Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran; Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran.
Research and Development Department, Med Fanavarn Plus Co., Karaj, Iran; Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran.
Phys Med. 2019 Nov;67:58-69. doi: 10.1016/j.ejmp.2019.10.001. Epub 2019 Oct 28.
Segmentation of the Left ventricle (LV) is a crucial step for quantitative measurements such as area, volume, and ejection fraction. However, the automatic LV segmentation in 2D echocardiographic images is a challenging task due to ill-defined borders, and operator dependence issues (insufficient reproducibility). U-net, which is a well-known architecture in medical image segmentation, addressed this problem through an encoder-decoder path. Despite outstanding overall performance, U-net ignores the contribution of all semantic strengths in the segmentation procedure. In the present study, we have proposed a novel architecture to tackle this drawback. Feature maps in all levels of the decoder path of U-net are concatenated, their depths are equalized, and up-sampled to a fixed dimension. This stack of feature maps would be the input of the semantic segmentation layer. The performance of the proposed model was evaluated using two sets of echocardiographic images: one public dataset and one prepared dataset. The proposed network yielded significantly improved results when comparing with results from U-net, dilated U-net, Unet++, ACNN, SHG, and deeplabv3. An average Dice Metric (DM) of 0.953, Hausdorff Distance (HD) of 3.49, and Mean Absolute Distance (MAD) of 1.12 are achieved in the public dataset. The correlation graph, bland-altman analysis, and box plot showed a great agreement between automatic and manually calculated volume, area, and length.
左心室（LV）的分割是定量测量（如面积、体积和射血分数）的关键步骤。然而，由于边界不明确和操作者依赖问题（可重复性不足），二维超声心动图图像中的自动 LV 分割是一项具有挑战性的任务。U-net 是医学图像分割中著名的架构，通过编码器-解码器路径解决了这个问题。尽管整体性能出色，但 U-net 在分割过程中忽略了所有语义强度的贡献。在本研究中，我们提出了一种新的架构来解决这个缺点。U-net 解码器路径中所有级别的特征图被串联，其深度被均衡化，并上采样到固定维度。这组堆叠的特征图将成为语义分割层的输入。该模型的性能使用两组超声心动图图像进行了评估：一个公共数据集和一个准备数据集。与 U-net、扩张 U-net、Unet++、ACNN、SHG 和 deeplabv3 的结果相比，所提出的网络产生了显著改进的结果。在公共数据集中，平均 Dice 度量（DM）为 0.953，Hausdorff 距离（HD）为 3.49，平均绝对距离（MAD）为 1.12。相关图、Bland-Altman 分析和箱线图显示，自动计算和手动计算的体积、面积和长度之间具有很好的一致性。
