Abstract
In this study, computer-aided detection (CADe) system is optimized to reduce radiologists’ workload and to improve accuracy of cancer detection by providing more quantitative (objective) decisions added to the qualitative (subjective) assessment of radiologists. The images have been collected from MIAS database. 3 databases were prepared by 3 different ROIs sizes (32x32, 42x42 & 52x52 pixels). Then, prepressing is done to enhance the peripheral of ROIs. This CADe computed parametric features from ROIs using statistics, histogram, GLCM and wavelet techniques. Sequential Forward Selection (SFS) technique is used to study the significance of features and eventually to omit redundancies. Several types of K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) classifiers were trained to differentiate between normal and abnormal ROIs, then tested on another non-training set. Best overall performance results obtained with ROI size of 32x32 and histogram of 32 levels (Accuracy = 97.37%, Sensitivity= 95%, Specificity = 100%, PPV = 100% and NPV = 94.74). The results also indicate some useful features are well-representing to abnormalities across different classifiers such as: Mean, STD, Square of STD, Mode, Median, Quantile (10%), Quantile (70%), Quantile (90%), Percentile (30%), throughout multiple histogram levels both in spatial and DWT spaces.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering and Advanced Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
