Wei Qiao, Hu Yaoping, Gelfand Gary, Macgregor John H
Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada.
IEEE Trans Biomed Eng. 2009 May;56(5):1383-93. doi: 10.1109/TBME.2009.2014074. Epub 2009 Feb 6.
Modern multislice computed tomography (CT) scanners produce isotropic CT images with a thickness of 0.6 mm. These CT images offer detailed information of lung cavities, which could be used for better surgical planning of treating lung cancer. The major challenge for developing a surgical planning system is the automatic segmentation of lung lobes by identifying the lobar fissures. This paper presents a lobe segmentation algorithm that uses a two-stage approach: 1) adaptive fissure sweeping to find fissure regions and 2) wavelet transform to identify the fissure locations and curvatures within these regions. Tested on isotropic CT image stacks from nine anonymous patients with pathological lungs, the algorithm yielded an accuracy of 76.7%-94.8% with strict evaluation criteria. In comparison, surgeons obtain an accuracy of 80% for localizing the fissure regions in clinical CT images with a thickness of 2.5-7.0 mm. As well, this paper describes a procedure for visualizing lung lobes in three dimensions using software--amira--and the segmentation algorithm. The procedure, including the segmentation, needed about 5 min for each patient. These results provide promising potential for developing an automatic algorithm to segment lung lobes for surgical planning of treating lung cancer.
现代多层计算机断层扫描（CT）扫描仪可生成厚度为0.6毫米的各向同性CT图像。这些CT图像提供了肺空洞的详细信息，可用于肺癌治疗的更好手术规划。开发手术规划系统的主要挑战是通过识别叶间裂来自动分割肺叶。本文提出了一种叶分割算法，该算法采用两阶段方法：1）自适应裂扫以找到裂区域；2）小波变换以识别这些区域内的裂位置和曲率。在来自九名患有病理性肺部的匿名患者的各向同性CT图像堆栈上进行测试，该算法在严格评估标准下的准确率为76.7%-94.8%。相比之下，外科医生在厚度为2.5-7.0毫米的临床CT图像中定位裂区域的准确率为80%。此外，本文还描述了一种使用软件——Amira——和分割算法在三维中可视化肺叶的程序。该程序，包括分割，每个患者大约需要5分钟。这些结果为开发一种自动算法以分割肺叶用于肺癌治疗的手术规划提供了有希望的潜力。
