实性乳腺肿块：三维能量多普勒超声血管特征的神经网络分析用于良恶性分类

Solid breast masses: neural network analysis of vascular features at three-dimensional power Doppler US for benign or malignant classification.

作者信息

Chang Ruey-Feng, Huang Sheng-Fang, Moon Woo Kyung, Lee Yu-Hau, Chen Dar-Ren

机构信息

Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan.

出版信息

Radiology. 2007 Apr;243(1):56-62. doi: 10.1148/radiol.2431060041. Epub 2007 Feb 20.

DOI:10.1148/radiol.2431060041

PMID:17312276

Abstract

PURPOSE

To retrospectively evaluate the accuracy of neural network analysis of tumor vascular features at three-dimensional (3D) power Doppler ultrasonography (US) for classification of breast tumors as benign or malignant, with histologic findings as the reference standard.

MATERIALS AND METHODS

This study was approved by the local ethics committee; informed consent was waived. Three-dimensional power Doppler US images of 221 solid breast masses (110 benign, 111 malignant) were obtained in 221 women (mean age, 46 years; range, 25-71 years). After narrowing down vessels to skeletons with a 3D thinning algorithm, six vascular feature values--vessel-to-volume ratio, number of vascular trees, total vessel length, longest path length, number of bifurcations, and vessel diameter-were computed. A neural network was used to classify tumors by using these features. Independent-samples t test and receiver operating characteristic (ROC) curve analysis were used.

RESULTS

Mean values of vessel-to-volume ratio, number of vascular trees, total vessel length, longest path length, number of bifurcations, and vessel diameter were 0.0089 +/- 0.0073 (standard deviation), 26.41 +/- 14.73, 23.02 cm +/- 19.53, 8.44 cm +/- 10.38, 36.31 +/- 37.06, and 0.088 cm +/- 0.021 in malignant tumors, respectively, and 0.0028 +/- 0.0021, 9.69 +/- 6.75, 5.17 cm +/- 4.78, 1.68 cm +/- 1.79, 6.05 +/- 7.55, and 0.064 cm +/- 0.028 in benign tumors, respectively (P < .001 for all six features). Area under ROC curve (A(z)) values of the six features were 0.84, 0.87, 0.87, 0.82, 0.84, and 0.75, respectively. Accuracy, sensitivity, specificity, and positive and negative predictive values were 85% (187 of 221), 83% (96 of 115), 86% (91 of 106), 86% (96 of 111), and 83% (91 of 110), respectively, with A(z) of 0.92 based on all six feature values.

CONCLUSION

Three-dimensional power Doppler US images and neural network analysis of features can aid in classification of breast tumors as benign or malignant.

摘要

目的

以组织学结果为参考标准，回顾性评估三维（3D）能量多普勒超声（US）对乳腺肿瘤血管特征进行神经网络分析以区分乳腺肿瘤为良性或恶性的准确性。

材料与方法

本研究经当地伦理委员会批准；无需知情同意。对221名女性（平均年龄46岁；范围25 - 71岁）的221个乳腺实性肿块（110个良性，111个恶性）进行了三维能量多普勒US成像。使用三维细化算法将血管细化为骨架后，计算六个血管特征值——血管与体积比、血管树数量、总血管长度、最长路径长度、分支数量和血管直径。使用这些特征通过神经网络对肿瘤进行分类。采用独立样本t检验和受试者操作特征（ROC）曲线分析。

结果

恶性肿瘤的血管与体积比、血管树数量、总血管长度、最长路径长度、分支数量和血管直径的平均值分别为0.0089±0.0073（标准差）、26.41±14.73、23.02 cm±19.53、8.44 cm±10.38、36.31±37.06和0.088 cm±0.021，良性肿瘤分别为0.0028±0.0021、9.69±6.75、5.17 cm±4.78、1.68 cm±1.79、6.05±7.55和0.064 cm±0.028（所有六个特征P均<0.001）。六个特征的ROC曲线下面积（A(z)）值分别为0.84、0.87、0.87、0.82、0.84和0.75。基于所有六个特征值，准确性、敏感性、特异性以及阳性和阴性预测值分别为85%（221个中的187个）、83%（115个中的96个）、86%（106个中的91个）、86%（111个中的96个）和83%（110个中的91个），A(z)为0.92。