Agreement in breast lesion assessment and final BI-RADS classification between radial and meander-like breast ultrasound

Background This study prospectively investigates the agreement between radial (r-US) and meander-like (m-US) breast ultrasound with regard to lesion location, lesion size, morphological characteristics and final BI-RADS classification of individual breast lesions. Methods Each patient of a consecutive, unselected, mixed collective received a dual ultrasound examination. Results The agreement between r-US and m-US for lesion location ranged from good (lesion to mammilla distance ICC 0.64; lesion to skin distance ICC 0.72) to substantial (clock-face localization κ 0.70). For lesion size the agreement was good (diameter ICC 0.72; volume ICC 0.69), for lesion margin and architectural distortion it was substantial (κ 0.68 and 0.70, respectively). Most importantly, there was a substantial agreement (κ 0.76) in the final BI-RADS classification between r-US and m-US. Conclusions Our recent comparison of radial and meander-like breast US revealed that the diagnostic accuracy of the two scanning methods was comparable. In this study, we observe a high degree of agreement between m-US and r-US for the lesion description (location, size, morphology) and final BI-RADS classification. These findings corroborate that r-US is a suitable alternative to m-US in daily clinical practice. Trial registration NCT02358837. Registered January 2015, retrospectively registered https://clinicaltrials.gov/ct2/results?cond=&term=NCT02358837&cntry=&state=&city=&dist=

Postprocessing for Skin Detection

Skin detectors play a crucial role in many applications: face localization, person tracking, objectionable content screening, etc. Skin detection is a complicated process that involves not only the development of apposite classifiers but also many ancillary methods, including techniques for data preprocessing and postprocessing. In this paper, a new postprocessing method is described that learns to select whether an image needs the application of various morphological sequences or a homogeneity function. The type of postprocessing method selected is learned based on categorizing the image into one of eleven predetermined classes. The novel postprocessing method presented here is evaluated on ten datasets recommended for fair comparisons that represent many skin detection applications. The results show that the new approach enhances the performance of the base classifiers and previous works based only on learning the most appropriate morphological sequences.

Agreement in Breast Lesion Assessment and Final BI-RADS Classification Between Radial and Meander-Like Breast Ultrasound

Background: This study prospectively investigates the agreement between radial (r-US) and meander-like (m-US) breast ultrasound with regard to lesion location, lesion size, morphological characteristics and final BI-RADS classification of individual breast lesions. Methods: Each patient of a consecutive, unselected, mixed collective received a dual ultrasound examination. Results: The agreement between r-US and m-US for lesion location ranged from good (lesion to mammilla distance ICC 0.64; lesion to skin distance ICC 0.72) to substantial (clock-face localization κ 0.70). For lesion size the agreement was good (diameter ICC 0.72; volume ICC 0.69), for lesion margin and architectural distortion it was substantial (κ 0.68 and 0.70, respectively). Most importantly, there was a substantial agreement (κ 0.76) in the final BI-RADS classification between r-US and m-US.Conclusions: Our recent comparison of radial and meander-like breast US revealed that the diagnostic accuracy of the two scanning methods was comparable. In this study, we observe a high degree of agreement between m-US and r-US for the lesion description (location, size, morphology) and final BI-RADS classification. These findings corroborate that r-US is a suitable alternative to m-US in daily clinical practice.Trial registration: NCT02358837. Registered January 2015, retrospectively registeredhttps://clinicaltrials.gov/ct2/results?cond=&term=NCT02358837&cntry=&state=&city=&dist=

Proposing SVM and HOG Techniques for Effective Face Recognition in Video Surveillance

Face Recognition is an active topic among Machine Learning Researchers for two decades owing to its increasing demand in security monitoring applications. The present Techniques while being working has some constraints. The challenges emerge with the orientation, quality, and expression, variations in lightning, or facial occlusions, which has a direct impact on the facial captures using video-based surveillance. This results in performance and accuracy issues. The current surveillance applications require more computational complexity with less accuracy and performance. The proposed video surveillance system overcomes these limitations of existing systems and provides maximum effective security with minimum computational complexity. The proposed Video security monitoring system provides a complete face localization, detection, and recognition. The draw out facial image data is compared with facial dataset images. The facial data is obtained from the video dataset accessed from the real environment. The face image is authenticated if a match is found and is declared unauthenticated otherwise. The security alarm after the unauthenticated alerts the security personal for further action. Hence, the proposed system is more non-evasive, accurate and reliable.