A Novel Framework for Improving Pulse-Coupled Neural Networks With Fuzzy Connectedness for Medical Image Segmentation

A pulse-coupled neural network (PCNN) is a promising image segmentation approach that requires no training. However, it is challenging to successfully apply a PCNN to medical image segmentation due to common but difficult scenarios such as irregular object shapes, blurred boundaries, and intensity inhomogeneity. To improve this situation, a novel framework incorporating fuzzy connectedness (FC) is proposed. First, a comparative study of the traditional PCNN models is carried out to analyze the framework and firing mechanism. Then, the characteristic matrix of fuzzy connectedness (CMFC) is presented for the first time. The CMFC can provide more intensity information and spatial relationships at the pixel level, which is helpful for producing a more reasonable firing mechanism in the PCNN models. Third, by integrating the CMFC into the PCNN framework models, a construction scheme of FC-PCNN models is designed. To illustrate this concept, a general solution that can be applied to different PCNN models is developed. Next, the segmentation performances of the proposed FC-PCNN models are evaluated by comparison with the traditional PCNN models, the traditional segmentation methods, and deep learning methods. The test images include synthetic and real medical images from the Internet and three public medical image datasets. The quantitative and visual comparative analysis demonstrates that the proposed FC-PCNN models outperform the traditional PCNN models and the traditional segmentation methods and achieve competitive performance to the deep learning methods. In addition, the proposed FC-PCNN models have favorable capability to eliminate inference from surrounding artifacts.