基于三维模糊连接脉冲耦合神经网络的肾脏CT图像自动分割算法

Automatic Kidney CT Images Segmentation Algorithm Based on 3D Fuzzy Connectedness and Pulse Coupled Neural Network

3维肾脏CT图像的自动准确分割对减轻医师阅片工作量和提高计算机辅助诊断效率具有重要意义。但是,由于肾脏器官的结构复杂性以及邻近部位的灰度相似性,3维肾脏的准确分割仍具有挑战性。该文基于简化脉冲耦合神经网络(SPCNN)结构简单、参数量少的特点,结合模糊连接度(FC)算法,提出一种3维肾脏CT图像的自动分割算法。主要贡献为:(1)将SPCNN的2维模型扩展为3维模型,可以充分利用3维CT图像的层间信息;(2)提出了一种基于感兴趣区域质心的3维种子点自动生成策略,可以有效提高算法的自动分割效率;(3)实现了3维FC响应图与3维SPCNN的有效耦合。所提算法在自制数据集和公开数据集上进行了验证实验,结果表明该算法的性能优于现有的主流算法,其Dice系数、准确率、敏感度、体积误差、平均对称表面距离的平均值分别可以达到0.9095,0.9969,0.8517,0.1749和0.8536。

Automatic and accurate segmentation of 3D kidney CT image is of great significance to reduce the workload of doctors and improve the efficiency of computer-aided diagnosis.However,due to the structural complexity of kidney organs and the gray similarity of adjacent parts,accurate segmentation of 3D kidney is still challenging.Based on the characteristics of simple structure and few parameters of Simplified Pulse Coupled Neural Network(SPCNN),combined with Fuzzy Connectedness(FC)algorithm,an automatic segmentation algorithm of three-dimensional kidney CT images is proposed in this paper.The main contributions of this paper are as follows:(1)The 2D SPCNN is extended to 3D SPCNN,which can make full use of the inter-layer information of 3D CT images.(2)A 3D seed point automatic generation strategy based on the centroid of region of interest is proposed,which can effectively improve the automatic segmentation efficiency of the algorithm.(3)Effective coupling of 3D FC response map and 3D SPCNN is realized.The proposed algorithm is validated on self-made and public datasets,and the results show that the performance of the proposed algorithm is better than that of the existing mainstream algorithms.The average values of Dice coefficient,accuracy,sensitivity,volume error and average symmetric surface distance can achieve 0.9095,0.9969,0.8517,0.1749 and 0.8536 respectively.