Measuring shape complexity of breast lesions on ultrasound images

被引:4
作者
Yang, Wei [1 ]
Zhang, Su [1 ]
Chen, Yazhu [1 ]
Li, Wenying [2 ]
Chen, Yaqing [2 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Biomed Engn, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Shanghai Peoples Hosp 6, Shanghai 200231, Peoples R China
来源
MEDICAL IMAGING 2008: ULTRASONIC IMAGING AND SIGNAL PROCESSING | 2008年 / 6920卷
关键词
breast cancer; image segmentation; shape analysis; feature extraction;
D O I
10.1117/12.770959
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
The shapes of malignant breast tumors are more complex than the benign lesions due to their nature of infiltration into surrounding tissues. We investigated the efficacy of shape features and presented a method using polygon shape complexity to improve the discrimination of benign and malignant breast lesions on ultrasound. First, 63 lesions (32 benign and 31 malignant) were segmented by K-way normalized cut with the priori rules on the ultrasound images. Then, the shape measures were computed from the automatically extracted lesion contours. A polygon shape complexity measure (SCM) was introduced to characterize the complexity of breast lesion contour, which was calculated from the polygonal model of lesion contour. Three new statistical parameters were derived from the local integral invariant signatures to quantify the local property of the lesion contour. Receiver operating characteristic (ROC) analysis was carried on to evaluate the performance of each individual shape feature. SCM outperformed the other shape measures, the area under ROC curve (AUC) of SCM was 0.91, and the sensitivity of SCM could reach 0.97 with the specificity 0.66. The measures of shape feature and margin feature were combined in a linear discriminant classifier. The resubstitution and leave-one-out AUC of the linear discriminant classifier were 0.94 and 0.92, respectively. The distinguishing ability of SCM showed that it could be a useful index for the clinical diagnosis and computer-aided diagnosis to reduce the number of unnecessary biopsies.
引用
收藏
页数:10
相关论文
共 33 条
  • [21] Integral invariants for shape matching
    Manay, Siddharth
    Cremers, Daniel
    Hong, Byung-Woo
    Yezzi, Anthony J., Jr.
    Soatto, Stefano
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (10) : 1602 - 1618
  • [22] Development of the cubic least squares mapping linear-kernel support vector machine classifier for improving the characterization of breast lesions on ultrasound
    Piliouras, N
    Kalatzis, I
    Dimitropoulos, N
    Cavouras, D
    [J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2004, 28 (05) : 247 - 255
  • [23] Boundary modelling and shape analysis methods for classification of mammographic masses
    Rangayyan, RM
    Mudigonda, NR
    Desautels, JEL
    [J]. MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2000, 38 (05) : 487 - 496
  • [24] A review of breast ultrasound
    Sehgal, Chandra M.
    Weinstein, Susan P.
    Arger, Peter H.
    Conant, Emily F.
    [J]. JOURNAL OF MAMMARY GLAND BIOLOGY AND NEOPLASIA, 2006, 11 (02) : 113 - 123
  • [25] Computer-based margin analysis of breast sonography for differentiating malignant and benign masses
    Sehgal, CM
    Cary, TW
    Kangas, SA
    Weinstein, SP
    Schultz, SM
    Arger, PH
    Conant, EF
    [J]. JOURNAL OF ULTRASOUND IN MEDICINE, 2004, 23 (09) : 1201 - 1209
  • [26] APPLICATION OF SHAPE-ANALYSIS TO MAMMOGRAPHIC CALCIFICATIONS
    SHEN, L
    RANGAYYAN, RM
    DESAUTELS, JEL
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 1994, 13 (02) : 263 - 274
  • [27] Normalized cuts and image segmentation
    Shi, JB
    Malik, J
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) : 888 - 905
  • [28] Texture analysis of lesions in breast ultrasound images
    Sivaramakrishna, R
    Powell, KA
    Lieber, ML
    Chilcote, WA
    Shekhar, R
    [J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2002, 26 (05) : 303 - 307
  • [29] SOLID BREAST NODULES - USE OF SONOGRAPHY TO DISTINGUISH BENIGN AND MALIGNANT LESIONS
    STAVROS, AT
    THICKMAN, D
    RAPP, CL
    DENNIS, MA
    PARKER, SH
    SISNEY, GA
    [J]. RADIOLOGY, 1995, 196 (01) : 123 - 134
  • [30] Image denoising and decomposition with total variation minimization and oscillatory functions
    Vese, LA
    Osher, SJ
    [J]. JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2004, 20 (1-2) : 7 - 18