Mining hidden data to predict patient prognosis: texture feature extraction and machine learning in mammography

2018 ◽  
Author(s):  
James Leighs ◽  
Mark Halling-Brown ◽  
Mishal Patel
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Texture Feature ◽  
Texture Feature Extraction ◽  
Hidden Data ◽  
Patient Prognosis

scholarly journals Comparative Analysis of Texture Patterns on Mammograms for Classification

2021 ◽  
Vol 38 (2) ◽  
pp. 379-386
Author(s):  
Nagadevi Darapureddy ◽  
Nagaprakash Karatapu ◽  
Tirumala Krishna Battula
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Classification Accuracy ◽  
Texture Feature ◽  
Gradient Boosting ◽  
Support Vector ◽  
Texture Feature Extraction ◽  
Support Vector Classifier ◽  
Tree Classifier

Breast cancer is a cancerous tumor that arrives within the tissues of the breast. Women are mostly attacked than men. To detect early cancer medical specialists, suggest mammography for screening. Algorithms in Machine learning were executed on mammogram images to classify whether the tissues are deleterious or not. An analysis is done based on the texture feature extraction using different techniques like Frequency decoded local binary pattern (FDLBP), Local Bit-plane Decoded Pattern (LBDP), Local Diagonal Extrema Pattern (LDEP), Local Directional Order Pattern (LDOP), Local Wavelet Pattern (LWP). The features extracted are tested on 322 images from MIA’s database of three different classes. The algorithms in Machine learning like K-Nearest Neighbor classifier (KNN), Support vector classifier (SVC), Decision Tree classifier (DTC), Random Forest classifier (RFC), AdaBoost classifier (AC), Gradient Boosting classifier (GBC), Gaussian Naive Bayes classifier (GNB), Linear Discriminant Analysis classifier (LDA), Quadratic Discriminant Analysis classifier (QDA) were used to evaluate the accuracy of classification. This paper examines the comparison of accuracy using different texture features. KNN algorithm with LDEP for texture feature extraction gives classification accuracy of 64.61%, SVC with all the texture patterns mentioned gives classification accuracy of 63.07%, DTC with FDLBP, LBDP gives classification accuracy of 47.69, RFC with LBDP and AC with LDOP and GBC with FDLBP gives 61.53% classification accuracy, GNB and LDA with FDLBP gives 60% and 63.07% classification accuracy respectively, QDA with LBDP gives 64.61 classification accuracy. Of all the Algorithms support vector classifier gives good accuracy results with all the texture patterns mentioned.

Contour- and Texture-based analysis for victim identification in forensic odontology

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
G. Jaffino ◽  
J. Prabin Jose
Keyword(s):  
Feature Extraction ◽  
Texture Feature ◽  
Forensic Odontology ◽  
Individual Identification ◽  
Texture Feature Extraction ◽  
Person Identification ◽  
Content Type ◽  
Photographic Images ◽  
Shape Extraction ◽  
Contour Shape

PurposeForensic dentistry is the application of dentistry in legal proceedings that arise from any facts relating to teeth. The ultimate goal of forensic odontology is to identify the individual when there are no other means of identification such as fingerprint, Deoxyribonucleic acid (DNA), iris, hand print and leg print. The purpose of selecting dental record is for the teeth to be able to withstand decomposition, heat degradation up to 1600 °C. Dental patterns are unique for every individual. This work aims to analyze the contour shape extraction and texture feature extraction of both radiographic and photographic dental images for person identification.Design/methodology/approachTo achieve an accurate identification of individuals, the missing tooth in the radiograph has to be identified before matching of ante-mortem (AM) and post-mortem (PM) radiographs. To identify whether the missing tooth is a molar or premolar, each tooth in the given radiograph has to be classified using a k-nearest neighbor (k-NN) classifier; then, it is matched with the universal tooth numbering system. In order to make exact person identification, this research work is mainly concentrate on contour shape extraction and texture feature extraction for person identification. This work aims to analyze the contour shape extraction and texture feature extraction of both radiographic and photographic images for individual identification. Then, shape matching of AM and PM images is performed by similarity and distance metric for accurate person identification.FindingsThe experimental results are analyzed for shape and feature extraction of both radiographic and photographic dental images. From this analysis, it is proved that the higher hit rate performance is observed for the active contour shape extraction model, and it is well suited for forensic odontologists to identify a person in mass disaster situations.Research limitations/implicationsForensic odontology is a branch of human identification that uses dental evidence to identify the victims. In mass disaster circumstances, contours and dental patterns are very useful to extract the shape in individual identification.Originality/valueThe experimental results are analyzed both the contour shape extraction and texture feature extraction of both radiographic and photographic images. From this analysis, it is proved that the higher hit rate performance is observed for the active contour shape extraction model and it is well suited for forensic odontologists to identify a person in mass disaster situations. The findings provide theoretical and practical implications for individual identification of both radiographic and photographic images with a view to accurate identification of the person.

Sign in / Sign up

Export Citation Format

Share Document