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

被引：2

作者：

Alam, SK ^{[1
]}

Lizzi, FL ^{[1
]}

Feleppa, EJ ^{[1
]}

Liu, T ^{[1
]}

Kalisz, A ^{[1
]}

机构：

[1] Riverside Res Inst, New York, NY 10036 USA

来源：

PROCEEDINGS OF THE IEEE 28TH ANNUAL NORTHEAST BIOENGINEERING CONFERENCE | 2002年

关键词：

D O I：

10.1109/NEBC.2002.999578

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 [生物医学工程];

摘要：

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+/-0.0346.

引用

页码：287 / 288

页数：2

共 17 条

[1]

*ADV TECHN LAB, 1994, SUMM ATL SPONS BREAS

[2]

Ultrasonic multifeature analysis procedures for breast lesion classification [J].