EVOLVING NEURAL NETWORKS FOR DETECTING BREAST-CANCER

被引：70

作者：

FOGEL, DB

WASSON, EC

BOUGHTON, EM

机构：

[1] MAUI MEM HOSP, WAILUKU, HI 96793 USA

[2] MAUI ECON DEV BOARD, MAUI, HI 96753 USA

来源：

CANCER LETTERS | 1995年 / 96卷 / 01期

关键词：

BREAST CANCER; NEURAL NETWORKS; EVOLUTIONARY PROGRAMMING;

D O I：

10.1016/0304-3835(95)03916-K

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Artificial neural networks are applied to the problem of detecting breast cancer from histologic data. Evolutionary programming is used to train the networks. This stochastic optimization method reduces the chance of becoming trapped in locally optimal weight sets. Preliminary results indicate that very parsimonious neural nets can outperform other methods reported in the literature on the same data. The results are statistically significant.

引用

页码：49 / 53

页数：5

共 12 条

[1] Bennet K., 1992, OPTIMIZATION METHODS, V1, P22
[2] FLOYD CE, 1994, CANCER, V74, P2944, DOI 10.1002/1097-0142(19941201)74:11<2944::AID-CNCR2820741109>3.0.CO
[3] 2-F
[4] Fogel D.B., 1995, EVOLUTIONARY COMPUTA
[5] HAYKIN S, 1994, NEURAL NETOWRKS COMP
[6] KOCUR CM, 1995, P SOC PHOTO-OPT INS, V2492, P905, DOI 10.1117/12.205202
[7] Mangasarian OL, 1990, SIAM NEWS, V23, P1
[8] TABAR L, 1985, TEACHING ATLAS MAMMO
[9] APPLICATION OF BACKPROPAGATION NEURAL NETWORKS TO DIAGNOSIS OF BREAST AND OVARIAN-CANCER
WILDING, P
MORGAN, MA
GRYGOTIS, AE
SHOFFNER, MA
ROSATO, EF
[J]. CANCER LETTERS, 1994, 77 (2-3) : 145 - 153
[10] MULTISURFACE METHOD OF PATTERN SEPARATION FOR MEDICAL DIAGNOSIS APPLIED TO BREAST CYTOLOGY
WOLBERG, WH
MANGASARIAN, OL
[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1990, 87 (23) : 9193 - 9196

← 1 2 →