Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images.
Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images.
复制标题
DOI：
10.1007/s11548-018-1843-2
复制
发表时间：
2018-12
影响因子：
3
通讯作者：
Nowicki A
中科院分区：
文献类型：
--
作者：
Byra M;Styczynski G;Szmigielski C;Kalinowski P;Michałowski Ł;Paluszkiewicz R;Ziarkiewicz-Wróblewska B;Zieniewicz K;Sobieraj P;Nowicki A
非酒精性脂肪性肝病是最常见的肝脏异常。迄今为止，肝活检是肝组织样本中直接定量肝脏脂肪变性的参考标准。在本文中，我们提出了一种基于神经网络的超声非酒精性脂肪肝疾病评估方法。我们使用在ImageNet数据集上预训练的Inception-ResNet-v2深度卷积神经网络来提取肝脏B型超声图像序列中的高级特征。通过楔形活检对每个肝脏的脂肪变性程度进行分级。并与肝肾指数法和灰度共生矩阵法进行了比较。在特征提取之后，我们应用支持向量机算法对脂肪肝图像进行分类。基于肝活检，脂肪肝定义为具有超过5%的脂肪变性肝细胞。接下来，我们使用特征和Lasso回归方法来评估脂肪变性水平。使用所提出的方法获得的受试者工作特征曲线下的面积等于0.977，高于肝肾指数法获得的面积0.959，并且远高于灰度共生矩阵算法的情况下的面积0.893。对于回归，脂肪变性水平与所提出的方法、肝肾指数和灰度共生矩阵算法之间的斯皮尔曼相关系数分别等于0.78、0.80和0.39。所提出的方法可以帮助超声医师自动诊断肝脏中的脂肪量。所提出的方法是有效的，并与其他方法相比，不需要超声波医师选择感兴趣的区域。
The nonalcoholic fatty liver disease is the most common liver abnormality. Up to date, liver biopsy is the reference standard for direct liver steatosis quantification in hepatic tissue samples. In this paper we propose a neural network-based approach for nonalcoholic fatty liver disease assessment in ultrasound. We used the Inception-ResNet-v2 deep convolutional neural network pre-trained on the ImageNet dataset to extract high-level features in liver B-mode ultrasound image sequences. The steatosis level of each liver was graded by wedge biopsy. The proposed approach was compared with the hepatorenal index technique and the gray-level co-occurrence matrix algorithm. After the feature extraction, we applied the support vector machine algorithm to classify images containing fatty liver. Based on liver biopsy, the fatty liver was defined to have more than 5% of hepatocytes with steatosis. Next, we used the features and the Lasso regression method to assess the steatosis level. The area under the receiver operating characteristics curve obtained using the proposed approach was equal to 0.977, being higher than the one obtained with the hepatorenal index method, 0.959, and much higher than in the case of the gray-level co-occurrence matrix algorithm, 0.893. For regression the Spearman correlation coefficients between the steatosis level and the proposed approach, the hepatorenal index and the gray-level co-occurrence matrix algorithm were equal to 0.78, 0.80 and 0.39, respectively. The proposed approach may help the sonographers automatically diagnose the amount of fat in the liver. The presented approach is efficient and in comparison with other methods does not require the sonographers to select the region of interest.
登录
查看更多内容
影响因子：
9.8
作者：
Adams, Leon A.;Harmsen, Scott;St Sauver, Jennifer L.;Charatcharoenwitthaya, Phunchai;Enders, Felicity B.;Therneau, Terry;Angulo, Paul
通讯作者：
Angulo, Paul
影响因子：
5
作者：
Marshall, Richard H.;Eissa, Marna;Davis, Nancy K.
通讯作者：
Davis, Nancy K.
影响因子：
9
作者：
Kalinowski, Piotr;Paluszkiewicz, Rafal;Krawczyk, Marek
通讯作者：
Krawczyk, Marek
影响因子：
2.4
作者：
Huynh, Benjamin Q.;Li, Hui;Giger, Maryellen L.
通讯作者：
Giger, Maryellen L.
影响因子：
3.7
作者：
Diedenhofen B;Musch J
通讯作者：
Musch J