Abstract
Objective To evaluate the performance of a computerized detection and classification with breast ultrasound images using the enhancement algorithm based on fuzzy logic and texture analysis.Methods Six hundred and three ultrasound images of 211 cases were analyzed including 109 benign lesionsand 102 malignant ones.The original and enhanced images were assessed by radiologists using double blind method.The pathological results were regarded as the golden standard.The diagnostic sensitivity,specificity,positive predictive value,negative predictive value and accuracy were calculated by the areas under curves(AUC)of the receiver operating characteristic curves.Results After enhancement of the breast lesions on ultrasound images,the fine details of breast lesion features were preserved by the proposed approaches while avoiding noise amplification and overenhancement,the images became distinct,and the regions became more homogeneous,and the boundaries of the regions were much clearer,and more suitable for diagnosis.The sensitivity and specificity of breast lesions on ultrasound images could be raised from 75.4%to 89.6 %,from 66.7 % to 91.2%.respectively,the diagnostic accuracy was raised from 78.20%to 89.57%,and Az of ultrasonic diagnosis also increased from 0.842 to 0.914,Z=5.101,there were significant differences in the AUC between the originaI breast Iesions and enhanced ones on ultrasound images(P<0.001).Conclusions The enhancement algorithm on breast ultrasound images were proposed and it can increase the diagnostic accuracy in differentiating benign and malignant breast lesions and decrease the rate of missing and misdiagnosis of breast lesions greatly. Key words: Ultrasonography; Breast diseases; Image enhancement
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.