MACHINE LEARNING TECHNIQUES TO DIAGNOSE BREAST-CANCER FROM IMAGE-PROCESSED NUCLEAR FEATURES OF FINE-NEEDLE ASPIRATES

被引：126

作者：

WOLBERG, WH

STREET, WN

MANGASARIAN, OL

机构：

[1] UNIV WISCONSIN, DEPT HUMAN ONCOL, MADISON, WI 53792 USA

[2] UNIV WISCONSIN, DEPT COMP SCI, MADISON, WI 53706 USA

来源：

CANCER LETTERS | 1994年 / 77卷 / 2-3期

基金：

美国国家科学基金会;

关键词：

BREAST CANCER; DIGITAL MORPHOMETRY; IMAGE ANALYSIS; MACHINE LEARNING; FINE NEEDLE ASPIRATION;

D O I：

10.1016/0304-3835(94)90099-X

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

An interactive computer system evaluates and diagnoses based on cytologic features derived directly from a digital scan of fine-needle aspirate (FNA) slides. A consecutive series of 569 patients provided the data to develop the system and an additional 54 consecutive, new patients provided samples to test the system. The projected prospective accuracy of the system estimated by tenfold cross validation was 97%. The actual accuracy on 54 new samples (36 benign, 1 atypia, and 17 malignant) was 100%. Digital image analysis coupled with machine learning techniques will improve diagnostic accuracy of breast fine needle aspirates.

引用

页码：163 / 171

页数：9

共 51 条

[11]

GIARD RWM, 1992, CANCER, V69, P2104, DOI 10.1002/1097-0142(19920415)69:8<2104::AID-CNCR2820690816>3.0.CO

[12]

2-O

[13]

GRIFFITH CN, 1986, SURG GYNECOL OBSTET, V162, P142

[14]

GUPTA RK, 1990, ACTA CYTOL, V34, P165

[15]

HALEVY A, 1987, SURG GYNECOL OBSTET, V164, P506

[16]

HAMMOND S, 1987, ACTA CYTOL, V31, P276

[17]

HORGAN PG, 1991, SURG GYNECOL OBSTET, V172, P290

[18]

HUTCHINSON ML, 1991, ANAL QUANT CYTOL, V13, P351

[19]

HUTCHINSON WB, 1980, J NATL CANCER I, V65, P13

[20]

KASS M, 1987, 1ST P INT C COMP VIS, P259

← 1 2 3 4 5 6 →