Lo C.-M.Moon W.K.CHIUN-SHENG HUANGChen J.-H.Yang M.-C.RUEY-FENG CHANG2020-03-232020-03-23201503015629https://www.scopus.com/inward/record.uri?eid=2-s2.0-84942990272&doi=10.1016%2fj.ultrasmedbio.2015.03.003&partnerID=40&md5=fb35ea6b9d676493a4a2edcb9c9ffc8chttps://scholars.lib.ntu.edu.tw/handle/123456789/477752Radiologists likely incorrectly classify benign masses as Breast Imaging Reporting and Data System (BIRADS) category 3. A computer-aided diagnosis (CAD) system was developed in this study as a second viewer to avoid misclassification of carcinomas. Sixty-nine biopsy-proven BI-RADS category 3 masses, including 21 malignant and 48 benign masses, were used to evaluate the CAD system. To improve the texture features, gray-scale variations between images were reduced by transforming pixels into intensity-invariant ranklet coefficients. The textures of the tumor and speckle pixels were extracted from the transformed ranklet images to provide more robust features than in conventionalCADsystems. As a result, tumor texture and speckle texture with ranklet transformation achieved significantly better areas under the receiver operating characteristic curve (Az) compared with those without ranklet transformation (Az = 0.83 vs. 0.58 and Az = 0.80 vs. 0.56, p value < 0.05). The improved CAD system can be a second reader to confirm the classification of BI-RADS category 3 masses. ? 2015 World Federation for Ultrasound in Medicine & Biology.Breast cancer; Breast imaging and reporting data system; Computer-aided diagnosis; Ranklet; Ultrasound[SDGs]SDG3Diagnosis; Image texture; Medical imaging; Pixels; Speckle; Textures; Tumors; Ultrasonics; Breast Cancer; Breast imaging reporting and data systems; Computer Aided Diagnosis(CAD); Data systems; Intensity invariant; Misclassifications; Ranklet; Receiver operating characteristic curves; Computer aided diagnosis; adult; aged; Article; breast biopsy; breast cancer; Breast Imaging Reporting and Data System; breast tumor; cancer classification; cancer grading; cancer size; computer assisted diagnosis; controlled study; diagnostic accuracy; diagnostic error; Gray scale echography; human; human tissue; image analysis; image processing; image quality; imaging and display; intensity invariant texture analysis; intraductal carcinoma; major clinical study; predictive value; priority journal; ranklet transformation; receiver operating characteristic; retrospective study; sensitivity and specificity; statistical parameters; ultrasound scanner; algorithm; automated pattern recognition; breast tumor; classification; computer assisted diagnosis; echography; echomammography; female; image enhancement; middle aged; nomenclature; practice guideline; procedures; reproducibility; severity of illness index; standards; three dimensional imaging; United States; very elderly; young adult; Adult; Aged; Aged, 80 and over; Algorithms; Breast Neoplasms; Female; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Middle Aged; Pattern Recognition, Automated; Practice Guidelines as Topic; Reproducibility of Results; Sensitivity and Specificity; Severity of Illness Index; Terminology as Topic; Ultrasonography, Mammary; United States; Young Adultjournal article10.1016/j.ultrasmedbio.2015.03.003258435142-s2.0-84942990272