared Over Messaging App , 2018, Signal Process. Image Commun..

[16]  Hu Liang,et al.  Object recognition using rotation invariant local binary pattern of significant bit planes , 2016, IET Image Process..

[17]  Rabul Hussain Laskar,et al.  Multi-Level Analysis of Bit-Plane Based GLAC Feature and other Existing Texture Features for a Robust Hand Detection System , 2018, 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI).