Predicting ovarian malignancy: Application of artificial neural networks to transvaginal and color Doppler flow US

被引:45
作者
Biagiotti, R
Desii, C
Vanzi, E
Gacci, G
机构
[1] Univ Florence, Dept Gynecol & Obstet, Florence, Italy
[2] Univ Florence, Dept Radiol, Florence, Italy
关键词
computers; diagnostic aid; neural network; ovary; neoplasms; US; ultrasound; (US); Doppler studies;
D O I
10.1148/radiology.210.2.r99fe18399
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
PURPOSE:To compare the performance of artificial neural networks (ANNs) with that of multiple logistic regression (MLR) models for predicting ovarian malignancy in patients with adnexal masses by using transvaginal B-mode and color Doppler flow ultrasonography (US). MATERIALS AND METHODS: A total of 226 adnexal masses were examined before surgery: Fifty-one were malignant and 175 were benign. The data were divided into training and testing subsets by using a "leave n out method." The training subsets were used to compute the optimum MLR equations and to train the ANNs. The cross-validation subsets were used to estimate the performance of each of the two models in predicting ovarian malignancy. RESULTS: At testing, three-layer back-propagation networks, based on the same input variables selected by using MLR tie, women's ages, papillary projections, random echogenicity, peak systolic velocity, and resistance index), had a significantly higher sensitivity than did MLR (96% vs 84%; McNemar test, P =.04). The Brier scores for ANNs were significantly lower than those calculated for MLR (Student t test for paired samples, P =.004). CONCLUSION: ANNs might have potential for categorizing adnexal masses as either malignant or benign on the basis of multiple variables related to demographic and US features.
引用
收藏
页码:399 / 403
页数:5
相关论文
共 32 条
[1]   POTENTIAL USEFULNESS OF AN ARTIFICIAL NEURAL NETWORK FOR DIFFERENTIAL-DIAGNOSIS OF INTERSTITIAL LUNG-DISEASES - PILOT-STUDY [J].
ASADA, N ;
DOI, K ;
MACMAHON, H ;
MONTNER, SM ;
GIGER, ML ;
ABE, C ;
WU, YZ .
RADIOLOGY, 1990, 177 (03) :857-860
[2]   What Size Net Gives Valid Generalization? [J].
Baum, Eric B. ;
Haussler, David .
NEURAL COMPUTATION, 1989, 1 (01) :151-160
[3]   APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO CLINICAL MEDICINE [J].
BAXT, WG .
LANCET, 1995, 346 (8983) :1135-1138
[4]   NEURAL NETWORKS IN RADIOLOGIC-DIAGNOSIS .1. INTRODUCTION AND ILLUSTRATION [J].
BOONE, JM ;
GROSS, GW ;
GRECOHUNT, V .
INVESTIGATIVE RADIOLOGY, 1990, 25 (09) :1012-1016
[5]   TRANS-VAGINAL COLOR FLOW IMAGING - A POSSIBLE NEW SCREENING TECHNIQUE FOR OVARIAN-CANCER [J].
BOURNE, T ;
CAMPBELL, S ;
STEER, C ;
WHITEHEAD, MI ;
COLLINS, WP .
BRITISH MEDICAL JOURNAL, 1989, 299 (6712) :1367-1370
[6]  
BROMLEY B, 1994, OBSTET GYNECOL, V83, P434
[7]   CLASSIFICATION OF ULTRASONIC IMAGE TEXTURE BY STATISTICAL DISCRIMINANT-ANALYSIS AND NEURAL NETWORKS [J].
DAPONTE, JS ;
SHERMAN, P .
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 1991, 15 (01) :3-9
[8]   A MORPHOLOGY INDEX BASED ON SONOGRAPHIC FINDINGS IN OVARIAN-CANCER [J].
DEPRIEST, PD ;
SHENSON, D ;
FRIED, A ;
HUNTER, JE ;
ANDREWS, SJ ;
GALLION, HH ;
PAVLIK, EJ ;
KRYSCIO, RJ ;
VANNAGELL, JR .
GYNECOLOGIC ONCOLOGY, 1993, 51 (01) :7-11
[9]   ARTIFICIAL NEURAL NETWORKS IN PATHOLOGY AND MEDICAL LABORATORIES [J].
DYBOWSKI, R ;
GANT, V .
LANCET, 1995, 346 (8984) :1203-1207
[10]  
FLEISCHER AC, 1991, J ULTRAS MED, V10, P563