Annu Int Conf IEEE Eng Med Biol Soc. 2021 Nov;2021:3582-3585. doi: 10.1109/EMBC46164.2021.9629698.
Accurate automatic liver and tumor segmentation plays a vital role in treatment planning and disease monitoring. Recently, deep convolutional neural network (DCNNs) has obtained tremendous success in 2D and 3D medical image segmentation. However, 2D DCNNs cannot fully leverage the inter-slice information, while 3D DCNNs are computationally expensive and memory intensive. To address these issues, we first propose a novel dense-sparse training flow from a data perspective, in which, densely adjacent slices and sparsely adjacent slices are extracted as inputs for regularizing DCNNs, thereby improving the model performance. Moreover, we design a 2.5D light-weight nnU-Net from a network perspective, in which, depthwise separable convolutions are adopted to improve the efficiency. Extensive experiments on the LiTS dataset have demonstrated the superiority of the proposed method.Clinical relevance- The proposed method can effectively segment livers and tumors from CT scans with low complexity, which can be easily implemented into clinical practice.
准确的自动肝脏和肿瘤分割在治疗计划和疾病监测中起着至关重要的作用。最近，深度卷积神经网络（DCNN）在 2D 和 3D 医学图像分割中取得了巨大的成功。然而，2D DCNN 不能充分利用切片间信息，而 3D DCNN 计算成本高且内存密集。为了解决这些问题，我们首先从数据的角度提出了一种新颖的密集-稀疏训练流程，其中，密集相邻的切片和稀疏相邻的切片被提取作为正则化 DCNN 的输入，从而提高了模型性能。此外，我们从网络的角度设计了一个 2.5D 轻量级 nnU-Net，其中采用了深度可分离卷积来提高效率。在 LiTS 数据集上的广泛实验表明了所提出方法的优越性。临床相关性——所提出的方法可以有效地从 CT 扫描中分割肝脏和肿瘤，具有低复杂性，可轻松应用于临床实践。
