Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan 411105, China.
Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan 411105, China.
Neural Netw. 2024 Nov;179:106507. doi: 10.1016/j.neunet.2024.106507. Epub 2024 Jul 4.
Segmentation and the subsequent quantitative assessment of the target object in computed tomography (CT) images provide valuable information for the analysis of intracerebral hemorrhage (ICH) pathology. However, most existing methods lack a reasonable strategy to explore the discriminative semantics of multi-scale ICH regions, making it difficult to address the challenge of complex morphology in clinical data. In this paper, we propose a novel multi-scale object equalization learning network (MOEL-Net) for accurate ICH region segmentation. Specifically, we first introduce a shallow feature extraction module (SFEM) for obtaining shallow semantic representations to maintain sufficient and effective detailed location information. Then, a deep feature extraction module (DFEM) is leveraged to extract the deep semantic information of the ICH region from the combination of SFEM and original image features. To further achieve equalization learning in different scales of ICH regions, we introduce a multi-level semantic feature equalization fusion module (MSFEFM), which explores the equalized fusion features of the described objects with the assistance of shallow and deep semantic information provided by SFEM and DFEM. Driven by the above three designs, MOEL-Net shows a solid capacity to capture more discriminative features in various ICH region segmentation. To promote the research of clinical automatic ICH region segmentation, we collect two datasets, VMICH and FRICH (divided into Test A and Test B) for evaluation. Experimental results show that the proposed model achieves the Dice scores of 88.28%, 90.92%, and 90.95% on the VMICH, FRICH Test A, and Test B, respectively, which outperform fourteen competing methods.
在计算机断层扫描（CT）图像中，对目标对象进行分割和随后的定量评估为分析脑出血（ICH）病理学提供了有价值的信息。然而，大多数现有的方法缺乏探索多尺度 ICH 区域的有区别语义的合理策略，因此难以解决临床数据中复杂形态的挑战。在本文中，我们提出了一种新颖的多尺度目标均衡学习网络（MOEL-Net），用于准确的 ICH 区域分割。具体来说，我们首先引入了一个浅层特征提取模块（SFEM），用于获取浅层语义表示，以保持足够和有效的详细位置信息。然后，利用深度特征提取模块（DFEM）从 SFEM 和原始图像特征的组合中提取 ICH 区域的深层语义信息。为了进一步在不同尺度的 ICH 区域实现均衡学习，我们引入了一个多层次语义特征均衡融合模块（MSFEFM），该模块借助 SFEM 和 DFEM 提供的浅层和深层语义信息，探索描述对象的均衡融合特征。受上述三个设计的驱动，MOEL-Net 显示出在各种 ICH 区域分割中捕捉更具区别性特征的强大能力。为了促进临床自动 ICH 区域分割的研究，我们收集了两个数据集，VMICH 和 FRICH（分为 Test A 和 Test B）进行评估。实验结果表明，所提出的模型在 VMICH、FRICH Test A 和 Test B 上的 Dice 分数分别达到 88.28%、90.92%和 90.95%，优于十四个竞争方法。
