基于sigmoid边缘模型的低对比度图像分割算法研究  

Improved Segmentation of Low-Contrast Lesions Using Sigmoid Edge Model

作　　者：丁力 周啸虎[1] 陈宇辰[1] 张子齐[1] DING Li;ZHOU Xiaohu;CHEN Yuchen;ZHANG Ziqi(Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing Jiangsu 210006, China)

机构地区：[1]南京医科大学附属南京医院(南京市第一医院)放射科,江苏南京210006

出　　处：《中国医疗设备》2017年第11期66-70,81,共6页China Medical Devices

基　　金：国家自然科学青年基金(81601477)

摘　　要：目的本文采用sigmoid函数模拟平滑噪声强度轮廓,提出一种图像分割混合算法,并将其用于低对比度的CT/MR肿瘤图像。方法首先,联合使用支持向量机、分水岭和离散数据逼近等算法按肿瘤大小进行分类初步分割;然后,采用sigmoid边缘模型拟合的边缘轮廓;最后,根据模型测试参数确定病灶的准确边界。分割结果采用医学电脑影像及电脑辅助涉入的国际研讨会会议工作组提出的评价体系进行评估。结果选用人工合成图像和临床CT/MR图像进行仿真实验。敏感性测试确定了分割算法的最佳参数:逼近阈值为15,分块数目M为12,dgap为4,邻域矩阵大小为3×3;本文算法能精确分割不同噪声水平图像,且各项评价指标的标准差均<1;对于临床实例图像,基于本文方法所得分割图像的VOE和RVD,第一组为28.21%和19.20%,第二组为7.62%和13.45%,均明显小于图论算法和水平集方法。结论本文提出的图像分割混合算法能精确分割不同特性、不同尺寸的肿瘤病灶,在噪声环境和临床实例中均表现出稳定性、优越性和普适性,具有较高的临床应用价值。Objective We used a smoothed noisy intensity profile by a sigmoid function and employ it to discover the true location of CT/MR tumor boundary more accurately.Methods A novel combination of the support vector machine,watershed,and scattered data approximation algorithms were employed to initially segment a tumor.Small and large abnormalities were treated distinctly.Next,the proposed sigmoid edge model was fitted to the normal profile of the border.The estimated parameters of the model were then utilized to find true boundary of a tissue.The quantitative metrics were evaluated by liver segmentation challenge proposed by Medical Image Computing and Computer Assisted Intervention.Results We extensively evaluated our method using synthetic images(contaminated with varying levels of noise)and clinical CT/MR data.Based on the sensitivity analysis results,we decided to set the threshold for data approximation,number of sectors and dgap as15,12and4,respectively.Visually and quantitatively experimental results indicated that VOE and RVD of the proposed method were28.21%and19.20%in the first team and7.62%and13.45%in the second team,which were superior to the existing methods.Conclusion For different size and any types of tumors,the proposed method can obtain more efficient and accurate segmentation results.It can also provide better robustness,superiority,and pervasiveness in the noise environment and clinical applications.

关 键 词：sigmoid边缘模型 图像分割 离散数据 肿瘤分割 分水岭算法 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]