Computerized Determination Scheme for Histological Classification of Masses on Breast Ultrasonographic Images Using Combination of CNN Features and Morphologic Features
Computerized Determination Scheme for Histological Classification of Masses on Breast Ultrasonographic Images Using Combination of CNN Features and Morphologic Features
复制标题
结合CNN特征和形态特征的乳腺超声图像肿块组织学分类的计算机确定方案
DOI：
10.1117/12.2564060
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Ryohei Nakayama
中科院分区：
文献类型：
--
作者：
Shinya Kunieda;Akiyoshi Hizukuri;Ryohei Nakayama
临床医生很难正确确定活检或随访乳腺超声图像上的肿块。本研究的目的是开发一种计算机化的确定方案，用于使用CNN（卷积神经网络）特征和形态学特征的组合对肿块进行组织学分类。该数据库包括585个乳腺超声图像。其中恶性肿瘤288例（浸润性癌218例，非浸润性癌70例），良性肿瘤297例（纤维腺瘤182例，囊肿115例）。在所提出的方法中，首先从肿块中确定CNN特征和形态学特征。CNN特征是通过使用主成分分析降低GoogLeNet中最终池化层输出的维度来定义的。形态学特征也被定义为考虑到图像特征通常用于描述肿块的乳房超声图像。采用具有CNN特征和形态学特征的支持向量机（SVM）对肿块的组织学分类进行分类。使用三重交叉验证方法对GoogLeNet和SVM进行训练和测试。对浸润性癌、非浸润性癌、纤维腺瘤和囊肿的分类准确率分别为84.4%（184/218）、72.9%（51/70）、85.7%（156/182）和87.8%（101/115）。其敏感性和特异性分别为87.2%（251/288）和93.3%（277/297），阳性预测值和阴性预测值分别为92.6%（251/271）和88.2%（277/314）。所提出的方法产生高的分类精度将是有用的鉴别诊断的肿块超声图像作为诊断辅助。
It can be difficult for clinicians to correctly determine biopsy or follow-up for masses on breast ultrasonographic images. The purpose of this study was to develop a computerized determination scheme for histological classification of masses using a combination of CNN (convolutional neural network) features and morphologic features. The database consisted of 585 breast ultrasonographic images. It included 288 malignant masses (218 invasive carcinomas and 70 noninvasive carcinomas) and 297 benign masses (182 fibroadenomas and 115 cysts). In the proposed method, CNN features and morphologic features were first determined from a mass. The CNN features were defined by reducing the dimensionality of the output of the final pooling layer in GoogLeNet using a principal component analysis. The morphologic features were also defined by taking into account image features commonly used for describing masses on breast ultrasonographic images. A support vector machine (SVM) with the CNN features and the morphologic features was employed to classify among histological classifications of masses. Three-fold cross validation method was used for training and testing the GoogLeNet and the SVM. The classification accuracies with the proposed method were 84.4% (184/218) for invasive carcinomas, 72.9% (51/70) for noninvasive carcinomas, 85.7% (156/182) for fibroadenomas, and 87.8% (101/115) for cysts, respectively. The sensitivity and the specificity were 87.2% (251/288) and 93.3% (277/297), whereas the positive predictive value and the negative predictive value were 92.6% (251/271) and 88.2% (277/314). The proposed method yielding high classification accuracies would be useful in the differential diagnosis of masses on ultrasonographic images as diagnosis aid.