Ananda Swathi, Jain Rahul Kumar, Li Yinhao, Iwamoto Yutaro, Han Xian-Hua, Kanasaki Shuzo, Hu Hongjie, Chen Yen-Wei
Graduate School of Information Science and Engineering, Ritsumeikan University, Kusatsu-shi 525-0058, Japan.
Faculty of Information and Communication Engineering, Osaka Electro-Communication University, Neyagawa-shi 572-0833, Japan.
Bioengineering (Basel). 2023 Jul 28;10(8):899. doi: 10.3390/bioengineering10080899.
Multi-phase computed tomography (CT) images have gained significant popularity in the diagnosis of hepatic disease. There are several challenges in the liver segmentation of multi-phase CT images. (1) Annotation: due to the distinct contrast enhancements observed in different phases (i.e., each phase is considered a different domain), annotating all phase images in multi-phase CT images for liver or tumor segmentation is a task that consumes substantial time and labor resources. (2) Poor contrast: some phase images may have poor contrast, making it difficult to distinguish the liver boundary. In this paper, we propose a boundary-enhanced liver segmentation network for multi-phase CT images with unsupervised domain adaptation. The first contribution is that we propose DD-UDA, a dual discriminator-based unsupervised domain adaptation, for liver segmentation on multi-phase images without multi-phase annotations, effectively tackling the annotation problem. To improve accuracy by reducing distribution differences between the source and target domains, we perform domain adaptation at two levels by employing two discriminators, one at the feature level and the other at the output level. The second contribution is that we introduce an additional boundary-enhanced decoder to the encoder-decoder backbone segmentation network to effectively recognize the boundary region, thereby addressing the problem of poor contrast. In our study, we employ the public LiTS dataset as the source domain and our private MPCT-FLLs dataset as the target domain. The experimental findings validate the efficacy of our proposed methods, producing substantially improved results when tested on each phase of the multi-phase CT image even without the multi-phase annotations. As evaluated on the MPCT-FLLs dataset, the existing baseline (UDA) method achieved IoU scores of 0.785, 0.796, and 0.772 for the PV, ART, and NC phases, respectively, while our proposed approach exhibited superior performance, surpassing both the baseline and other state-of-the-art methods. Notably, our method achieved remarkable IoU scores of 0.823, 0.811, and 0.800 for the PV, ART, and NC phases, respectively, emphasizing its effectiveness in achieving accurate image segmentation.
多期计算机断层扫描（CT）图像在肝脏疾病诊断中已变得非常流行。在多期CT图像的肝脏分割中存在若干挑战。（1）标注：由于在不同期观察到明显的对比增强（即，每期被视为一个不同的域），为肝脏或肿瘤分割标注多期CT图像中的所有期图像是一项耗费大量时间和劳动力资源的任务。（2）对比度差：一些期图像可能对比度差，使得难以区分肝脏边界。在本文中，我们提出了一种用于多期CT图像的具有无监督域适应的边界增强肝脏分割网络。第一个贡献是，我们提出了DD-UDA，一种基于双判别器的无监督域适应方法，用于在没有多期标注的多期图像上进行肝脏分割，有效解决了标注问题。为了通过减少源域和目标域之间的分布差异来提高准确性，我们通过使用两个判别器在两个级别上进行域适应，一个在特征级别，另一个在输出级别。第二个贡献是，我们在编码器-解码器主干分割网络中引入了一个额外的边界增强解码器，以有效识别边界区域，从而解决对比度差的问题。在我们的研究中，我们使用公共LiTS数据集作为源域，我们的私有MPCT-FLLs数据集作为目标域。实验结果验证了我们提出的方法的有效性，即使在没有多期标注的情况下，在多期CT图像的每期上进行测试时也产生了显著改进的结果。在MPCT-FLLs数据集上评估时，现有的基线（UDA）方法在门静脉期（PV）、动脉期（ART）和非增强期（NC）的交并比（IoU）分数分别为0.785、0.796和0.772，而我们提出的方法表现出卓越的性能，超过了基线和其他最新方法。值得注意的是，我们的方法在PV、ART和NC期的IoU分数分别达到了显著的0.823、0.811和0.800，强调了其在实现准确图像分割方面的有效性。
