College of Information Science and Engineering, Xinjiang University, Urumqi, China.
College of Software, Xinjiang University, Urumqi, China.
PLoS One. 2024 Mar 21;19(3):e0299392. doi: 10.1371/journal.pone.0299392. eCollection 2024.
Skin cancer is one of the most common malignant tumors worldwide, and early detection is crucial for improving its cure rate. In the field of medical imaging, accurate segmentation of lesion areas within skin images is essential for precise diagnosis and effective treatment. Due to the capacity of deep learning models to conduct adaptive feature learning through end-to-end training, they have been widely applied in medical image segmentation tasks. However, challenges such as boundary ambiguity between normal skin and lesion areas, significant variations in the size and shape of lesion areas, and different types of lesions in different samples pose significant obstacles to skin lesion segmentation. Therefore, this study introduces a novel network model called HDS-Net (Hybrid Dynamic Sparse Network), aiming to address the challenges of boundary ambiguity and variations in lesion areas in skin image segmentation. Specifically, the proposed hybrid encoder can effectively extract local feature information and integrate it with global features. Additionally, a dynamic sparse attention mechanism is introduced, mitigating the impact of irrelevant redundancies on segmentation performance by precisely controlling the sparsity ratio. Experimental results on multiple public datasets demonstrate a significant improvement in Dice coefficients, reaching 0.914, 0.857, and 0.898, respectively.
皮肤癌是全球最常见的恶性肿瘤之一，早期发现对于提高治愈率至关重要。在医学影像领域，准确地对皮肤图像中的病变区域进行分割，对于精确诊断和有效治疗至关重要。由于深度学习模型通过端到端训练能够进行自适应特征学习，因此它们已被广泛应用于医学图像分割任务中。然而，正常皮肤和病变区域之间的边界模糊、病变区域的大小和形状存在显著差异以及不同样本中的不同病变类型等挑战，给皮肤病变分割带来了重大障碍。因此，本研究引入了一种名为 HDS-Net（混合动态稀疏网络）的新型网络模型，旨在解决皮肤图像分割中边界模糊和病变区域变化的挑战。具体来说，所提出的混合编码器能够有效地提取局部特征信息，并将其与全局特征进行整合。此外，引入了动态稀疏注意力机制，通过精确控制稀疏比来减轻不相关冗余对分割性能的影响。在多个公共数据集上的实验结果表明，Dice 系数有了显著提高，分别达到了 0.914、0.857 和 0.898。
