https://scholars.lib.ntu.edu.tw/handle/123456789/477809
標題: | Automatic Selection of Representative Slice From Cine-Loops of Real-Time Sonoelastography for Classifying Solid Breast Masses | 作者: | YEUN-CHUNG CHANG Yang M.-C. CHIUN-SHENG HUANG Chang S.-C. Huang G.-Y. Moon W.K. Chang R.-F. |
公開日期: | 2011 | 卷: | 37 | 期: | 5 | 起(迄)頁: | 709-718 | 來源出版物: | Ultrasound in Medicine and Biology | 摘要: | This study aimed to evaluate the performance of automatic selection of representative slice from cine-loops of real-time sonoelastography for classifying benign and malignant breast masses. This retrospective study included 141 ultrasound elastographic studies (93 benign and 48 malignant masses). A novel computer-assisted system was developed for the automatic segmentation of the targeted lesion from cine-loops of real-time sonoelastography. Its hard ratio, defined as the ratio of the number of hard pixels within the tumor divided by the total number of pixels of the whole tumor, was also calculated. The targeted mass was segmented by edge-detection and region growing methods, with combined motion registration after manually defining the original seed. Signal-to-noise ratio (SNRe) and contrast-to-noise ratio (CNRe) of ultrasound elastogram were computed to obtain an optimum slice for differentiating benign and malignant lesions. The diagnostic results of automatic slice selection using maximum strain, maximum SNRe, maximum CNRe, maximum compression and the slices selected by radiologists were compared. Mann-Whitney U test, performance indexes and receiver operating characteristic (ROC) curves were used for statistical analysis. Performance using the maximum SNRe (accuracy 84.4%, sensitivity 83.3%, specificity 85.0% and Az value 0.90) was the best as compared with those of maximum CNRe (82.3%, 79.2%, 83.9% and 0.88, respectively), maximum compression (78.0%, 79.2%, 77.4% and 0.85, respectively), maximum strain (79.4%, 79.2%, 79.6% and 0.87, respectively) and radiologists' selection (77.3%, 77.1%, 77.4% and 0.80, respectively). Automatic selection of representative slice from the cine-loops of real-time sonoelastography is a practical, objective and accurate approach for classifying solid breast masses.(E-mail: moonwk@radcom.snu.ac.kr and rfchang@csie.ntu.edu.tw). ? 2011 World Federation for Ultrasound in Medicine & Biology. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-79954628925&doi=10.1016%2fj.ultrasmedbio.2011.02.007&partnerID=40&md5=8dd4b9c888b1f413c7213a3d0682bf98 https://scholars.lib.ntu.edu.tw/handle/123456789/477809 |
ISSN: | 0301-5629 | DOI: | 10.1016/j.ultrasmedbio.2011.02.007 | SDG/關鍵字: | Automatic segmentations; Automatic selection; Breast mass; Breast ultrasonography; Combined motions; Computer-assisted diagnosis; Computer-assisted system; Contrast to noise ratio; Elastograms; Malignant lesion; Malignant mass; Mann-Whitney U test; Maximum-SNR; Performance indices; Receiver operating characteristic curves; Region growing methods; Signal to noise; Solid breast mass; Sonoelastography; Statistical analysis; Signal to noise ratio; Tumors; Ultrasonic imaging; Ultrasonics; Ultrasonography; Pixels; adult; aged; article; automation; B scan; breast cancer; breast tumor; computer assisted diagnosis; contrast to noise ratio; controlled study; diagnostic accuracy; differential diagnosis; elastography; electrical parameters; female; human; image analysis; image quality; major clinical study; mathematical analysis; maximum compression slice; maximum strain slice; prediction; priority journal; radiological parameters; radiologist; real time echography; retrospective study; sampling; sensitivity and specificity; signal noise ratio; solid tumor; tumor classification; Adult; Aged; Breast Neoplasms; Elasticity Imaging Techniques; Female; Humans; Image Interpretation, Computer-Assisted; Middle Aged; Retrospective Studies; Ultrasonography, Mammary |
顯示於: | 醫學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。