Gridach Mourad, Yasrab Robail, Drukker Lior, Papageorghiou Aris T, Noble J Alison
Institute of Biomedical Engineering, University of Oxford, Oxford, UK.
Nuffield Department of Women's & Reproductive Health, University of Oxford, Oxford, UK.
Proc IEEE Int Symp Biomed Imaging. 2023 Apr 18;58:1-4. doi: 10.1109/ISBI53787.2023.10230727.
Manual annotation of medical images is time consuming for clinical experts; therefore, reliable automatic segmentation would be the ideal way to handle large medical datasets. In this paper, we are interested in detection and segmentation of two fundamental measurements in the first trimester ultrasound (US) scan: Nuchal Translucency (NT) and Crown Rump Length (CRL). There can be a significant variation in the shape, location or size of the anatomical structures in the fetal US scans. We propose a new approach, namely Densely Attentional-Aware Network for First Trimester Ultrasound CRL and NT Segmentation (DA2Net), to encode variation in feature size by relying on the powerful attention mechanism and densely connected networks. Our results show that the proposed D2ANet offers high pixel agreement (mean JSC = 84.21) with expert manual annotations.
对于临床专家而言，手动标注医学图像非常耗时；因此，可靠的自动分割将是处理大型医学数据集的理想方式。在本文中，我们关注孕早期超声（US）扫描中两个基本测量值的检测与分割：颈项透明层（NT）和头臀长（CRL）。胎儿超声扫描中的解剖结构在形状、位置或大小上可能存在显著差异。我们提出了一种新方法，即用于孕早期超声CRL和NT分割的密集注意力感知网络（DA2Net），通过依靠强大的注意力机制和密集连接网络来编码特征大小的变化。我们的结果表明，所提出的D2ANet与专家手动标注具有高度的像素一致性（平均JSC = 84.21）。
