一种基于HRCT影像的肺结节计算机辅助检测方法

肺癌是威胁人类生命的第一杀手,如果肺癌能在早期被发现、诊断和治疗,将大大提高肺癌患者的生存率。提出了一种自动的基于高分辨率CT影像(HRCT)的肺结节计算机辅助检测(CAD)方法,可以分为肺实质分割、感兴趣区域(ROI)识别、肺结节特征提取与分类、三维可视化显示几个步骤,综合采用了自适应阈值分割、数学形态学、偏微分方程与不变矩分析等算法。通过对多组肺癌患者CT影像的测试,该方法可以帮助医生有效的提高对于肺癌疾病的诊断准确率。

Computer-aided Detection Scheme for Lung Nodule Based on HRCT Images

Lung cancer is the most common fatal malignancy in both men and women, early detection and treatment of lung cancer can greatly improve the survival rate of patient. An automatic computer-aided detection (CAD) scheme was proposed that could identify the lung nodule at an early stage from high resolution CT images (HRCT). The work is separated to several steps: the segmentation of lung parenchyma, the detection of region of interests (ROI), the feature extraction and classification, 3D visualization, which use adaptive threshold segmentation, math morphologic, Gaussian filter, Hessian matrix and moment algorithm. Though clinical trials, the computer-aided detection scheme can help physician improve the diagnosis efficiency.