Rampun Andrik, Jarvis Deborah, Griffiths Paul D, Zwiggelaar Reyer, Scotney Bryan W, Armitage Paul A
Academic Unit of Radiology, Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Sheffield S10 2RX, UK.
Department of Computer Science, Aberystwyth University, Wales SY23 3DB, UK.
J Imaging. 2021 Oct 1;7(10):200. doi: 10.3390/jimaging7100200.
In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively.
在这项工作中，我们开发了单输入多输出U-Net（SIMOU-Net），这是一种用于胎儿脑部分割的混合网络，它受到原始U-Net与整体嵌套边缘检测（HED）网络融合的启发。SIMOU-Net与原始U-Net相似，但它具有更深的架构，并考虑了从每个侧面输出中提取的特征。它的作用类似于集成神经网络，然而，我们的方法不是对几个独立训练模型的输出进行平均（这在计算上很昂贵），而是将单个网络的输出进行组合，以减少预测的方差和泛化误差。使用由超过11500张二维图像组成的200个正常胎儿脑进行实验，结果得到的骰子系数和杰卡德系数分别为94.2±5.9%和88.7±6.9%。我们进一步在54个异常病例（超过3500张图像）上测试了所提出的网络，分别获得了91.2±6.8%和85.7±6.6%的骰子系数和杰卡德系数。
