An interval prototype classifier based on a parameterized distance applied to breast thermographic images

Breast cancer is one of the leading causes of death in women. Because of this, thermographic images have received a refocus for diagnosing this cancer type. This work proposes an innovative approach to classify breast abnormalities (malignant, benignant and cyst), employing interval temperature data in order to detect breast cancer. The learning step takes into account the internal variation of the intervals when describing breast abnormalities and uses a way to map these intervals into a space where they can be more easily separated. The method builds class prototypes, and the allocation step is based on a parameterized Mahalanobis distance for interval-valued data. The proposed classifier is applied to a breast thermography dataset from Brazil with 50 patients. We investigate two different scenarios for parameter configuration. The first scenario focuses on the overall misclassification rate and achieves 16 % misclassification rate and 93 % sensitivity to the malignant class. The second scenario maximizes the sensitivity to the malignant class, achieving 100 % sensitivity to this specific class, along with 20 % overall misclassification rate. We compare the performances of our approach and of many methods taken from the literature of interval data classification for the breast thermography task. Results show that our method outperforms competing algorithms.

[1]  Sushmita Mitra,et al.  Symbolic classification, clustering and fuzzy radial basis function network , 2005, Fuzzy Sets Syst..

[2]  Gerald Schaefer,et al.  Thermography based breast cancer analysis using statistical features and fuzzy classification , 2009, Pattern Recognit..

[3]  Hairong Qi,et al.  Asymmetry analysis in breast cancer detection using thermal infrared images , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[4]  E. Y.-K. Ng,et al.  A review of thermography as promising non-invasive detection modality for breast tumor , 2009 .

[5]  Pragati Kapoor,et al.  Image processing for early diagnosis of breast cancer using infrared images , 2010, 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE).

[6]  Manabu Ichino,et al.  A Fuzzy Symbolic Pattern Classifier , 1996 .

[7]  Marcus C. Araújo,et al.  Interval symbolic feature extraction for thermography breast cancer detection , 2014, Expert Syst. Appl..

[8]  Monique Noirhomme-Fraiture,et al.  Symbolic Data Analysis and the SODAS Software , 2008 .

[9]  Donato Malerba,et al.  Classification of symbolic objects: A lazy learning approach , 2006, Intell. Data Anal..

[10]  Yves Lechevallier,et al.  Dynamic Cluster Methods for Interval Data Based on Mahalanobis Distances , 2004 .

[11]  Javier Arroyo,et al.  iMLP: Applying Multi-Layer Perceptrons to Interval-Valued Data , 2007, Neural Processing Letters.

[12]  Qing Wang,et al.  Morphological measurement of localized temperature increase amplitudes in breast infrared thermograms and its clinical application , 2008, Biomed. Signal Process. Control..

[13]  Renata M. C. R. de Souza,et al.  Logistic regression-based pattern classifiers for symbolic interval data , 2011, Pattern Analysis and Applications.

[14]  Telmo de Menezes e Silva Filho,et al.  Fuzzy learning vector quantization approaches for interval data , 2013, 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[15]  Rangaraj M. Rangayyan,et al.  Classification of breast masses in mammograms using genetic programming and feature selection , 2006, Medical and Biological Engineering and Computing.

[16]  Asnida Abd Wahab,et al.  Thermal distribution analysis of three-dimensional tumor-embedded breast models with different breast density compositions , 2015, Medical & Biological Engineering & Computing.

[17]  Aura Conci,et al.  Breast thermography from an image processing viewpoint: A survey , 2013, Signal Process..

[18]  U. Rajendra Acharya,et al.  Thermography Based Breast Cancer Detection Using Texture Features and Support Vector Machine , 2012, Journal of Medical Systems.

[19]  Rangaraj M. Rangayyan,et al.  Multimodality Breast Imaging: Diagnosis and Treatment , 2013 .

[20]  A.C. Frery,et al.  Symbolic approach to SAR image classification , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[21]  Fabrice Rossi,et al.  Multi-layer Perceptron on Interval Data ? , 2002 .

[22]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[23]  U. Rajendra Acharya,et al.  Data mining technique for breast cancer detection in thermograms using hybrid feature extraction strategy , 2012 .

[24]  Paula Brito,et al.  Linear discriminant analysis for interval data , 2006, Comput. Stat..

[25]  Gerald Schaefer,et al.  Breast thermogram analysis using a cost-sensitive multiple classifier system , 2012, Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics.

[26]  Hiok Chai Quek,et al.  A novel cognitive interpretation of breast cancer thermography with complementary learning fuzzy neural memory structure , 2007, Expert Systems with Applications.

[27]  Francisco de A. T. de Carvalho,et al.  Classification of SAR Images Through a Convex Hull Region Oriented Approach , 2004, ICONIP.

[28]  D. B. Plewes,et al.  Role of equalisation mammography of dense breasts , 2006, Medical and Biological Engineering and Computing.

[29]  Edwin Diday,et al.  Growing a tree classifier with imprecise data , 2000, Pattern Recognit. Lett..

[30]  M. Sasikala,et al.  Automatic detection of abnormal breast thermograms using asymmetry analysis of texture features , 2013, Journal of medical engineering & technology.

[31]  Rangaraj M. Rangayyan,et al.  Infrared Imaging for Breast Cancer Detection with Proper Selection of Properties: From Acquisition Protocol to Numerical Simulation , 2013 .

[32]  Rangaraj M. Rangayyan,et al.  Review of recent advances in segmentation of the breast boundary and the pectoral muscle in mammograms , 2015, Medical & Biological Engineering & Computing.