Multi-feature analysis for automated breast lesion classification from ultrasonic data

We have developed quantitative descriptors of lesions for reliable, operator-independent breast cancer identification using ultrasound. These include acoustic features as well as morphometric features related to lesion shape. Acoustic features include "echogenicity," "heterogeneity," and "shadowing," computed from radio-frequency (RF) spectral-parameter images of the lesion and surrounding tissue. Morphometric features were computed by geometric and fractal analysis of manually-traced lesion boundaries. Initial results show that no single parameter can precisely identify cancerous breast lesions and that the use of multiple features can substantially improve discrimination. Our analysis produced an ROC-curve area of 0.9164 /spl plusmn/ 0.0346.

[1]  E. H. Lloyd,et al.  Long-Term Storage: An Experimental Study. , 1966 .

[2]  L F Richardson,et al.  The problem of contiguity : An appendix to statistics of deadly quarrels , 1961 .

[3]  G Berger,et al.  Computerized ultrasound B-scan characterization of breast nodules. , 2000, Ultrasound in medicine & biology.

[4]  C W Piccoli,et al.  Tissue classification with generalized spectrum parameters. , 2001, Ultrasound in medicine & biology.

[5]  John C. Russ,et al.  The Image Processing Handbook , 2016, Microscopy and Microanalysis.

[6]  Tian Liu,et al.  Computer-aided diagnosis of breast lesions using a multifeature analysis procedure , 2002, SPIE Medical Imaging.

[7]  J. Jellins,et al.  IBUS guidelines for the ultrasonic examination of the breast. IBUS International Faculty. International Breast Ultrasound School. , 1999, European journal of ultrasound : official journal of the European Federation of Societies for Ultrasound in Medicine and Biology.

[8]  Tian Liu,et al.  Ultrasonic multifeature analysis procedures for breast lesion classification , 2000, Medical Imaging.

[9]  W Yao,et al.  Ultrasonographic texture analysis of parenchymatous organs by the four‐neighborhood‐pixels algorithm: clinical experiment. , 2001, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[10]  B B Goldberg,et al.  Ultrasound analysis of 104 primary breast carcinomas classified according to histopathologic type. , 1983, Radiology.

[11]  P. Skaane,et al.  Analysis of sonographic features in the differentiation of fibroadenoma and invasive ductal carcinoma. , 1998, AJR. American journal of roentgenology.

[12]  E. Feleppa,et al.  Theoretical framework for spectrum analysis in ultrasonic tissue characterization. , 1983, The Journal of the Acoustical Society of America.

[13]  A. Stavros,et al.  Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. , 1995, Radiology.