Yang Xiao, Ye Xiaojia, Zhao Dong, Heidari Ali Asghar, Xu Zhangze, Chen Huiling, Li Yangyang
School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China.
School of Statistics and Mathematics, Shanghai Lixin University of Accounting and Finance, Shanghai, China.
Front Neuroinform. 2022 Nov 1;16:1041799. doi: 10.3389/fninf.2022.1041799. eCollection 2022.
Melanoma is a malignant tumor formed by the cancerous transformation of melanocytes, and its medical images contain much information. However, the percentage of the critical information in the image is small, and the noise is non-uniformly distributed. We propose a new multi-threshold image segmentation model based on the two-dimensional histogram approach to the above problem. We present an enhanced ant colony optimization for continuous domains (EACOR) in the proposed model based on the soft besiege and chase strategies. Further, EACOR is combined with two-dimensional Kapur's entropy to search for the optimal thresholds. An experiment on the IEEE CEC2014 benchmark function was conducted to measure the reliable global search capability of the EACOR algorithm in the proposed model. Moreover, we have also conducted several sets of experiments to test the validity of the image segmentation model proposed in this paper. The experimental results show that the segmented images from the proposed model outperform the comparison method in several evaluation metrics. Ultimately, the model proposed in this paper can provide high-quality samples for subsequent analysis of melanoma pathology images.
黑色素瘤是由黑素细胞癌变形成的恶性肿瘤，其医学图像包含大量信息。然而，图像中关键信息的占比小，且噪声分布不均匀。针对上述问题，我们提出了一种基于二维直方图方法的新型多阈值图像分割模型。在所提出的模型中，基于软包围和追逐策略，我们提出了一种用于连续域的增强蚁群优化算法（EACOR）。此外，EACOR与二维卡普尔熵相结合以搜索最优阈值。对IEEE CEC2014基准函数进行了实验，以衡量所提出模型中EACOR算法可靠的全局搜索能力。此外，我们还进行了多组实验来测试本文所提出的图像分割模型的有效性。实验结果表明，所提出模型分割出的图像在多个评估指标上优于对比方法。最终，本文所提出的模型可为后续黑色素瘤病理图像分析提供高质量样本。
