S2FLNet: Hepatic steatosis detection network with body shape.

S2FLNet: Hepatic steatosis detection network with body shape.
复制标题

DOI:
10.1016/j.compbiomed.2021.105088
复制
发表时间:
2022-01
影响因子:
7.7
通讯作者:
--
中科院分区:
工程技术2区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

脂肪在肝细胞中的积累会增加心脏并发症和心血管疾病死亡率的风险。因此,一种快速准确地检测肝脂肪变性的方法至关重要。然而,目前的方法,例如,肝活组织检查、磁共振成像和计算机断层摄影术扫描成本高和/或医疗并发症。在本文中,我们提出了一种深度神经网络,仅使用体型来估计肝脏脂肪变性的程度(低,中,高)。该网络采用扩张的残差网络块,通过扩大感受野来提取输入体型图的精细特征。此外,为了更准确地分类脂肪变性的程度,我们创建了中心损失和交叉熵损失的混合,以压缩类内变化并分离类间差异。我们使用各种网络参数对公共医疗数据集进行了广泛的测试。我们的实验结果表明,所提出的网络达到了超过82%的总准确率,并提供了一个准确和可访问的评估肝脂肪变性。
Fat accumulation in the liver cells can increase the risk of cardiac complications and cardiovascular disease mortality. Therefore, a way to quickly and accurately detect hepatic steatosis is critically important. However, current methods, e.g., liver biopsy, magnetic resonance imaging, and computerized tomography scan, are subject to high cost and/or medical complications. In this paper, we propose a deep neural network to estimate the degree of hepatic steatosis (low, mid, high) using only body shapes. The proposed network adopts dilated residual network blocks to extract refined features of input body shape maps by expanding the receptive field. Furthermore, to classify the degree of steatosis more accurately, we create a hybrid of the center loss and cross entropy loss to compact intra-class variations and separate inter-class differences. We performed extensive tests on the public medical dataset with various network parameters. Our experimental results show that the proposed network achieves a total accuracy of over 82 % and offers an accurate and accessible assessment for hepatic steatosis.
DOI: 10.1038/ejcn.2016.109
发表时间: 2016-11-01
影响因子: 4.7
作者:
Ng, B. K.;Hinton, B. J.;Shepherd, J. A.
通讯作者: Shepherd, J. A.
DOI: 10.1016/j.jpeds.2006.08.075
发表时间: 2006-12-01
影响因子: 5.1
作者:
Lee, Sojung;Bacha, Fida;Arslanian, Silva A.
通讯作者: Arslanian, Silva A.
DOI: 10.1109/jbhi.2019.2903190
发表时间: 2020-01-01
影响因子: 7.7
作者:
Lu, Yao;Hahn, James K.;Zhang, Xiaoke
通讯作者: Zhang, Xiaoke
DOI: 10.1007/s10278-013-9622-7
发表时间: 2013-12-01
影响因子: 4.4
作者:
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者: Prior, Fred
DOI: 10.1007/s11263-019-01228-7
发表时间: 2020-02-01
影响因子: 19.5
作者:
Selvaraju, Ramprasaath R.;Cogswell, Michael;Batra, Dhruv
通讯作者: Batra, Dhruv