Zhao Ming, Yang Yimin, Zhou Bingxue, Wang Quan, Li Fu
School of Computer Science, Yangtze University, Jingzhou 434025, China.
School of Internet of Things Engineering, Wuxi University, Wuxi 214105, China.
Sensors (Basel). 2025 Jan 7;25(2):300. doi: 10.3390/s25020300.
The task of nucleus segmentation plays an important role in medical image analysis. However, due to the challenge of detecting small targets and complex boundaries in datasets, traditional methods often fail to achieve satisfactory results. Therefore, a novel nucleus segmentation method based on the U-Net architecture is proposed to overcome this issue. Firstly, we introduce a Weighted Feature Enhancement Unit (WFEU) in the encoder decoder fusion stage of U-Net. By assigning learnable weights to different feature maps, the network can adaptively enhance key features and suppress irrelevant or secondary features, thus maintaining high-precision segmentation performance in complex backgrounds. In addition, to further improve the performance of the network under different resolution features, we designed a Double-Stage Channel Optimization Module (DSCOM) in the first two layers of the model. This DSCOM effectively preserves high-resolution information and improves the segmentation accuracy of small targets and boundary regions through multi-level convolution operations and channel optimization. Finally, we proposed an Adaptive Fusion Loss Module (AFLM) that effectively balances different lossy targets by dynamically adjusting weights, thereby further improving the model's performance in segmentation region consistency and boundary accuracy while maintaining classification accuracy. The experimental results on 2018 Data Science Bowl demonstrate that, compared to state-of-the-art segmentation models, our method shows significant advantages in multiple key metrics. Specifically, our model achieved an IOU score of 0.8660 and a Dice score of 0.9216, with a model parameter size of only 7.81 M. These results illustrate that the method proposed in this paper not only excels in the segmentation of complex shapes and small targets but also significantly enhances overall performance at lower computational costs. This research offers new insights and references for model design in future medical image segmentation tasks.
细胞核分割任务在医学图像分析中起着重要作用。然而，由于数据集中检测小目标和复杂边界的挑战，传统方法往往无法取得令人满意的结果。因此，提出了一种基于U-Net架构的新型细胞核分割方法来克服这个问题。首先，我们在U-Net的编码器-解码器融合阶段引入了加权特征增强单元（WFEU）。通过为不同的特征图分配可学习的权重，网络可以自适应地增强关键特征并抑制无关或次要特征，从而在复杂背景下保持高精度的分割性能。此外，为了进一步提高网络在不同分辨率特征下的性能，我们在模型的前两层设计了一个双阶段通道优化模块（DSCOM）。这个DSCOM通过多级卷积操作和通道优化有效地保留了高分辨率信息，并提高了小目标和边界区域的分割精度。最后，我们提出了一种自适应融合损失模块（AFLM），它通过动态调整权重有效地平衡了不同的损失目标，从而在保持分类精度的同时，进一步提高了模型在分割区域一致性和边界精度方面的性能。2018年数据科学碗竞赛的实验结果表明，与最先进的分割模型相比，我们的方法在多个关键指标上具有显著优势。具体来说，我们的模型实现了0.8660的交并比（IOU）分数和0.9216的骰子系数（Dice）分数，模型参数大小仅为7.81M。这些结果表明，本文提出的方法不仅在复杂形状和小目标的分割方面表现出色，而且在较低的计算成本下显著提高了整体性能。这项研究为未来医学图像分割任务中的模型设计提供了新的见解和参考。
