Classification of breast and colorectal tumors based on percolation of color normalized images

Abstract Percolation is a fractal descriptor that has been applied recently on computer vision problems. We applied this descriptor on 58 colored histological breast images, and 165 colored histological colorectal images, both stained with Hematoxylin and Eosin, in order to extract features to differentiate between benign and malignant cases. The experiments were also performed over normalized images, aiming to analyze the influence of different color normalization techniques on percolation-based features and whether they can provide better classification results. The feature sets obtained from the application of the method on the original images and on the normalized images with three different techniques were tested using 12 different classifiers. We compared the obtained results with other relevant methods in the area and observed significant contributions, with AUC rates above 0.900 in both normalized and non-normalized images. We also verified that color normalization does not contribute to the classification of breast tumors when associated with percolation features. However, color normalized images from the colorectal tumor’s dataset provided better results than the original images.

[1]  J. Griggs,et al.  Quality of life and metastatic breast cancer: the role of body image, disease site, and time since diagnosis , 2015, Quality of Life Research.

[2]  B. S. Manjunath,et al.  Evaluation and benchmark for biological image segmentation , 2008, 2008 15th IEEE International Conference on Image Processing.

[3]  Konstantinos N. Plataniotis,et al.  A Complete Color Normalization Approach to Histopathology Images Using Color Cues Computed From Saturation-Weighted Statistics , 2015, IEEE Transactions on Biomedical Engineering.

[4]  Alexander Rakhlin,et al.  Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis , 2018 .

[5]  Evangelia I. Zacharaki,et al.  Tensor Decomposition for Multiple-Instance Classification of High-Order Medical Data , 2018, Complex..

[6]  Huijuan Lu,et al.  A cost-sensitive rotation forest algorithm for gene expression data classification , 2017, Neurocomputing.

[7]  J. Martín-Herrero,et al.  Alternative techniques for cluster labelling on percolation theory , 2000 .

[8]  J. Ross Quinlan,et al.  Learning decision tree classifiers , 1996, CSUR.

[9]  Saeed Hassanpour,et al.  Deep Learning for Classification of Colorectal Polyps on Whole-slide Images , 2017, Journal of pathology informatics.

[10]  Dan Schonfeld,et al.  Color normalization of histology slides using graph regularized sparse NMF , 2017, Medical Imaging.

[11]  Nasir M. Rajpoot,et al.  A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution , 2014, IEEE Transactions on Biomedical Engineering.

[12]  Hao Chen,et al.  Gland segmentation in colon histology images: The glas challenge contest , 2016, Medical Image Anal..

[13]  M. Ivanovici,et al.  Psoriasis image analysis using color lacunarity , 2012, 2012 13th International Conference on Optimization of Electrical and Electronic Equipment (OPTIM).

[14]  Marko Robnik-Sikonja,et al.  Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF , 2004, Applied Intelligence.

[15]  Mihai Ivanovici,et al.  The lacunarity of colour fractal images , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[16]  Fan Yang,et al.  Breast cancer classification in pathological images based on hybrid features , 2019, Multimedia Tools and Applications.

[17]  Phedias Diamandis,et al.  Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction , 2018, BMC Bioinformatics.

[18]  Alessandro Santana Martins,et al.  Classification of colorectal cancer based on the association of multidimensional and multiresolution features , 2019, Expert Syst. Appl..

[19]  Marko Robnik-Sikonja,et al.  An adaptation of Relief for attribute estimation in regression , 1997, ICML.

[20]  David B. A. Epstein,et al.  Glandular Morphometrics for Objective Grading of Colorectal Adenocarcinoma Histology Images , 2017, Scientific Reports.

[21]  Rebecca Richards-Kortum,et al.  Micro-anatomical quantitative optical imaging: toward automated assessment of breast tissues , 2015, Breast Cancer Research.

[22]  Tommy Löfstedt,et al.  Gray-level invariant Haralick texture features , 2019, PloS one.

[23]  Alessandro Santana Martins,et al.  Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images , 2018, SIBGRAPI.

[24]  Ghassan Hamarneh,et al.  Adversarial Stain Transfer for Histopathology Image Analysis , 2018, IEEE Transactions on Medical Imaging.

[25]  Lee A. D. Cooper,et al.  Vectorized persistent homology representations for characterizing glandular architecture in histology images , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[26]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[27]  Nemanja Rajkovic,et al.  Analysis of Histopathology Images by the Use of Monofractal and Multifractal Algorithms , 2017, 2017 21st International Conference on Control Systems and Computer Science (CSCS).

[28]  Riku Turkki,et al.  Breast cancer outcome prediction with tumour tissue images and machine learning , 2019, Breast Cancer Research and Treatment.

[29]  Divya Jain,et al.  An Efficient Hybrid Feature Selection model for Dimensionality Reduction , 2018 .

[30]  Melih Kandemir,et al.  Empowering Multiple Instance Histopathology Cancer Diagnosis by Cell Graphs , 2014, MICCAI.

[31]  Nassir Navab,et al.  Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images , 2016, IEEE Transactions on Medical Imaging.

[32]  Rabi Yacoub,et al.  Multi-radial LBP Features as a Tool for Rapid Glomerular Detection and Assessment in Whole Slide Histopathology Images , 2017, Scientific Reports.

[33]  Nasir M. Rajpoot,et al.  Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images , 2016, IEEE Trans. Medical Imaging.

[34]  Konstantinos N. Plataniotis,et al.  Color model comparative analysis for breast cancer diagnosis using H and E stained images , 2015, Medical Imaging.

[35]  Banshidhar Majhi,et al.  Automated pathological brain detection system: A fast discrete curvelet transform and probabilistic neural network based approach , 2017, Expert Syst. Appl..

[36]  Alessandro Santana Martins,et al.  Features based on the percolation theory for quantification of non-Hodgkin lymphomas , 2017, Comput. Biol. Medicine.

[37]  Alaattin Erkanli,et al.  Rapid staining and imaging of subnuclear features to differentiate between malignant and benign breast tissues at a point-of-care setting , 2016, Journal of Cancer Research and Clinical Oncology.

[38]  J. Angel Arul Jothi,et al.  A survey on automated cancer diagnosis from histopathology images , 2017, Artificial Intelligence Review.

[39]  Leandro Alves Neves,et al.  Computational normalization of H&E-stained histological images: Progress, challenges and future potential , 2019, Artif. Intell. Medicine.

[40]  Raymond J. Mooney,et al.  Constructing Diverse Classifier Ensembles using Artificial Training Examples , 2003, IJCAI.

[41]  Leandro Alves Neves,et al.  Multidimensional and fuzzy sample entropy (SampEnMF) for quantifying H&E histological images of colorectal cancer , 2018, Comput. Biol. Medicine.

[42]  R. M. Nogueira,et al.  Fractal Dimension in Liver Histological Findings of Wistar Rats Experimentally Intoxicated with Venom of Crotalus durissus terrificus , 2019, Acta Scientiae Veterinariae.

[43]  Mihai Ivanovici,et al.  Fractal Dimension of Color Fractal Images , 2011, IEEE Transactions on Image Processing.

[44]  Anne M. Denton,et al.  Lazy Classifiers Using P-trees , 2002, CAINE.

[45]  Allen G. Hunt,et al.  SATURATION DEPENDENCE OF TRANSPORT IN POROUS MEDIA PREDICTED BY PERCOLATION AND EFFECTIVE MEDIUM THEORIES , 2015 .

[46]  Kaushal K. Shukla,et al.  Classification of Histopathological images of Breast Cancerous and Non Cancerous Cells Based on Morphological features , 2017 .

[47]  Andrew Y. Ng,et al.  Preventing "Overfitting" of Cross-Validation Data , 1997, ICML.

[48]  Bernard Manderick,et al.  An adaptive rule-based classifier for mining big biological data , 2016, Expert Syst. Appl..

[49]  Murat Karabatak,et al.  A new classifier for breast cancer detection based on Naïve Bayesian , 2015 .

[50]  Bora Korkmazer,et al.  Use of shear wave elastography to differentiate benign and malignant breast lesions. , 2014, Diagnostic and interventional radiology.