Kyushu Institute of Technology, Fukuoka, Japan.
University of Occupational & Environment Health, Fukuoka, Japan.
Int J Comput Assist Radiol Surg. 2017 Oct;12(10):1789-1798. doi: 10.1007/s11548-017-1598-1. Epub 2017 May 9.
A temporal subtraction (TS) image is obtained by subtracting a previous image, which is warped to match the structures of the previous image and the related current image. The TS technique removes normal structures and enhances interval changes such as new lesions and substitutes in existing abnormalities from a medical image. However, many artifacts remaining on the TS image can be detected as false positives.
This paper presents a novel automatic segmentation of lung nodules using the Watershed method, multiscale gradient vector flow snakes and a detection method using the extracted features and classifiers for small lung nodules (20 mm or less).
Using the proposed method, we conduct an experiment on 30 thoracic multiple-detector computed tomography cases including 31 small lung nodules.
The experimental results indicate the efficiency of our segmentation method.
通过减去先前的图像来获得时间减法（TS）图像，该先前的图像被扭曲以匹配先前图像和相关当前图像的结构。TS 技术从医学图像中去除正常结构，并增强间隔变化，例如新的病变和现有异常的替代物。然而，在 TS 图像上仍然可以检测到许多伪影作为假阳性。
本文提出了一种使用分水岭方法、多尺度梯度向量流蛇和使用提取特征和分类器的检测方法对小肺结节（20 毫米或更小）进行自动分割的新方法。
使用所提出的方法，我们对包括 31 个小肺结节在内的 30 个胸部多探测器计算机断层扫描病例进行了实验。
实验结果表明了我们分割方法的效率。
