PDF(Pubmed)
Abstract：
Automated perimetrium segmentation of transvaginal ultrasound images is an important process for computer-aided diagnosis of uterine diseases. However, ultrasound images often contain various structures and textures, and these structures have different shapes, sizes, and contrasts; therefore, accurately segmenting the parametrium region of the uterus in transvaginal uterine ultrasound images is a challenge. Recently, many fully supervised deep learning-based methods have been proposed for the segmentation of transvaginal ultrasound images. Nevertheless, these methods require extensive pixel-level annotation by experienced sonographers. This procedure is expensive and time-consuming. In this paper, we present a bidirectional copy-paste Mamba (BCP-Mamba) semi-supervised model for segmenting the parametrium. The proposed model is based on a bidirectional copy-paste method and incorporates a U-shaped structure model with a visual state space (VSS) module instead of the traditional sampling method. A dataset comprising 1940 transvaginal ultrasound images from Tongji Hospital, Huazhong University of Science and Technology is utilized for training and evaluation. The proposed BCP-Mamba model undergoes comparative analysis with two widely recognized semi-supervised models, BCP-Net and U-Net, across various evaluation metrics including Dice, Jaccard, average surface distance (ASD), and Hausdorff_95. The results indicate the superior performance of the BCP-Mamba semi-supervised model, achieving a Dice coefficient of 86.55%, surpassing both U-Net (80.72%) and BCP-Net (84.63%) models. The Hausdorff_95 of the proposed method is 14.56. In comparison, the counterparts of U-Net and BCP-Net are 23.10 and 21.34, respectively. The experimental findings affirm the efficacy of the proposed semi-supervised learning approach in segmenting transvaginal uterine ultrasound images. The implementation of this model may alleviate the expert workload and facilitate more precise prediction and diagnosis of uterine-related conditions.
摘要：
经阴道超声图像的自动分割是计算机辅助诊断子宫疾病的重要过程。然而,超声图像通常包含各种结构和纹理，这些结构有不同的形状，尺寸,和对比；因此，在经阴道子宫超声图像中准确分割子宫旁区域是一个挑战。最近,许多基于完全监督的深度学习方法被提出用于经阴道超声图像的分割。然而，这些方法需要经验丰富的超声医师进行广泛的像素级注释。该过程是昂贵且耗时的。在本文中,我们提出了一个双向复制粘贴Mamba（BCP-Mamba）半监督模型，用于分割旁动脉。所提出的模型基于双向复制粘贴方法，并结合了带有视觉状态空间（VSS）模块的U形结构模型，而不是传统的采样方法。一个包含1940个来自同济医院的经阴道超声图像的数据集，利用华中科技大学进行培训和评估。提出的BCP-Mamba模型与两个广泛认可的半监督模型进行了比较分析，BCP-Net和U-Net,跨各种评估指标，包括骰子，Jaccard,平均表面距离(ASD)，和Hausdorff_95。结果表明，BCP-Mamba半监督模型具有优越的性能，实现了86.55%的骰子系数，超过U-Net（80.72%）和BCP-Net（84.63%）型号。该方法的Hausdorff_95为14.56。相比之下,U-Net和BCP-Net的对应部分分别为23.10和21.34。实验结果肯定了所提出的半监督学习方法在分割经阴道子宫超声图像中的功效。该模型的实现可以减轻专家的工作量，并有助于更精确地预测和诊断子宫相关状况。
